Patent Application
20250140109
The present invention relates to a signal analysis apparatus, a signal analysis method, and a computer-readable medium.
Techniques for estimating speeds of vehicles traveling on roads using signals obtained through measurement by sensing apparatuses are known. With regard to the techniques, Patent Literature 1 discloses a method of estimating traffic flow characteristics (average traffic speed, the number of vehicles, speed of each vehicle, and the like) using optical fibers that are along many roads.
Patent Literature 1: Japanese Unexamined Patent Application Publication No. 2021-121917
It is desirable to detect an event such as congestion or an accident using an estimated speed. Here, the signal acquired through the measurement in the sensing apparatus may include an element such as noise that has an adverse influence on the signal. In the method of estimating the speed of a vehicle using a signal including noise or the like, it is difficult to accurately estimate a speed due to the influence of noise or the like. Accordingly, there is concern of an event not being able to be detected appropriately.
An object of the present disclosure is to solve such a problem and is to provide a signal analysis apparatus, a signal analysis method, and a computer-readable medium capable of appropriately detecting an event.
According to an aspect of the present disclosure, a signal analysis apparatus includes: estimation means for estimating a speed of a vehicle traveling on a road at each of times at each of positions on the road using a signal obtained by measuring the road; and event detection means for detecting an event occurring on the road based on at least one of a corrected speed obtained by performing a smoothing process on an estimated speed that has been estimated and an inaccuracy degree indicating a degree of inaccuracy of the estimated speed.
According to another aspect of the present disclosure, a signal analysis method includes estimating a speed of a vehicle traveling on a road at each of times at each of positions on the road using a signal obtained by measuring the road; and detecting an event occurring on the road based on at least one of a corrected speed obtained by performing a smoothing process on an estimated speed that has been estimated and an inaccuracy degree indicating a degree of inaccuracy of the estimated speed.
According to still another aspect of the present disclosure, a program causes a computer to execute: a step of estimating a speed of a vehicle traveling on a road at each of times at each of positions on the road using a signal obtained by measuring the road; and a step of detecting an event occurring on the road based on at least one of a corrected speed obtained by performing a smoothing process on an estimated speed that has been estimated and an inaccuracy degree indicating a degree of inaccuracy of the estimated speed.
According to the present disclosure, it is possible to provide a signal analysis apparatus, a signal analysis method, and a computer-readable medium capable of appropriately detecting an event.
Before an example embodiment of the present disclosure is described, an overview of the example embodiment according to the present disclosure will be described.
The signal analysis apparatus 1 includes an estimation unit 2 and an event detection unit 4. The estimation unit 2 has a function as estimation means. The event detection unit 4 has a function as event detection means. The signal analysis apparatus 1 can be realized by, for example, a computer.
The estimation unit 2 estimates a speed of a vehicle traveling on a road (step S12). Specifically, the estimation unit 2 estimates a speed of a vehicle traveling on a road at each of times at each of positions on the road using a signal obtained by measuring the road. The signal obtained through the measurement can be obtained by, for example, a sensing apparatus for optical fiber sensing or the like to be described below. An estimated speed that has been estimated can be calculated at each time for each position on the road. Details will be described below.
The event detection unit 4 detects an event using the estimated speed (step S14). Specifically, the event detection unit 4 detects an event occurring on the road based on at least one of the corrected speed obtained by performing the smoothing process on the estimated speed and the inaccuracy degree indicating the degree of inaccuracy of the estimated speed. Here, the “event” is any event occurring on a road. In particular, a speed of a vehicle traveling on a road changes because the event occurs. For example, in the present exemplary example embodiment, the “event” is an event that causes a decrease in speed of the vehicle, but the present invention is not limited thereto. The “event” is, for example, congestion or an accident on a road, but the present invention is not limited thereto.
Also, the “inaccuracy degree” means a degree to which a corresponding estimated speed may be considered to be inaccurate. For example, when the estimated speed is unnaturally slower (or faster) than an estimated speed at a nearby position at that time, the inaccuracy degree related to the estimated speed may be large. When the estimated speed is unnaturally slower (or faster) than the estimated speed at that position at a nearby time, the inaccuracy degree related to the estimated speed may increase. Details will be described below. The inaccuracy degree may indicate the degree of abnormality of an estimated speed. Alternatively, the inaccuracy degree may indicate the degree of unsuitability of the estimated speed. In addition, the inaccuracy degree may indicate validity of the estimated speed. In this case, as the validity of the estimated speed increases, the inaccuracy degree may decrease. The inaccuracy degree may indicate reliability of the estimated speed. In this case, as the reliability of the estimated speed increases, the inaccuracy degree may decrease.
