ESTIMATING TRAVELER VOLUME BY EVALUATING AERIAL IMAGES

BACKGROUND

Within the field of computing, many scenarios involve an estimation of a volume of travelers in an area, such as a number of vehicles in a road; a transit pattern of visitors in a parking lot of a business; the movement of a population of pedestrians at an event; or a migratory pattern of a set of wildlife. In such scenarios, the traveler volume, as well as other properties such as the direction, speed, and travel patterns of the travelers, may be estimated through a variety of techniques, such as human observation; tagging and tracking of individual travelers; and cameras or other detectors positioned throughout the area. However, such techniques may involve significant costs in terms of equipment purchase, deployment, monitoring, and maintenance, and may also exhibit insufficient accuracy and/or timeliness in the collected data about the traveler volume. For example, it may be desirable to adjust transit control devices in an area in order to balance a flow of vehicular traffic. However, data about the volume and fluctuation of vehicular traffic in various areas may not be attainable in a reliable and rapid manner using such techniques, which may limit the accuracy and responsiveness of transit control measures.

SUMMARY

This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key factors or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

A volume of travelers in an area may be evaluated through the use of aerial imaging. In particular, the recent development of drone technology has improved the affordability and sophistication of such devices that an aerial drone may capture aerial images of the area from an aerial perspective. Additionally, the development of object recognition machine vision techniques enables the recognition of objects in an image in a comparatively reliable and computationally efficient manner. The conjunction of these technological developments enables the provision of new techniques for estimating a volume of travelers in an area.

As a first example of the techniques presented herein, a device may estimate traveler volume in area. The device may receive an aerial image of the area captured from an aerial perspective; invoke an image evaluator with the aerial image to recognize travelers in the aerial image; count the travelers recognized in the aerial image; and estimate the traveler volume of the area according to the count of the travelers and an area size of the area depicted in the aerial image, in accordance with the techniques presented herein.

As a second example of the techniques presented herein, an aerial device, such as a drone, may evaluate and report to a transit service a traveler volume of an area. The aerial device may navigate to an aerial perspective of the area, and may then, using a camera, capture an aerial image of the area from the aerial perspective. The aerial device may also invoke an image evaluator with the aerial image to recognize travelers in the aerial image, and count the travelers recognized in the aerial image. The aerial device may then transmit the count of the travelers to the transit service, in accordance with the techniques presented herein.

As a third example of the techniques presented herein, a transit server may be configured to estimate a traveler volume of an area. The transit server may receive an aerial image of the area from an aerial perspective, and apply an image evaluator to the aerial image to recognize travelers in the image evaluator, and to count the travelers recognized in the aerial image. The transit server may then estimate the traveler volume of the area according to the count of the travelers and an area size of the area depicted in the aerial image, in accordance with the techniques presented herein.

To the accomplishment of the foregoing and related ends, the following description and annexed drawings set forth certain illustrative aspects and implementations. These are indicative of but a few of the various ways in which one or more aspects may be employed. Other aspects, advantages, and novel features of the disclosure will become apparent from the following detailed description when considered in conjunction with the annexed drawings.

DESCRIPTION OF THE DRAWINGS

FIG. 1 is an illustration of an example scenario featuring an estimation of a traveler volume in an area.

FIG. 2 is an illustration of an example scenario featuring an estimation of a traveler volume in an area in accordance with the techniques presented herein.

FIG. 3 is an illustration of an example method of estimating a traveler volume in an area, in accordance with the techniques presented herein.

FIG. 4 is an illustration of an example method of causing an aerial device, such as a drone, to estimate and report a traveler volume in an area, in accordance with the techniques presented herein.

FIG. 5 is an illustration of an example system for estimating a traveler volume in an area, in accordance with the techniques presented herein.

FIG. 6 is an illustration of an example computer-readable medium comprising processor-executable instructions configured to embody one or more of the provisions set forth herein.

FIG. 7 is an illustration of an example technique for classifying respective travelers in an area, in accordance with the techniques presented herein.

FIG. 8 is an illustration of an example technique for tracking traveler volume and transit patterns in an area over time, in accordance with the techniques presented herein.

FIG. 9 is an illustration of an example technique for tracking a transit pattern of an individual traveler while also anonymizing the individual traveler, in accordance with the techniques presented herein.

FIG. 10 is an illustration of an example technique for controlling a transit pattern in a region using traveler volume estimated through aerial images, in accordance with the techniques presented herein.

FIG. 11 is an illustration of an example computing environment wherein one or more of the provisions set forth herein may be implemented.

DETAILED DESCRIPTION

The claimed subject matter is now described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the claimed subject matter. It may be evident, however, that the claimed subject matter may be practiced without these specific details. In other instances, structures and devices are shown in block diagram form in order to facilitate describing the claimed subject matter.

A. Introduction

FIG. 1 is an illustration of an example scenario 100 featuring techniques for estimating a volume of travelers 104 in an area 102, such as vehicles traveling on a road during a heavy transit volume period. In this example scenario 100, it may be desirable to estimate the volume of travelers 104 passing through the area 102 over time, e.g., in order to assess patterns in the utilization of the road; to assess a severity of a traffic congestion problem, such as the effect of a vehicular accident 106 on the flow of traffic on the road; to allocate development resources in an efficient manner; to allocate a toll over the volume of travelers 104; and/or to enable transit control systems to promote or discourage travel through the area 102 in order to promote balance of the travel pattern of travelers 104 throughout a region.

