This application claims priority of Chinese Application No. 201410813662.0, filed on Dec. 24, 2014.
The disclosure relates to a method, a system and a computer-readable medium for estimating distance, more particularly to a method, a system and a computer-readable medium for estimating a distance between a first target and a second target in an image based on an image depth map of the image.
As fabrication processes of semiconductors improve, mobile devices such as mobile phones and tablets are incorporated with more functionalities (e.g., having a camera for capturing an image and/or a video), are manufactured with lower cost, and are therefore becoming widely used. However, conventional mobile devices are unable to directly obtain a size of an object (or a distance between two targets) in the image captured thereby. Currently, one way of obtaining the size of the object is to place a reference object (e.g., a coin, a ruler, etc.) near the object in order to obtain an estimate of the size, which is inconvenient and inaccurate.
Therefore, an object of the disclosure is to provide a method that can provide a more convenient way of obtaining an estimate of a size of an object and/or a distance between two targets in an image.
According to the disclosure, the method for estimating a distance between a first target and a second target in an image is to be implemented using a distance estimation system. The distance estimation system includes a processor module. The method includes the steps of:
generating, by the processor module, an image depth map associated with the image;
generating, by the processor module, first position information associated with a first position which corresponds to the first target in the image, and second position information associated with a second position, which corresponds to the second target in the image; and
computing, by the processor module, an estimate of a distance between the first target and the second target based on at least the image depth map, the first position information and the second position information.
Another object of the disclosure is to provide a distance estimation system that is programmed to implement the aforementioned method.
According to the disclosure, the distance estimation system is for estimating a distance between a first target and a second target in an image. The distance estimation system includes a processor module that is programmed to:
generate an image depth map associated with the image;
generate first position information associated with a first position which corresponds to the first target, and second position information associated with a second position which corresponds to the second target; and
compute an estimate of a distance between the first target and the second target based on at least the image depth map, the first position information and the second position information.
Yet another object of the disclosure is to provide a non-transitory computer-readable medium. According to the disclosure, the non-transitory computer-readable medium stores a software application therein. The software application includes instructions that, when executed by a processor module of a distance estimation system, causes the processor module to perform a method for estimating a distance between a first target and a second target in an image. The method includes the steps of:
generating an image depth map associated with the image;
generating first position information associated with a first position which corresponds to the first target, and second position information associated with a second position which corresponds to the second target; and
computing an estimate of a distance between the first target and the second target based on at least the image depth map, the first position information and the second position information.
Other features and advantages of the disclosure will become apparent in the following detailed description of the embodiments with reference to the accompanying drawings, of which:
Before the disclosure is described in greater detail, it should be noted that like elements are denoted by the same reference numerals throughout the disclosure.
The image capturing module 11 has stereopsis functionality. That is, an image captured by the image capturing module 11 includes information regarding a depth of each object captured in the image. As a result, the image captured by the image capturing module 11 may allow a person to identify relative depths of objects contained in the image. The image capturing module 11 may include a lens and an image sensor, and is capable of image capturing.
It is noted that, in various embodiments, one or more additional lenses and image sensors may be included in the image capturing module 11. For example, in one embodiment, a plurality of image sensors are included, and each time when the image capturing module 11 is used for image capturing, a plurality of images are obtained, each corresponding with a respective one of the image sensors. In another embodiment, a plurality of lenses are included, and each time when the image capturing module 11 is used for image capturing, a plurality of images are obtained, each corresponding with a respective one of the lenses.
The input module 12 may be embodied in a touchscreen, a set of buttons, or a combination thereof, to serve as a user interface for receiving user input. The display module 13 is configured to display the image. The sensor module 14 is configured to detect a tilt angle of the image sensor with respect to an imaginary vertical line. For example, the imaginary vertical line is perpendicular to a horizontal plane such as a ground. The processor module 15 is coupled to the image capturing module 11, the input module 12, the display module 13, the sensor module 14, and the computer-readable medium 16.
The computer-readable medium 16 stores a software application therein. The software application includes instructions that, when executed by the processor module 15, causes the processor module 15 to perform a method for estimating a distance. In practice, the software application may be stored in the computer-readable medium 16 or downloaded via a network.
In this embodiment, the distance estimation system may be embodied in a mobile device such as a smart phone, a digital camera, a tablet computer, etc. Accordingly, the image capturing module 11 is a camera module, the input module 12 is a touchscreen interface, the display module 13 is a display screen, the sensor module 14 is a gyroscope or other components capable of detecting a tilt angle of the mobile device (i.e., with respect to a pitch axis, a roll axis or a yaw axis), and the computer-readable medium 16 is a storage medium of the mobile device.
It is noted that in other embodiments, the tilt angle of the mobile device may be calculated using, for example, trigonometric functions, and the sensor module 14 may be omitted.
In other embodiments, the distance estimation system may be embodied in a combination of a computer and a device capable of capturing an image, such as a mobile device, an event data recorder (EDR), a monitoring device, a rear view camera, etc. In this case, the input module 12 is a mouse and/or keyboard of the computer, the display module 13 is a screen of the computer, the sensor module 14 is a gyroscope or other components capable of detecting a tilt angle of the device capable of capturing an image, the processor module 15 is a processor of the computer such as a CPU, and the computer-readable medium 16 is a storage medium of the computer such as a random access memory (RAM), an electrically-erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), a hard disk, etc.
It is noted that in other embodiments, the tilt angle of the device capable of capturing an image may be calculated using, for example, trigonometric functions, and the sensor module 14 may be omitted.