Here, optical fiber sensing according to a comparative example will be described.
The sensing apparatus 52 can be implemented by, for example, a distributed acoustic sensing (DAS) technique. The sensing apparatus 52 can detect vibration generated at a position at which the optical fiber cable 54 is provided. Specifically, as indicated by an arrow P, the sensing apparatus 52 causes pulsed light (sensing signal) to be incident on the optical fiber cable 54 toward a termination 54e of the optical fiber cable 54. The termination 54e is subjected to a termination process of curbing reflection of the pulsed light. Alternatively, the optical fiber cable 54 may not be subjected to the termination process.
Here, when the pulsed light is incident on the optical fiber cable 54, returned light called backscattered light is generated as indicated by an arrow R. That is, the optical fiber cable 54 is not uniform. Therefore, when pulsed light enters the optical fiber cable 54, returned light is generated at every position of the optical fiber cable 54. The sensing apparatus 52 observes the returned light chronologically.
Then, when vibration is applied to a certain position X of the optical fiber cable 54 by a vehicle traveling on the road 80 near the position X, quality (amplitude, light intensity, or the like) of returned light generated at the position changes. The sensing apparatus 52 can calculate the generation position X of the returned light of which the quality changes with a round-trip time of the light. Specifically, it is assumed that a distance from the sensing apparatus 52 to the position X at which the returned light of which the quality changes is generated is L, it can be assumed that c is the speed of light in vacuum, and n is a refractive index of an optical fiber. In this case, a time from incidence of the pulsed light by the sensing apparatus 52 to return of the returned light generated at the position X to the sensing apparatus 52 is expressed as 2 Ln/c. Thus, the distance L from the sensing apparatus 52 to the position X can be calculated by measuring the time from the incidence of the pulsed light by the sensing apparatus 52 to the return of the returned light. By preventing the sensing apparatus 52 from emitting the next pulsed light from the incidence of the pulsed light by the sensing apparatus 52 to the return of the returned light, it is possible to curb (i.e., prevent or reduce) mixing of the pulsed light in the optical fiber cable 54.
In this way, the sensing apparatus 52 acquires measurement data obtained by measuring the returned light (signal) at each position of the optical fiber cable 54 chronologically by measuring the road 80. Then, the optical fiber sensing system 50 can detect a position and a time at which vibration is generated by the vehicle traveling on the road 80 by analyzing a change in quality such as intensity or amplitude of the returned light. Thus, the optical fiber sensing system 50 can detect a position at which the vehicle is traveling at a certain time. Further, the sensing apparatus 52 can acquire a traveling trajectory of the vehicle traveling on the road 80 by performing the position detection chronologically. Details will be described below.
In
Here, the trajectory Tr is indicated by a graph in which the horizontal axis represents a position (a distance from the sensing apparatus 52) and a vertical axis represents time. In
Accordingly, when an inclination of the trajectory Tr is oriented from the top right to the bottom left (downward to the left), the trajectory Tr indicates that a corresponding vehicle Ve is traveling in a direction approaching the sensing apparatus 52. On the other hand, when the inclination of the trajectory Tr is oriented from the top left to the bottom right (downward to the right), the trajectory Tr indicates that the corresponding vehicle Ve is traveling in a direction away from the sensing apparatus 52. Accordingly, the vehicle Ve11 corresponding to the left-downward trajectory Tr11 is traveling in a direction approaching the sensing apparatus 52. The vehicle Ve12 corresponding to the right-downward trajectory Tr12 is traveling in a direction away from the sensing apparatus 52. The vehicle Ve21 corresponding to the left-downward trajectory Tr21 is traveling in a direction approaching the sensing apparatus 52. Similarly, the vehicles Ve22 and Ve23 respectively corresponding to the left-downward trajectories Tr22 and Tr23 are traveling in a direction approaching the sensing apparatus 52.
The inclination of the trajectory Tr corresponds to a speed of the corresponding vehicle Ve. Specifically, a gentle inclination of the trajectory Tr indicates that the corresponding vehicle Ve is traveling smoothly, that is, there is a high likelihood that the vehicle Ve is traveling at a normal traveling speed. Conversely, a steep inclination of the trajectory Tr indicates that the traveling of the corresponding vehicle Ve is congested, that is, there is a high likelihood that the vehicle Ve is traveling at a speed lower than the normal traveling speed. In other words, a steep inclination of the trajectory Tr indicates a high likelihood that the corresponding vehicle Ve is caught in congestion or encountering a problem such as an accident. Accordingly, there is a high likelihood that the vehicles Ve11 and Ve12 respectively corresponding to the gently inclined trajectories Tr11 and Tr12 are smoothly traveling. Conversely, there is a high likelihood that the vehicles Ve21, Ve22, and Ve23 respectively corresponding to the steeply inclined trajectories Tr21, Tr22, and Tr23 are caught in congestion or the like.