To this end, various techniques may be utilized to estimate the traveler volume of travelers 104 in the area 102. As a first such example, a transit service 110 may deploy a set of roadside sensors 108, such as transit cameras or sensors that count the number of vehicles passing a particular position in the area 102. A multitude of roadside sensors 108 may be utilized to detect the transit flow of the travelers 104 over time, e.g., deploying roadside sensors 108 at regular intervals in the area 102, and having all such roadside sensors 108 report about the detected transit patterns to the transit service 110. An alternative to roadside sensors 108 involves embedding pressure-sensitive equipment in the surface of a road that detects the passage of travelers 104. As a second such example, respective travelers 104 may be individually tagged with devices that report their transit patterns to the transit service 110. The reported data may be extrapolated from the small subset of travelers 104 that report such data, to the full population of travelers 104 in the area 102. In addition to a count of the travelers 104 in the area 102, the roadside sensors 108 and/or traveler devices may report other data to the transit service 110, such as the direction, location, speed, and/or acceleration of the respective travelers 104. As a third such example, an individual 112 may observe the area 102 and provide an approximate estimate of the traveler volume in the area 102. These and other techniques may be utilized to estimate the traveler volume of travelers 104 in the area 102.

Although such techniques may enable the estimation of traveler volume, several disadvantages may arrive therefrom. As a first such example, these methods may entail significant expense in terms of equipment (e g, implementing hundreds of fixed roadside and road-embedded sensors may entail significant costs for equipment acquisition, deployment, operation, monitoring, and maintenance), and the use of individuals 112 may entail a disproportionately large hourly cost. As a second such example, these methods may be prone to error; e.g., an individual 112 may generate inaccurate and disproportionate estimates, and a first estimate by a first individual 112 of an area 102 may conflict with a second estimate by a second individual 112 for the same area 102. Roadside sensors 108 and/or pressure-sensitive equipment may exhibit inaccuracy (e.g., the roadside camera may be partially obstructed by debris or weather elements, and pressure-sensitive equipment may count an 18-wheel vehicle several times while failing to count lighter vehicles such as motorcycles), and a transit service 110 that utilizes such equipment may produce incorrect traveler volume estimates. Estimates based on information transmitted by vehicles 104 may be contingent upon additional information about the proportion of such reporting travelers 104 in the area 102, which may be difficult to determine with certainty, and disparities in such information or assumptions thereof may lead to inaccurate estimates. As a third such example, these techniques may provide traveler volume data in a delayed manner; e.g., a portion of a transit service 110 deployed in a remote area may not have a direct connection with a transit monitoring station, and may only report data sporadically, only in lengthy intervals, or only when visited by transit control personnel to retrieve the data. Therefore, the collection of such data may be suitable for surveying or historical study, but may be too slow for transit control management. As a fourth such example, such equipment methods may be fixed at a particular area 102, and traveler volume information about other areas 102 within a region may involve additional equipment costs, costly and time-consuming redeployment of existing equipment, and/or a significant delay to implement. These and other disadvantages may arise from the estimation of traveler volume using the techniques depicted in the example scenario 100 of FIG. 1.

B. Presented Techniques

FIG. 2 is an illustration of an example scenario 200 featuring techniques for achieving an estimation 212 of traveler volume 216 utilizing an aerial device 202, such as a drone, and a machine vision technique 208, such as object recognition applicable to an aerial image 206 of the area 102, in accordance with the techniques presented herein.

In this example scenario 200, an aerial device 202, such as a drone, is navigated to an aerial perspective over the area 102, and uses a camera 204 to capture an aerial image 206 of the area 102. The aerial image 206 of the area may be evaluated by an image evaluator 208, which uses machine vision technique (e.g., an object recognition technique that is capable of identifying the travelers 104 from an aerial perspective) to achieve an object recognition 210 of the travelers 104 presented in the aerial image 206. A device may then count the travelers 104 recognized in the aerial image 206, which may be compared with an area size 216 of the area 102 depicted in the aerial image 206. Based on the object recognition 210 of the travelers 104 in the aerial image 206, an estimate 212 of traveler volume 216 in the area 102 may be achieved by identifying a count 214 of the travelers 210 from the object recognition 210 and the area size 216 of the area 102 to generate an estimate 212 of the traveler volume 218 of the travelers 104 in the area 102. Additional information may also be generated from the capturing and comparison one or more images 206, such as the determination of the direction, speed, acceleration, and transit patterns of the travelers 104 over time. The estimates 212 of the traveler volume 218 may be utilized, e.g., to evaluate transit patterns of the travelers 104 through the area 102; to identify problems arising in such transit patterns, such as causes of traffic congestion and safety risks; to operate transit control devices in the area 102 in order to adjust the transit of the travelers 104, such as transit signals and tolls; and/or to allocate the deployment of development resources, such as adding and/or expanding roads, bridges, bypasses, and public transit systems to reduce patterns of traffic congestion and to increase the traveler capacity of the region. Many such uses may be devised for the estimates 212 of traveler volume 218 in the area 102 collected in accordance with the techniques presented herein.

C. Technical Effects

The techniques presented herein may provide a variety of technical effects in the scenarios provided herein.