The method as illustrated in
In step S1, for the image captured by the image capturing module 11, the processor module 15 generates an image depth map associated with the image. The image depth map contains information regarding a distance between a surface of each of the targets captured in the image and a viewpoint, which generally indicates the position of the lens.
It is noted that in other embodiments, operations for generating the image depth map may employ one or more images captured by the image capturing module 11 for improved accuracy.
In step S2, the processor module 15 generates first position information associated with a first position which corresponds to the first target, and second position information associated with a second position which corresponds to the second target. In particular, the first position information includes a set of coordinates of the first position on the image where the first target is located. Similarly, the second position information includes a set of coordinates of the second position on the image where the second target is located.
In step S3, the processor module 15 controls the display module 13 to display a first mark at the first position, and to display a second mark at the second position. Referring to
In step S4, the processor module 15 computes the estimate of the distance between the first target and the second target based on at least the image depth map, the first position information, and the second position information. Specifically, step S4 includes the following sub-steps S41 and S42.
In sub-step S41, the processor module 15 estimates a first target distance between the first target and the lens based on the first position information, the image depth map, a focus length of the lens for capturing the image, and a pixel size of the image sensor.
In sub-step S42, the processor module 15 computes the estimate of the distance between the first target and the second target, based on at least the first target distance, the first position information, the second position information, and the focus length of the lens. The sub-step S42 further includes the following sub-steps S421 to S423.
In sub-step S421, the processor module 15 obtains a first pixel position and a second pixel position on the image sensor, based respectively on the first position information and the second position information. The first and second pixel positions correspond to the first and second positions in the image, respectively. In sub-step S422, the processor module 15 calculates a distance between the first pixel position and the second pixel position on the image sensor. In sub-step S423, the processor module 15 computes the estimate of the distance between the first target and the second target based on the first target distance, the distance between the first pixel position and the second pixel position on the image sensor, the focus length of the lens, and the tilt angle of the mobile device.
It is known that the triangle (ΔMT1T2) and the triangle (ΔMXY2) are similar triangles (as seen in
In sub-step S41, the first target distance (d1) is obtained. Next, in sub-step S421, the first and second pixel positions (Y1, Y2) are obtained. Therefore, a distance (h11) between the first and second pixel positions (Y1, Y2) on the image sensor (I) can be calculated in sub-step S422.
Subsequently, in sub-step S423, the estimate of the height (h1) of the cabinet (O) (i.e., the actual distance between the first and second targets (T1, T2)) can be computed using the following equation:
since L1=h11*sin(A), L2=f*sec(A), and L3=h11*cos(A). By taking the tilt angle into consideration, the estimation of the actual distance between the first and second targets (T1, T2) may have improved accuracy.
In step S5, the processor module 15 controls the display module 13 to display the estimate of the height (h1) (i.e., the actual distance between the first and second targets (T1, T2)). For example, the symbol “D:1M” in
The difference between the method in this embodiment shown in
In sub-step S41′, the processor module 15 estimates the first target distance between the first target and the lens, and further estimates a second target distance between the second target and the lens. The estimations are based on the first position information, the second position information, the image depth map, the focus length of the lens for capturing the image, and the pixel size of the image sensor.
In sub-step S42′, the processor module 15 computes the estimate of the distance between the first target and the second target. The computing is based on at least the first target distance, the second target distance, the first position information, the second position information, and the focus length of the lens.
In sub-step S41′, the processor module 15 estimates the first target distance (d1) and the second target distance (d2).
Next, in sub-step S421′, the processor module 15 obtains the first and second pixel positions (Y1, Y2). Therefore, a distance (h33) between the first and second pixel positions (Y1, Y2) on the image sensor (I) can be calculated in sub-step S422′.
Afterward, in sub-step S423′, an estimate of the height (h2) of the object (O′) can be computed using the following equations:
It is noted that the angle (K) may be obtained using small-angle approximation. That is, the angle (K) can be approximated by the ratio (h33/f). It is noted that the estimation is more accurate when the angle (K) is smaller. Moreover, the estimate of the height (h2) is computed using the law of cosines. Therefore, the estimation is more accurate when the tilt angle of the image sensor (I) is smaller, preferably smaller than 20 degrees.
In a third embodiment, the distance estimation system as shown in
The difference between the method in this embodiment shown in
In sub-step S41″, the processor module 15 estimates the first target distance (d1) and the second target distance (d2).
Next, in sub-step S421″, the processor module 15 obtains the pixel positions (Y1, Y2). In sub-step S422″, the processor module 15 calculates a first distance (h21) between the first pixel position (Y1) and the center point of the image sensor (I), and a second distance (h22) between the second pixel position (Y2) and the center point of the image sensor (I).
Afterward, in sub-step S423″, the estimate of the height (h2) of the object (O′) can be computed using the following equations:
To sum up, the distance estimation system, method and computer-readable medium according to the embodiments of the disclosure provides a relatively more convenient, reliable, and efficient way to obtain an estimate of a distance between two targets in the image, using the image depth map, the first position information, the second position information, and parameters regarding the image capturing module 11 (e.g., the focal length, size of pixels, etc.). The method as described in the disclosure may be applied in calculating a size of one object (by selecting two extreme points of the one object as the targets) or in calculating a distance between two different objects. As a result, the image captured by the distance estimation system as described in the disclosure contains three-dimensional information.
While the disclosure has been described in connection with what are considered the exemplary embodiments, it is understood that this disclosure is not limited to the disclosed embodiments but is intended to cover various arrangements included within the spirit and scope of the broadest interpretation so as to encompass all such modifications and equivalent arrangements.
Number | Date | Country | Kind |
---|---|---|---|
201410813662.0 | Dec 2014 | CN | national |