The optical fiber sensing system 50 estimates a traveling trajectory of the vehicle and a speed of the vehicle by analyzing a signal (measurement data) obtained by the sensing apparatus 52 (step S900). Here, the measurement data is time waveform data (time-series data) of a change in phase of the returned light occurring at each position of the optical fiber cable 54. This change in phase corresponds to intensity of vibration ascertained at each position of the optical fiber cable 54. The optical fiber sensing system 50 detects an event such as congestion or an accident using the estimated speed (step S920). That is, an event may be detected if the estimated speed is extremely slow at a certain time at a certain position.
As described above, the traveling trajectory data 500 in
Here, depending on a situation of the road 80, there is a region such as a bridge where vibration occurs constantly or a region where vibration is strong. Alternatively, due to an influence of noise or the like, the intensity may increase on the measurement data although the vibration is not actually strong. In this case, there is a likelihood that the traveling trajectory data 500 does not appropriately represent a trajectory of each vehicle. Accordingly, in order to remove the influence, the optical fiber sensing system 50 performs a normalization process on the traveling trajectory data 500 (step S904). Thus, an oblique line in the traveling trajectory data 500 favorably represents the trajectory Tr of each vehicle to some extent.
Subsequently, the optical fiber sensing system 50 divides the traveling trajectory data 500 into a plurality of patches (step S906). For example, as illustrated in
An arrow Pa indicates an image of a specific example of the traveling trajectory data 500 divided into the patches 502. Here, in the actual traveling trajectory data 500, as indicated by an ellipse, a trajectory (oblique line) may be broken due to the influence of noise or the like. Accordingly, the optical fiber sensing system 50 according to the comparative example removes noise contained in each patch 502 using the analysis engine 92 (step S908). The analysis engine 92 can be realized by a machine learning algorithm such as deep neural network (DNN). The analysis engine 92 is learned so as to output the traveling trajectory data in which the inclination of the oblique line appropriately indicates the speed by many pieces of training data corresponding to the traveling trajectory data represented by a position (distance) and a time. The analysis engine 92 receives the traveling trajectory data (image data) of each patch 502 as an input, and outputs the traveling trajectory data (image data) in which an influence of noise is removed and the oblique line represents a speed. The optical fiber sensing system 50 calculates the average estimated speed corresponding to each patch 502 from the inclination of each traveling trajectory (oblique line) in the traveling trajectory data output from the analysis engine 92 (step S910). Specifically, the optical fiber sensing system 50 calculates the speed from the inclination of each oblique line (trajectory) included in the patch 502 and calculates the average estimated speed in the patch 502 by averaging the calculated speeds.
Accordingly, like speed data indicated by an arrow A2, in the method according to the comparative example, there is a likelihood that obviously unnatural deceleration is estimated differently from actual deceleration due to the influence of noise or the like. In other words, this unnatural deceleration is an estimated speed due to erroneous estimation caused due to the influence of noise or the like. In this case, when the estimated speed due to erroneous estimation is less than a threshold for low-speed detection, there is a likelihood that erroneous detection occurs, for example, an event such as congestion is detected although the event does not actually occur. Therefore, there is a likelihood that an alarm is erroneous, such as alarm indicating that an event occurs, although an event such as congestion does not actually occur.
On the other hand, the signal analysis apparatus 1 according to the present example embodiment detects an event based on at least one of a corrected speed obtained by performing a smoothing process on an estimated speed and an inaccuracy degree indicating the inaccuracy degree of the estimated speed. Here, the corrected speed is obtained by correcting the estimated speed due to erroneous estimation. Accordingly, by detecting the event based on the corrected speed, erroneous detection of the event is curbed, and thus the event can be appropriately detected. For the estimated speed due to erroneous estimation, the corresponding inaccuracy degree may increase. Accordingly, it is possible to prevent the event detection from being performed for the estimated speed with a large inaccuracy degree. Accordingly, by detecting the event based on the inaccuracy degree, erroneous detection of the event is curbed, and thus the event can be appropriately detected.
It is also possible to appropriately detect an event even when a signal analysis system including the signal analysis apparatus 1, the sensing apparatus 52, and the optical fiber cable 54 is used. It is possible to appropriately detect an event even when a signal analysis method and a program for executing the signal analysis method realized by the signal analysis apparatus 1 are used.