As a first such example, the techniques provided herein may enable the collection of estimates 212 of traveler volume 218 in a comparatively cost-effective manner as compared with other techniques, such as those illustrated in the example scenario 100 of FIG. 1. For example, the costs of acquiring and operating aerial devices, such as drones, to capture and relay aerial images 206 of an area 102, and also the computational resources for applying a machine vision technique such as object recognition to recognize and count the travelers 104 in an image 210, are more affordable due to rapid development of these areas of technology and an expansion of commercial offerings. For example, such equipment does not have to be developed for the specialized purpose of estimating traveler volume 218 that raises the equipment costs, but may be acquired as general-purpose equipment and reconfigured for the task of estimating traveler volumes. Moreover, the deployment and return of aerial devices 202 throughout the region 102 may reduce the exposure of such equipment to adverse weather that damages and/or wears out such equipment, as compared with fixed equipment such as roadside and road-embedded equipment. Moreover, the cost of deploying an aerial device 202 over an area 102 may be significantly less than for portable equipment that is transported to the area 102 by transit service personnel.

As a second such example, the techniques provided herein may achieve a more estimate 212 of traveler volume 218 than may be achieved by other techniques. For example, aerial images 206 captured from an aerial perspective may be less prone to visual obstruction than equipment positioned on the ground of the area 102, and less prone to errors of subjectivity as compared with estimates produced by individuals 112.

As a third such example, the techniques provided herein may enable a more rapid and flexible collection of estimates 212 of traveler volume 218 than may be achieved by other techniques. For example, if an estimate 212 of traveler volume 218 is desired for a particular area 102, an aerial device 202 may be navigated to the area 102 to collect and return the desired estimate 212, and the aerial devices 202 may be readily redeployed to obtain an estimate 212 of traveler volume 218 for a second area 102. By contrast, portable equipment to the area 102 may have to be deployed by transit service personnel to the area 102, as well as activated and configured, and then later retrieved by such personnel, thereby incurring significant delays (particularly if such transit service personnel are also delayed in deploying the equipment due to heavy traveler volume 218 in the area 102). Additionally, equipment that is deployed to a remote area may not be continuously connected to the transit service 110, such that data may be received from the equipment only sporadically, only over long intervals, and/or only when transit service personnel may visit the equipment to retrieve the data. These and other technical advantages may arise from the estimation of traveler volume 218 in accordance with the techniques presented herein.

D. Example Embodiments

FIG. 3 presents a first example embodiment of the techniques presented herein, illustrated as an example method 300 of estimating a traveler volume 218 of travelers 104 in an area 102. The example method 300 may be implemented on a device having a processor and an image evaluator 208, such as a machine vision technique that uses object recognition to identify travelers 104 in an aerial image 206. The example method 300 may be implemented, e.g., as a set of instructions stored in a memory component of the device (e.g., a memory circuit, a platter of a hard disk drive, a solid-state memory component, or a magnetic or optical disc) that, when executed by the processor of the device, cause the device to perform the techniques presented herein.

The example method 300 begins at 302 and involves executing 304 the instructions on the processor. Specifically, the instructions cause the device to receive 306 an aerial image 206 of the area 102 captured from an aerial perspective. The instructions also cause the device to invoke 308 the image evaluator 208 with the aerial image 206 to recognize travelers 104 in the aerial image 206. The instructions also cause the device to count 310 the travelers 104 recognized in the aerial image 206. The instructions also cause the device to estimate 312 the traveler volume 218 of the area 102 according to the count 214 of the travelers 104 and an area size 216 of the area 102 depicted in the aerial image 206. In this manner, the example method 300 causes the device to generate an estimate 212 of traveler volume 218 in accordance with the techniques presented herein, and so ends at 314.

FIG. 4 presents a second example embodiment of the techniques presented herein, illustrated as an example method 400 of causing an aerial device 202 to estimate a traveler volume 218 of travelers 104 in an area 102. The example method 400 may be implemented on an aerial device 202, such as a drone, that features a processor, a camera 204, and an image evaluator 208 that is capable of applying a machine vision technique involving object recognition to an aerial image 206 to identify travelers 104 depicted in the aerial image 206. The example method 300 may be implemented, e.g., as a set of instructions stored in a memory component of the aerial device 202 (e.g., a memory circuit, a platter of a hard disk drive, a solid-state memory component, or a magnetic or optical disc) that, when executed by the processor of the aerial device 202, cause the aerial device 202 to perform the techniques presented herein.

The example method 400 begins at 402 and involves navigating 404 the aerial device 202 to an aerial perspective of the area 102. The example method 400 also involves executing, on the processor of the aerial device 202, instructions that cause the aerial device 202 to perform a variety of tasks. As a first such task, the instructions cause the aerial device 202 to, using the camera 204, capture 408 an aerial image 206 of the area 102 from the aerial perspective. As a second such task, the instructions cause the aerial device 202 to invoke 410 the image evaluator 208 with the aerial image 206 to recognize travelers 104 in the aerial image 206. As a third such task, the instructions cause the aerial device 202 to count 412 the travelers 104 recognized in the aerial image 206. As a fourth such task, the instructions cause the aerial device 202 to transmit 414 the count 214 of the travelers 104 to the transit service 110. The example method 400 further involves estimating 416 the traveler volume 218 (e.g., by the aerial device 202 or a device of the transit service 110) according to the count 214 of the travelers 104 recognized in the aerial image 206 and an area size 216 of the area 102 depicted in the aerial image 206. In this manner, the example method 400 of FIG. 4 achieves the estimation of the traveler volume 218 of travelers in the area 102 in accordance with the techniques presented herein, and so ends at 418.