Hereinafter, an example embodiment will be described with reference to the drawings. To clarify description, in the following description and drawings, omission and simplification are made as appropriate. In each drawing, the same elements are denoted by the same reference signs, and redundant description will be omitted as necessary.
As described above, the sensing apparatus 52 causes pulsed light to be incident on the optical fiber cable 54 and receives returned light. Thus, the sensing apparatus 52 acquires measurement data of the returned light (signal) at each position of the optical fiber cable 54. The sensing apparatus 52 transmits the measurement data (signal) at each position of the optical fiber cable 54 to the signal analysis apparatus 100.
The signal analysis apparatus 100 corresponds to the signal analysis apparatus 1 illustrated in
The control unit 102 is, for example, a processor such as a central processing unit (CPU). The control unit 102 has a function as a calculation device that performs a control process, a calculation process, and the like. The control unit 102 may include a plurality of processors. The storage unit 104 is, for example, a storage device such as a memory or a hard disk. The storage unit 104 is, for example, a read only memory (ROM), a random access memory (RAM), or the like. The storage unit 104 has a function of storing a control program, a calculation program, and the like executed by the control unit 102. That is, the storage unit 104 (memory) stores one or more instructions. The storage unit 104 has a function of temporarily storing processing data and the like. The storage unit 104 may include a database. The storage unit 104 may include a plurality of memories.
The communication unit 106 performs a process necessary for communicating with other apparatuses such as the sensing apparatus 52 via a network. The communication unit 106 may include a communication port, a router, a firewall, and the like. The interface unit 108 (interface (IF)) is, for example, a user interface (UI). The interface unit 108 includes an input device such as a keyboard, a touch panel, or a mouse, and an output device such as a display or a speaker. The interface unit 108 may be configured such that the input device and the output device are integrated, for example, like a touch screen (touch panel). The interface unit 108 receives a data inputting operation by a user (operator) and outputs information to the user. The interface unit 108 outputs, for example, the fact that an event is generated when the event is detected.
The signal analysis apparatus 100 according to the first example embodiment includes, as components, a signal acquisition unit 110, a trajectory acquisition unit 120, a speed estimation unit 130, an estimated speed processing unit 140, an event detection unit 150, and an event notification unit 160. The estimated speed processing unit 140 includes an estimated speed data storage unit 142, a corrected speed calculation unit 144, and an inaccuracy degree calculation unit 146.
The signal acquisition unit 110 has a function as signal acquisition means. The trajectory acquisition unit 120 has a function as trajectory acquisition means. The speed estimation unit 130 corresponds to the estimation unit 2 illustrated in
Each of the above-described components can be realized, for example, by executing a program under the control of the control unit 102. More specifically, each component can be realized by causing the control unit 102 to execute a program (command) stored in the storage unit 104. Each component may be realized by recording a necessary program in any nonvolatile recording medium and installing the program as necessary. Each component is not limited to be realized by software by a program, and may be realized by any combination of hardware, firmware, and software. Each component may be realized using an integrated circuit such as a field-programmable gate array (FPGA) or a microcomputer that can be programmed by a user. In this case, the integrated circuit may be used to realize a program including the foregoing components. A specific function of each component will be described below with reference to
The trajectory acquisition unit 120 acquires the trajectory data (step S104). Specifically, the trajectory acquisition unit 120 acquires trajectory data (the traveling trajectory data 500) indicating a traveling trajectory of each vehicle using the measurement data acquired from the sensing apparatus 52 like the above-described optical fiber sensing system 50. As described above, the trajectory data is a map including a position (a distance from the sensing apparatus 52) and a time. The process of the trajectory acquisition unit 120 corresponds to the above-described process of S902.
The speed estimation unit 130 estimates the speed of the vehicle traveling on the road (step S106). Specifically, the speed estimation unit 130 estimates the speed of the vehicle traveling on the road at each of times at each of positions on the road using the trajectory data (the traveling trajectory data 500). More specifically, like the above-described optical fiber sensing system 50, the speed estimation unit 130 divides the traveling trajectory data 500 into the patches 502 with a size of a predetermined distance and a predetermined time, and calculates the estimated speed of the vehicle corresponding to the patch 502 for each of the divided patches 502. The process of the speed estimation unit 130 corresponds to the above-described processes of S904 to S910.
The estimated speed processing unit 140 performs a process on the calculated estimated speed (S110 to S114). The estimated speed data storage unit 142 stores the estimated speed data (step S110). Specifically, the estimated speed data storage unit 142 stores the estimated speed data indicating a value of the estimated speed for each position and time (that is, each patch) calculated by the speed estimation unit 130. The estimated speed data storage unit 142 can be realized by the storage unit 104. The estimated speed data may be, for example, data in a comma separated value (CSV) format or data in a two-dimensional matrix format including position and time components.
The estimated speed map 200 illustrated in
For example, in
The patch 202B corresponds to a position closer to the sensing apparatus 52 by one patch (for example, 1 km) than the position (first position) corresponding to the patch 202A at the same time as the time (first time) corresponding to the patch 202A. The estimated speed at the position and time corresponding to the patch 202B is 60 (km/h). The patch 202C corresponds to a position farther from the sensing apparatus 52 by one patch (for example, 1 km) than the position (first position) corresponding to the patch 202A at the same time as the time (first time) corresponding to the patch 202A. The estimated speed at the position and time corresponding to the patch 202C is 50 (km/h).
An upper patch 202D of the patch 202A corresponds to a time near the time (first time) corresponding to the patch 202A at the position (first position) corresponding to the patch 202A. Similarly, a lower patch 202E of the patch 202A corresponds to a time near the time (first time) corresponding to the patch 202A at the position (first position) corresponding to the patch 202A. Further, a patch 202F located above the patch 202A by two patches may also correspond to a time near a time (first time) corresponding to the patch 202A at a position (first position) corresponding to the patch 202A along with the patch 202D.
The patch 202D corresponds to a time earlier than the time (first time) corresponding to the patch 202A by one patch (for example, 1 minute) at the same position as the position (first position) corresponding to the patch 202A. The estimated speed at the position and time corresponding to the patch 202D is 70 (km/h). The patch 202E corresponds to a time later than the time (first time) corresponding to the patch 202A by one patch (for example, 1 minute) at the same position as the position (first position) corresponding to the patch 202A. The estimated speed at the position and time corresponding to the patch 202E is 50 (km/h). The patch 202F corresponds to a time earlier than the time (first time) corresponding to the patch 202A by two patches (for example, 2 minutes) at the same position as the position (first position) corresponding to the patch 202A. The estimated speed at the position and time corresponding to the patch 202F is 80 (km/h).
The description will be made again with reference to
Here, it is assumed that the patch X corresponds to the first time of the first position, and the estimated speed of the patch X is the first estimated speed. In this case, the corrected speed calculation unit 144 performs the smoothing process on the first estimated speed using at least one of the estimated speed of the position near the first position at the first time and the estimated speed of the first position at the time near the first time. Thus, the corrected speed calculation unit 144 calculates the corrected speed related to the estimated speed (first estimated speed) of the patch X.
More specifically, as the smoothing process, the corrected speed calculation unit 144 calculates an average value of the estimated speeds of the patches 202A, 202B, 202C, 202D, and 202F. The calculated average value corresponds to the corrected speed. That is, the corrected speed calculation unit 144 calculates the corrected speed by calculating an average value of the estimated speed of the patch X in which the corrected speed is to be calculated and the estimated speeds of the patches around the patch X. In the example of
In the foregoing example, the smoothing in the spatial direction and the smoothing in the temporal direction are performed on the estimated speed of the patch X in which the corrected speed is to be calculated, but the present invention is not limited thereto. That is, only the smoothing in the spatial direction or only the smoothing in the temporal direction may be performed on the estimated speed of the patch X in which the corrected speed is to be calculated. For example, when a resolution in the spatial direction is not good, that is, when a size of the patch 202 in the spatial direction (position direction; in the lateral direction) is large (for example, about 10 km), there is a likelihood that the estimated speeds of the adjacent patches 202 is not unnatural even when the estimated speeds are greatly different from each other. Accordingly, in this case, only the smoothing in the temporal direction may be performed.
In the foregoing example, when the smoothing process is performed, the estimated speed of the patch X and the estimated speeds of the four surrounding patches X are used, but the present invention is not limited thereto. Any number of patches X used in the smoothing process is used. In the foregoing example, as the smoothing process, the estimated speed of the patch X and the estimated speeds and the average (simple average) of the four surrounding patches X are calculated, but the present invention is not limited thereto. Any smoothing process can be performed. For example, the smoothing process may be performed using a weighted average.
In the foregoing example, for the smoothing in the temporal direction, the estimated speed of the patch earlier than (that is, in the past) the time of the patch X in which the corrected speed is to be calculated is used. However, when the estimated speed related to the patch later than the time of the patch X in which the corrected speed is to be calculated has already been calculated, the smoothing process may be performed using the estimated speed of the patch later than the time of the patch X in which the corrected speed is to be calculated. On the other hand, by performing the smoothing process using the estimated speed of the patch earlier than the time of the patch X in which the corrected speed is to be calculated, it is possible to calculate the corrected speed immediately after the estimated speed of the patch X in which the corrected speed is to be calculated is calculated. Accordingly, it is possible to guarantee immediacy of the calculation of the corrected speed and immediacy of the event detection to be described below.