FIG. 5 presents an illustration of an example scenario 500 featuring a third example embodiment of the techniques presented herein, illustrated as an example server 502 comprising a system 510 that generates an estimate 212 of traveler volume 218 of travelers 104 in an area 102. The example system 510 may be implemented, e.g., on a server 502 having a processor 504, a communicator device that receives an aerial image 206 of the area 102 captured by a camera 204 of an aerial device 202 from an aerial perspective. Respective components of the example system 510 may be implemented, e.g., as a set of instructions stored in a memory 508 of the server 502 and executable on the processor 504 of the server 502, such that the interoperation of the components causes the server 502 to operate according to the techniques presented herein.

The example system 510 comprises an image evaluator 512, which recognizes travelers 104 in the aerial image 206 (e.g., using a machine vision object recognition technique), and counts the travelers 104 recognized in the aerial image 206. The example system 510 further comprises a traveler volume estimator 514, which estimates the traveler volume 218 of the area 102 according to the count 214 of the travelers 104 and an area size 216 of the area 102 depicted in the aerial image 206. In this manner, the interoperation of the components of the example system 510 enables the server 502 to estimate the traveler volume in accordance with the techniques presented herein.

Still another embodiment involves a computer-readable medium comprising processor-executable instructions configured to apply the techniques presented herein. Such computer-readable media may include, e.g., computer-readable storage media involving a tangible device, such as a memory semiconductor (e.g., a semiconductor utilizing static random access memory (SRAM), dynamic random access memory (DRAM), and/or synchronous dynamic random access memory (SDRAM) technologies), a platter of a hard disk drive, a flash memory device, or a magnetic or optical disc (such as a CD-R, DVD-R, or floppy disc), encoding a set of computer-readable instructions that, when executed by a processor of a device, cause the device to implement the techniques presented herein. Such computer-readable media may also include (as a class of technologies that are distinct from computer-readable storage media) various types of communications media, such as a signal that may be propagated through various physical phenomena (e.g., an electromagnetic signal, a sound wave signal, or an optical signal) and in various wired scenarios (e.g., via an Ethernet or fiber optic cable) and/or wireless scenarios (e.g., a wireless local area network (WLAN) such as WiFi, a personal area network (PAN) such as Bluetooth, or a cellular or radio network), and which encodes a set of computer-readable instructions that, when executed by a processor of a device, cause the device to implement the techniques presented herein.

An example computer-readable medium that may be devised in these ways is illustrated in FIG. 6, wherein the implementation 600 comprises a computer-readable medium 602 (e.g., a CD-R, DVD-R, or a platter of a hard disk drive), on which is encoded computer-readable data 604. This computer-readable data 604 in turn comprises a set of computer instructions 606 configured to operate according to the principles set forth herein. As a first such example, the computer instructions 606 may cause the device 610 to utilize a method of estimating a traveler volume 218 of travelers 104 in an area 102, such as the example method 300 of FIG. 3. As a second such example, the computer instructions 606 may provide a method of causing an aerial device 202 to estimate a traveler volume 218 of travelers 104 in an area 102, such as the example method 400 of FIG. 4. As a third such example, the computer instructions 606 may provide a system for estimating a traveler volume 218 of travelers 104 in an area 102, such as the example system 510 in the example scenario 500 of FIG. 5. Many such computer-readable media may be devised by those of ordinary skill in the art that are configured to operate in accordance with the techniques presented herein.

E. Variable Aspects

The techniques discussed herein may be devised with variations in many aspects, and some variations may present additional advantages and/or reduce disadvantages with respect to other variations of these and other techniques. Moreover, some variations may be implemented in combination, and some combinations may feature additional advantages and/or reduced disadvantages through synergistic cooperation. The variations may be incorporated in various embodiments (e.g., the example method 300 of FIG. 3; the example method 400 of FIG. 4; the example system 510 of FIG. 5; and the example computer-readable storage device 602 of FIG. 6) to confer individual and/or synergistic advantages upon such embodiments.

E1. Scenarios

A first aspect that may vary among embodiments of these techniques relates to the scenarios wherein such techniques may be utilized.

As a first variation of this first aspect, the techniques presented herein may be used with many types of travelers 104, including vehicles such as automobiles, motorcycles, trucks, trains, buses, watercraft, aircraft, drones, and spacecraft; pedestrians, such as individuals in a crowd; and migratory wildlife. The techniques may also be utilized to estimate traveler volume 104 in many environments, such as a roadway, highway, parking lot, sidewalk, dirt or grass path, waterway, airspace, and an enclosed structure such as a shopping mall.

As a second variation of this first aspect, the volume of travelers in an area may be observed and calculated as many types of measurements, such as a count of travelers; a density of travelers in an area; a size or mass of the collection of travelers in an area; and/or a change or trend in the number of travelers in an area.

As a third variation of this first aspect, the techniques provided herein may utilize a variety of aerial devices 202. Such aerial devices 202 may be capable of remaining stationary while airborne, such as a helicopter or balloon, or only of traveling to maintain lift, such as an airplane, and may travel at a variety of speeds, Such aerial devices 202 may also be powered by various power sources, such as fuel, a chemical or electric energy storage device, sunlight, or water or moisture, and may either collect energy while remaining in the environment or may return to the transit service for refueling.

As a fourth variation of this first aspect, many variations in the architecture of the provided techniques may be selected. As a first such example, the aerial device 202 may be operated autonomously (e.g., a drone that includes an autonomous navigation control system) and/or by a human operator, either on a continuous basis (e.g., a wireless communication device may enable the human operator to interact with, control, and/or receive data from the aerial device 202 on a continuous basis, either remotely or while positioned in the area 102) or a periodic basis (e.g., the human operator may provide instructions to an otherwise autonomous aerial device 202, such as a selection of an area 102 for which to evaluate traveler volume 26, and may later interact with the aerial device 202 upon its return to receive the estimate 212 of the traveler volume 218 and to reprogram the aerial device 202 for redeployment). As a second such example, a portion of the image evaluation and/or traveler volume estimation may be distributed among one or more aerial devices 202 and one or more ground-based devices, such as servers utilized by the transit service 110 during the estimation of traveler volume.

As a fifth variation of this first aspect, an aerial vehicle 202 may capture an aerial image 206 of an area 102 using a variety of imaging techniques, such as different portions of the electromagnetic spectrum (e.g., full-spectrum imaging; monochromatic imaging; thermal imaging in the infrared range; and/or lidar detection), as well as other forms of imaging, such as sonar or radar imaging. Such aerial images 206 may also be captured at a variety of zoom and/or focus levels, and may be captured as a single aerial image 206 or a succession of aerial images 206 in the same or different image modalities at the same or different times, such as a monochromatic image and a thermal image, which may be compared to correlate different concurrent aerial images 206 for greater accuracy or information, and/or to detect changes in the transit patterns of the travelers 104 over time, Many such scenarios may be devised to which the techniques presented herein may be advantageously utilized.

E2. Aerial Image Evaluation

A second aspect that may vary among embodiments of the techniques presented herein involves the manner of evaluating the aerial image 206 to perform the recognition and counting of the travelers 104 depicted therein.

As a first variation of this second aspect, many image processing techniques may be utilized to recognize and count the travelers 104 in the aerial image 206. For example, the machine vision community has devised an extensive variety of object recognition techniques, based upon spectral analysis, shape identification (e.g., identifying discrete geometric shapes in the image 104), comparison with prototypical images of recognizable options, and motion evaluation through a comparison of images captured over time. Such image processing may also utilize a variety of machine learning techniques, such as artificial neural networks, genetic algorithms, and Bayesian classifiers, which may be developed and trained to recognize a particular set of shapes and/or objects in an image, such as aerial views of travelers 104, and then invoked with the aerial image 206 to recognize such objects depicted in the aerial image 206.

FIG. 7 presents an illustration of an example scenario 700 featuring a second variation of this second aspect, wherein a machine vision technique, using an object classifier 704, may be used to identify travelers 104 in a location 102 such as a parking lot of a business 702. In this example scenario 700, the object classifier 704 has been developed to recognize the aerial appearance of travelers 104 appearing in an aerial image 206 captured from an aerial perspective by an aerial device 202, such as a drone. The object classifier 704 may comprise, e.g., an artificial neural network 710 that has been provided with a training set that maps prototypical aerial depictions 708 of travelers 104 in aerial images 704 to an identification thereof, and has been trained to achieve such recognition for any aerial image 206. Moreover, in this example scenario 700, the artificial neural network 710 has been trained to classify respective travelers 104 according to a traveler type 706; e.g., a first aerial depiction 708 of a traveler 104 may be provided that maps to a first traveler type 704, such as a truck, and a second aerial depiction 708 may be provided that maps to a second traveler type 704, such as an automobile. The object classifier 704 may be applied to an aerial image 206 of the area 102 to detect the travelers 104 within, thereby generating an estimate 212 of traveler volume 218 (e.g., the volume of vehicles in the parking lot of the business 702) as compared with the capacity of the parking lot). Moreover, the object classifier 704 may classify the respective travelers 104 according to a traveler type 706, and may generate more detailed estimates 212 of the numbers and/or proportion of the respective traveler types 706 among the population of recognized travelers 104. In this manner, an object classifier 704 may utilize an artificial neural network 710 to recognize, count, and/or classify the travelers 104 depicted in an aerial image 206 of an area 102 in accordance with the techniques presented herein.

As a third variation of this second aspect, in addition to generating an estimate 212 of the traveler volume 218 of an area 102, the techniques presented herein may be utilized to generate additional information about the transit patterns of travelers 104 in the area 102. As a first such example, in addition to estimating the traveler volume 218, an image evaluator 208 may also identify a transit direction and/or transit speed of the respective travelers 104 recognized in the area 102 (e.g., by identifying the same traveler 104 in a succession of aerial images 206, and then comparing the positions and orientation of the traveler 104 in the successive aerial images 206). Such identification may be performed for individual travelers 104, and/or for a group or population of travelers 104 en masse (e.g., determining that the traveler body together is moving in a direction and/or at a particular transit speed). Further evaluation may be utilized to determine transit patterns among the travelers 104, e.g., sub-groups within a population of travelers 140 that are moving and/or remaining stationary together through the area 102. Estimates 212 of traveler volume 218 and transit patterns may also be aggregated in various ways; e.g., a period may be determined during which the aerial image 206 of the area 102 was captured, and the estimate 212 of the traveler volume 218 for the period to a data set identifying a typical traveler volume for the area 102 during respective periods.