The description will be made again with reference to
Here, it is assumed that the patch X corresponds to the first time of the first position, and the estimated speed of the patch X is the first estimated speed. In this case, the inaccuracy degree calculation unit 146 calculates the inaccuracy degree for the first estimated speed using at least one of the estimated speed at the position near the first position at the first time and the estimated speed at the first position at the time near the first time. Thus, the inaccuracy degree calculation unit 146 calculates the inaccuracy degree related to the estimated speed (first estimated speed) of the patch X.
As the inaccuracy degree calculated for the estimated speed of the patch X increases, there is a high likelihood that the estimated speed of the patch X deviates from an actual speed due to an influence of noise or the like. That is, the higher the inaccuracy degree calculated for the estimated speed of the patch X is, the lower validity of the estimated speed of the patch X is. The inaccuracy degree may correspond to, for example, variations in the estimated speed of the patch X and the estimated speed(s) of the patch(es) 202 around the patch X. That is, the inaccuracy degree may increase as the variations in the first estimated speed (the estimated speed of the patch X), the estimated speed of the position near the first position at the first time, and the estimated speed at the first position at the time near the first time increase. The inaccuracy degree may be, for example, an index representing a variation, such as a variance, a standard deviation, or an average deviation. The inaccuracy degree may be, for example, an average value of differences between the estimated speed of the patch X and the estimated speed of each of the plurality of patches 202 around the patch X as an index representing the variation. That is, the inaccuracy degree calculation unit 146 may calculate, as the inaccuracy degree, an index representing a variation between the first estimated speed and at least one of the estimated speed of the position near the first position at the first time and the estimated speed at the first position at the time near the first time.
More specifically, in the example of
In the foregoing example, the inaccuracy degree associated with the variation in the spatial direction and the variation in the temporal direction is calculated for the estimated speed of the patch X in which the inaccuracy degree is to be calculated, but the present invention is not limited thereto. That is, for the estimated speed of the patch X in which the inaccuracy degree is to be calculated, the inaccuracy degree associated with only the variation in the spatial direction may be calculated, or the inaccuracy degree associated with only the variation in the temporal direction may be calculated. As described above, when a resolution in the spatial direction is not good, that is, when the size of the patch 202 in the spatial direction (the position direction; the horizontal direction) is large (for example, about 10 km), there is a likelihood that the estimated speeds of the adjacent patches 202 is not unnatural even when the estimated speeds are greatly different from each other. Accordingly, in this case, the inaccuracy degree may be calculated in consideration of only variations in the temporal direction.
In the foregoing example, when the inaccuracy degree is calculated, the estimated speed of the patch X and the estimated speeds of the four surrounding patches X are used, but the present invention is not limited thereto. Any number of patches X used to calculate the inaccuracy degree is used. In the foregoing example, the patch 202 used to calculate the inaccuracy degree for the estimated speed of the patch X is the same as the patch 202 used to perform the smoothing process on the estimated speed of the patch X, but the present invention is not limited thereto. In the foregoing example, the variance between the estimated speed of the patch X and the estimated speeds of the surrounding patches X is calculated as the inaccuracy degree for the estimated speed of the patch X, but the present invention is not limited thereto. The inaccuracy degree can be calculated using an index representing any variation. For example, as the inaccuracy degree for the estimated speed of the patch X, the standard deviation between the estimated speed of the patch X and the estimated speeds of the four surrounding patches X may be calculated, or the average deviation of the estimated speeds may be calculated.
In the foregoing example, the estimated speed of the patch earlier than (that is, in the past) the time of the patch X in which the inaccuracy degree is to be calculated is used for the variation in the temporal direction. However, when the estimated speed of the patch later than the time of the patch X in which the inaccuracy degree is to be calculated has already been calculated, the inaccuracy degree may be calculated using the estimated speed of the patch later than the time of the patch X in which the inaccuracy degree is to be calculated. On the other hand, by calculating the inaccuracy degree using the estimated speed of the patch earlier than the time of the patch X in which the inaccuracy degree is to be calculated, it is possible to calculate the inaccuracy degree immediately after the estimated speed of the patch X in which the inaccuracy degree is to be calculated is calculated. Accordingly, it is possible to guarantee the immediacy of the calculation of the inaccuracy degree and the immediacy of event detection to be described below.