FIG. 8 presents an illustration of an example scenario involving a recognition of a transit pattern among travelers 104 within an area 102, such as vehicles and/or individuals depicted at different times in aerial images 206 of a parking lot of a business 702. In this example scenario 104, the aerial device 202 captures a succession of aerial images 206 at various times 802, and, in addition to estimating the traveler volume 218 within the area 102, may compare the aerial images 206 to detect transit patterns among such visitors, such as fluctuations in the parking capacity of the area 102 during different periods (e.g., on different days or at different times of day), and the direction of travel of travelers 104 within the area 102. Additionally, a particular traveler 804 may be identified as of interest, and the transit of the traveler 804 in the area 102 may be evaluated by applying the image evaluator 208 to recognize the traveler 804 in the succession of aerial images 206. For example, the image evaluator 208 may determine the arrival of the traveler 804 at a second time 802 due to its first appearance in a second aerial image 206 captured at the second time 802; a transit pattern 806 of the traveler 804 in the area 102, according to a comparison of the position of the traveler 804 in the succession of aerial images 206; and/or a departure of the traveler 804 from the area 102. Such information may inform a variety of evaluations, such as the sufficiency of the parking capacity of the area 102; a typical duration 808 of a presence of a traveler 104 within the area 102; and/or safety issues that may arise due to transit patterns of the travelers 104 through the area 102, in accordance with the techniques presented herein.

FIG. 9 presents an illustration of an example scenario 900 featuring a third variation of this second aspect, wherein a selected traveler 802 may be tracked over time using an aerial device 202, in a manner that is sensitive to the privacy of an individual. In this example scenario 900, a selected traveler 804 is identified for which a transit pattern of the selected traveler 804 through a particular area 102 is to be evaluated over successive periods, such as correlating information about respective visits of the selected traveler 804 to a business 702. An image evaluator 208 may be able not only to recognize the traveler 804 as a traveler 104 in successive aerial images 206 taken at different times, but as the same selected traveler 804 during multiple instances of transit through the area 102, e.g., by recognizing, in a particular portion 902 of an aerial image 206, a visual feature 904 of the selected traveler 804 that reveals the identity of the selected traveler 804 (e.g., a facial feature of an individual, or a license plate of a vehicle). The transit service 110 may therefore generate comparative information about the successive instances of transit of the selected traveler 804 through the area 102. Because the privacy interests of the individual may mitigate toward removal of the visual feature 904 from stored aerial images 206, an anonymizer 906 may alter the portion 902 of the aerial image 206 comprising the visual feature 904 revealing the identity of the selected traveler 804, and may generate an anonymized aerial image 908 that obscures 910 the visual feature 904. Additionally, the identity of the individual 804 may be consistently tracked according to an anonymous identifier, such as a unique number that is arbitrarily assigned to the selected traveler 804 to enable consistent tracking without revealing the identity of the selected traveler 804. For example, the transit service 110 may, upon detecting the selected traveler 804 in an aerial image 206, determine whether the identity of the selected traveler 804 is associated with an anonymous identifier 912, and if not, may assign a new anonymous identifier 912 to the selected traveler 804. The transit service 110 may thereafter store an activity record 914 of the selected traveler 804 in aerial images 206 according to the anonymous identifier 912, thus generating an activity record 914 that documents the transit of the selected traveler 804 in the area 102 while not revealing the identity of the selected traveler 804.

As a fourth variation of this second aspect, the estimate 212 of traveler volume 218 within an area 102 may provide further information about the nature of the traveler volume 218 and the area 102, such as an event occurring within the area 102. For example, the traveler volume 218 for a particular area 102 may be compared with a traveler volume threshold (e.g., a maximum typical traveler volume 218 for the area 102), such that an estimate 212 above the traveler volume threshold may prompt further evaluation of the traveler volume 218 (e.g., upon determining that the traveler volume exceeds the traveler volume threshold, the transit service 110 may identify a transit event occurring in the area 102, such as the development of traffic congestion or an unexplained gathering of travelers 104 in a particular area 102). Additionally, respective transit events may be of a transit event type selected from a transit event type set (e.g., traffic congestion arising on a road due to a vehicular accident, construction, or an obstruction of the road by a weather event such as flooding). The transit service 110 (e.g., a server and/or aerial vehicle 202) may, using the aerial image 206 of the area 102, identify the transit event type of the event, and classify the transit event according to the transit event type. Many such types of information may be derived from the invocation of various image evaluators 208 with aerial images 206 of an area 102 in the context of estimating traveler volume 218 in accordance with the techniques presented herein.

E3. Uses of Traveler Volume Estimates

A third aspect that may vary among embodiments of the techniques presented herein involves uses of the estimates 212 of traveler volume 218 generated in accordance with the techniques presented herein.