The description will be made again with reference to
Specifically, for each patch 202, the event detection unit 150 determines whether the corresponding corrected speed is equal to or less than a predetermined threshold Vth (first threshold) and the corresponding inaccuracy degree is equal to or less than a predetermined threshold Dth (second threshold). When this determination is positive, the event detection unit 150 determines that an event occurs at a position corresponding to the patch 202 and a time corresponding to the patch 202. Conversely, when this determination is negative, the event detection unit 150 determines that an event does not occur at the position corresponding to the patch 202 and the time corresponding to the patch 202.
When an event is detected (YES in S120), the event notification unit 160 issues an alarm indicating that an event occurs at a position corresponding to the patch 202 and a time corresponding to the patch 202 (step S130). For example, the event notification unit 160 may perform control such that a display mode of the patch 202 in which the event is detected is more conspicuous than display modes of the other patches 202 in the estimated speed map 200 displayed on the interface unit 108. Alternatively, the event notification unit 160 may perform control such that display indicating that an event occurs at a position corresponding to the patch 202 and a time corresponding to the patch 202 is output to the interface unit 108 that is a display. Alternatively, the event notification unit 160 may perform control such that a voice indicating that an event occurs at a position corresponding to the patch 202 and a time corresponding to the patch 202 is output to the interface unit 108 that is a speaker. Then, a processing flow returns to S112, and a similar process is performed on the other patches 202.
Conversely, when the event is not detected (NO in S120), the process of S130 is not performed. Then, the processing flow returns to S112, and a similar process is performed on the other patches 202.
For example, in the estimated speed map 200 of
On the other hand, by performing the smoothing process as described above, as illustrated in
When the influence of noise or the like is greatly large like speed data indicated by an arrow A4 in
On the other hand, the estimated speed can be determined to be inaccurate by calculating the inaccuracy degree (variation) as described above. That is, the estimated speed of which the inaccuracy degree is large is greatly affected by noise or the like and is not reliable because there is a high likelihood that the estimated speed is affected due to erroneous estimation. Specifically, in the inaccuracy degree data indicated by an arrow A6, when the inaccuracy degree is equal to or greater than the threshold (Dth) like an ellipse B6, it is assumed that the event detection is not performed using the corresponding speed (the corrected speed and the estimated speed). In this case, even when the speed (the corrected speed and the estimated speed) at that time is equal to or less than the threshold, it is determined that an event is not detected. Accordingly, when erroneous estimation such as a steep decrease in the estimated speed occurs like the example of
In the estimated speed map 200 illustrated in
Here, in the examples of
In the estimated speed map 200 illustrated in
Here, when a low-speed event such as congestion actually occurs, a portion in which the vehicle speed (average vehicle speed) becomes low on the road propagates backward (upstream in the traveling direction of the vehicle) with passage of time. For example, it is assumed that a cause of congestion occurs at a position corresponding to a patch 202Y and a time corresponding to the patch 202Y. In this case, in the estimated speed map 200, in the temporal direction, the speed becomes low in the patch 202 corresponding to a later time from the time. In the spatial direction, the speed becomes low in the patch 202 corresponding to the rear side from the position. Accordingly, when the cause of the congestion occurs at the position and the time corresponding to the patch 202Y, the low-speed event propagates to the time and the position after the patch 202Y.
Accordingly, in a patch 202 (for example, a patch 202Z) in which a true low speed event is occurring, the estimated speed (vehicle speed) can decrease in the surrounding patches 202. Then, in the patches 202 indicated by the ellipse C1 in
In this way, in the patch 202 in which the true low-speed event occurs, not only the estimated speed of the patch 202 but also the estimated speed of the surrounding patches 202 are reduced. Accordingly, when the corrected speed calculation unit 144 calculates the corrected speed with respect to the estimated speed of the patch X in which the true low-speed event occurs using the estimated speed of the surrounding patches 202, the corrected speed calculation unit 144 can calculate the corrected speed with a low speed value. In the corrected speed map 220 illustrated in
In the patch 202 in which the true low-speed event occurs, not only the estimated speed of the patch 202 but also the estimated speeds of the surrounding patches 202 are reduced. Accordingly, when the inaccuracy degree calculation unit 146 calculates the inaccuracy degree for the estimated speed of the patch X in which the true low-speed event occurs using the estimated speed of the surrounding patches 202, the inaccuracy degree calculation unit 146 can calculate the low inaccuracy degree because of a small variation in the estimated speeds. In the inaccuracy degree map 240 illustrated in
On the other hand, in patches 202G, 202H, and 202I indicated by the arrow C2 in
Here, when the corrected speed calculation unit 144 calculates the corrected speed with respect to the estimated speed of the patch 202G using the estimated speeds of the surrounding patches 202, the calculated corrected speed is greater than the threshold Vth like the corrected speed of a patch 222G of the corrected speed map 220 illustrated in
When the corrected speed calculation unit 144 calculates the corrected speed with respect to the estimated speed of the patch 202H using the estimated speeds of the surrounding patches 202, the calculated corrected speed is greater than the threshold Vth like the corrected speed of a patch 222H of the corrected speed map 220 illustrated in
Conversely, when the corrected speed calculation unit 144 calculates the corrected speed with respect to the estimated speed of the patch 202J that does not exceed the threshold, the calculated corrected speed is equal to or less than the threshold Vth like the corrected speed of a patch 222J of the corrected speed map 220 illustrated in
Even when the corrected speed obtained for the patch 202 in which an event does not actually occur is equal to or less than the threshold like the patch 202J, an event can be curbed from being erroneously detected by performing event detection using the inaccuracy degree. Accordingly, the event detection can be performed more accurately using the corrected speed and the inaccuracy degree. Accordingly, it is possible to further curb an erroneous alarm.