As a first variation of this third aspect, the area 102 may be associated with an environment (e.g., a wildlife preserve, a residential neighborhood, an industrial park, or an indoor environment such as a mall), and estimates 212 of the traveler volume 218 may inform an environmental impact evaluator that evaluates an environmental impact of the traveler volume 218 on the environment. For example, estimates 212 of traveler volume 218 may be correlated with wildlife stress and/or population indicators, transit times, pollution levels, quality of life in a residential neighborhood, and/or commercial business volume.

As a second variation of this third aspect, the area 102 may be a target for further development, e.g., expansion of a road network and/or pedestrian path area to increase capacity, improve traveler safety, and/or reduce volatility of traffic congestion. Estimates 212 of traveler volume 218 in the area 102 may be utilized to allocate resources for such development, e.g., determine where and when transit patterns create issues within the area 102, such that development resources may be allocated to expand capacity in areas 102 where such expansion is likely to ameliorate such problems.

FIG. 10 is an illustration of an example scenario 1000 featuring a third variation of this third aspect, wherein a transit service 110 utilize a transit control adjuster to adjusts a transit restriction imposed by the transit control, in proportion with the estimate 212 of the traveler volume 218 of the area 102. In this example scenario 1000, an area 102 is associated with transit controls that impose transit restrictions on the respective travelers 104 of the area 102. A transit service 110 may be tasked with controlling such transit in order to reduce traffic congestion in a region 1002, and may do so by utilizing transit controls that persuade travelers 104 to take a detour (e.g., detouring travelers from a primary route within the region 1002 to a secondary route that may be longer, but that may have less traffic congestion). For example, at a first time 1008, aerial devices 202 may be deployed above each area 102 to generate estimates 212 of traveler volume 218 at the first time 1008, while a transit toll 1004 is assessed to each traveler 104 in the area 102. The estimates 212 of traveler volume 218 may indicate that the first area 102 exhibits significant traffic congestion, while the second area 102 exhibits comparatively light traveler volume 218. In order to reduce this disparity, at a second time, the transit tolls 1004 for the respective areas 102 may be adjusted (e.g., increasing the toll 1004 for the first area 102 while reducing the toll 1004 for the second area 102) in order to persuade travelers 104 to choose a detour through the second area 102. The transit system 110 may transmit a signal to transit control devices that collect the tolls 1004 from the travelers 104, and may therefore instruct the transit control devices to adjust the tolls 1004 in proportion with the estimate 212 of the traveler volume 218 in each area 102. Additional estimates 212 of traveler volume 218 may continue to be collected, and the adjustment of the tolls 1004 may reveal modest, but not adequate, redistribution of traveler volume 218. Accordingly, at a third time 1012, a second transit control device 1006 may be adjusted, e.g., a stoplight that periodically restricts entry to the first area 102, and thereby reduces traveler volume 218 therein. For example, where a detour area exist to the transit service 110 present to travelers an alternative to traveling through an area 102 having a high traveler volume 218, and is associated with a transit control that imposes a transit restriction on the respective travelers of the detour area, the transit system 110 may utilize a detour transit control adjuster that adjusts the transit restriction of the transit control in proportion with the traveler volume 218 of the area 102.

As a fourth variation of this third aspect, a transit service 202 may further comprise a transit event notifier, which, when the traveler volume exceeding a traveler volume threshold and indicating a transit event, notifies a user of the transit event. The user may comprise, e.g., one or more travelers 104, transit control personnel for a transit service 110, and/or first responders who may be tasked with attending to the transit event. As a first such example, a device may present to the user a region map indicating, for respective areas 102 of the region, the estimate 212 of the traveler volume 218 for the area 102; and the transit event notifier may update the region map to indicate the estimate 212 of the traveler volume 218 of the area 102 on the map. As a second such example, where a selected traveler 804 is associated with a route through the area 102 to a destination, a route adjuster may adjust an estimated arrival time of the selected traveler 804 at the destination according to the estimate 212 of the traveler volume 218 of the area 102. As a third such example, where a selected traveler 804 is associated with a route through the area 102 to a destination, a detour presenter may, responsive to the estimate 212 of the traveler volume 216 exceeding a traveler volume threshold, present to the selected traveler 804 an alternative route to the destination that does not pass through the area 102. These and other techniques may be utilized to notify various users, such as transit system personnel and travelers 104 through the area 102, of the estimates 212 of traveler volume 216 in accordance with the techniques presented herein.

F. Computing Environment

FIG. 11 and the following discussion provide a brief, general description of a suitable computing environment to implement embodiments of one or more of the provisions set forth herein. The operating environment of FIG. 11 is only one example of a suitable operating environment and is not intended to suggest any limitation as to the scope of use or functionality of the operating environment. Example computing devices include, but are not limited to, personal computers, server computers, hand-held or laptop devices, mobile devices (such as mobile phones, Personal Digital Assistants (PDAs), media players, and the like), multiprocessor systems, consumer electronics, mini computers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

Although not required, embodiments are described in the general context of “computer readable instructions” being executed by one or more computing devices. Computer readable instructions may be distributed via computer readable media (discussed below). Computer readable instructions may be implemented as program modules, such as functions, objects, Application Programming Interfaces (APIs), data structures, and the like, that perform particular tasks or implement particular abstract data types. Typically, the functionality of the computer readable instructions may be combined or distributed as desired in various environments.

FIG. 11 illustrates an example of a system 1100 comprising a computing device 1102 configured to implement one or more embodiments provided herein. In one configuration, computing device 1102 includes at least one processing unit 1106 and memory 1108. Depending on the exact configuration and type of computing device, memory 1108 may be volatile (such as RAM, for example), non-volatile (such as ROM, flash memory, etc., for example) or some combination of the two. This configuration is illustrated in FIG. 11 by dashed line 1104.

In other embodiments, device 1102 may include additional features and/or functionality. For example, device 1102 may also include additional storage (e.g., removable and/or non-removable) including, but not limited to, magnetic storage, optical storage, and the like. Such additional storage is illustrated in FIG. 11 by storage 1110. In one embodiment, computer readable instructions to implement one or more embodiments provided herein may be in storage 1110. Storage 1110 may also store other computer readable instructions to implement an operating system, an application program, and the like. Computer readable instructions may be loaded in memory 1108 for execution by processing unit 1106, for example.

The term “computer readable media” as used herein includes computer storage media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions or other data. Memory 1108 and storage 1110 are examples of computer storage media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by device 1102. Any such computer storage media may be part of device 1102.

Device 1102 may also include communication connection(s) 1116 that allows device 1102 to communicate with other devices. Communication connection(s) 1116 may include, but is not limited to, a modem, a Network Interface Card (NIC), an integrated network interface, a radio frequency transmitter/receiver, an infrared port, a USB connection, or other interfaces for connecting computing device 1102 to other computing devices. Communication connection(s) 1116 may include a wired connection or a wireless connection. Communication connection(s) 1116 may transmit and/or receive communication media.

The term “computer readable media” may include communication media. Communication media typically embodies computer readable instructions or other data in a “modulated data signal” such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” may include a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.

Device 1102 may include input device(s) 1114 such as keyboard, mouse, pen, voice input device, touch input device, infrared cameras, video input devices, and/or any other input device. Output device(s) 1112 such as one or more displays, speakers, printers, and/or any other output device may also be included in device 1102. Input device(s) 1114 and output device(s) 1112 may be connected to device 1102 via a wired connection, wireless connection, or any combination thereof. In one embodiment, an input device or an output device from another computing device may be used as input device(s) 1114 or output device(s) 1112 for computing device 1102.

Components of computing device 1102 may be connected by various interconnects, such as a bus. Such interconnects may include a Peripheral Component Interconnect (PCI), such as PCI Express, a Universal Serial Bus (USB), firewire (IEEE 1394), an optical bus structure, and the like. In another embodiment, components of computing device 1102 may be interconnected by a network. For example, memory 1108 may be comprised of multiple physical memory units located in different physical locations interconnected by a network.

Those skilled in the art will realize that storage devices utilized to store computer readable instructions may be distributed across a network. For example, a computing device 1120 accessible via network 1118 may store computer readable instructions to implement one or more embodiments provided herein. Computing device 1102 may access computing device 1120 and download a part or all of the computer readable instructions for execution. Alternatively, computing device 1102 may download pieces of the computer readable instructions, as needed, or some instructions may be executed at computing device 1102 and some at computing device 1120.

G. Usage of Terms

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

As used in this application, the terms “component,” “module,” “system”, “interface”, and the like are generally intended to refer to a computer-related entity, either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of illustration, both an application running on a controller and the controller can be a component. One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers.

Furthermore, the claimed subject matter may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof to control a computer to implement the disclosed subject matter. The term “article of manufacture” as used herein is intended to encompass a computer program accessible from any computer-readable device, carrier, or media. Of course, those skilled in the art will recognize many modifications may be made to this configuration without departing from the scope or spirit of the claimed subject matter.

Various operations of embodiments are provided herein. In one embodiment, one or more of the operations described may constitute computer readable instructions stored on one or more computer readable media, which if executed by a computing device, will cause the computing device to perform the operations described. The order in which some or all of the operations are described should not be construed as to imply that these operations are necessarily order dependent. Alternative ordering will be appreciated by one skilled in the art having the benefit of this description. Further, it will be understood that not all operations are necessarily present in each embodiment provided herein.

Moreover, the word “example” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “example” is not necessarily to be construed as advantageous over other aspects or designs. Rather, use of the word example is intended to present concepts in a concrete fashion. As used in this application, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless specified otherwise, or clear from context, “X employs A or B” is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then “X employs A or B” is satisfied under any of the foregoing instances. In addition, the articles “a” and “an” as used in this application and the appended claims may generally be construed to mean one or more unless specified otherwise or clear from context to be directed to a singular form.

Also, although the disclosure has been shown and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. The disclosure includes all such modifications and alterations and is limited only by the scope of the following claims. In particular regard to the various functions performed by the above described components (e.g., elements, resources, etc.), the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., that is functionally equivalent), even though not structurally equivalent to the disclosed structure which performs the function in the herein illustrated example implementations of the disclosure. In addition, while a particular feature of the disclosure may have been disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of the other implementations as may be desired and advantageous for any given or particular application. Furthermore, to the extent that the terms “includes”, “having”, “has”, “with”, or variants thereof are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising.”

ESTIMATING TRAVELER VOLUME BY EVALUATING AERIAL IMAGES

Information

Publication Number

Date Filed

Date Published

Inventors

Original Assignees

CPC

International Classifications

Abstract

Description

Claims

CROSS-REFERENCE TO RELATED APPLICATIONS

PCT Information

Provisional Applications (1)