The present invention is not limited to the foregoing example embodiments, and can be modified as appropriate without departing from the gist and the scope of the present invention. For example, the order of the steps (processes) in the above-described flowchart can be changed as appropriate. One or more of the steps (processes) in the flowchart can be omitted as appropriate. For example, in the flowchart of
Alternatively, only either the process of S112 or the process of S114 may be executed. When only the process of S112 is executed, the event detection unit 150 determines in the process of S120 whether the corresponding corrected speed is equal to or less than the threshold Vth for each patch 202. When the corrected speed is equal to or less than the threshold Vth, the event detection unit 150 determines that an event occurs at a position corresponding to the patch 202 and a time corresponding to the patch 202. Conversely, when the corrected speed is not equal to or less than the threshold Vth, the event detection unit 150 determines that the event does not occur at the position corresponding to the patch 202 and the time corresponding to the patch 202.
On the other hand, when only the process of S114 is executed, the event detection unit 150 determines in the process of S120 whether the corresponding estimated speed is equal to or less than the threshold Vth and the corresponding inaccuracy degree is equal to or less than the threshold Dth for each patch 202. When this determination is positive, the event detection unit 150 determines that an event occurs at a position corresponding to the patch 202 and a time corresponding to the patch 202. That is, in this case, since the estimated speed corresponding to the patch 202 is reliable (that is, not due to erroneous estimation) and the estimated speed decreases to the threshold Vth or less, it is determined that an event occurs. Conversely, when this determination is negative, the event detection unit 150 determines that an event does not occur at the position corresponding to the patch 202 and the time corresponding to the patch 202. That is, when the inaccuracy degree is not equal to or less than the threshold Dth, the corresponding estimated speed is unreliable. Therefore, the event detection is not performed based on the unreliable estimated speed. When the estimated speed is not equal to or less than the threshold Vth, there is a high likelihood that a speed reduction event does not occur. Therefore, it is not determined that an event occurs.
In the above-described example embodiment, the sizes of the patches are uniform. However, the sizes of the patches may not be uniform. For example, the sizes of the patches divided in the traveling trajectory data 500 may be different depending on the positions of the patches. The same applies to the sizes of the patches of the estimated speed map 200, the corrected speed map 220, and the inaccuracy degree map 240.
In the above-described example embodiment, an estimated speed of a vehicle traveling on a road is acquired using a signal obtained through the optical fiber sensing. However, the estimated speed of the vehicle may be acquired using a signal obtained according to a method other than the optical fiber sensing.
The above-described program includes a command group (or software codes) for causing a computer to perform one or more functions that have been described in the example embodiments when the program is read by the computer. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. As examples and not by way of limitation, the computer-readable medium or the tangible storage medium includes a random-access memory (RAM), a read-only memory (ROM), a flash memory, a solid-state drive (SSD) and any other memory technique, a CD-ROM, a digital versatile disk (DVD), a Blu-ray (registered trademark) disc or any other optical disk storage, a magnetic cassette, a magnetic tape, a magnetic disk storage, and any other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or a communication medium. As examples and not by way of limitation, the transitory computer-readable medium or the communication medium include electrical, optical, acoustic and signals, or propagated signals in other forms.
Some or all of the above-described example embodiments can be described as in the following Supplementary Notes, but are not limited to the following Supplementary Notes.
A signal analysis apparatus including:
The signal analysis apparatus according to Supplementary Note 1, wherein the event detection means detects an event when the corrected speed is equal to or less than a predetermined first threshold.
The signal analysis apparatus according to Supplementary Note 2, wherein the event detection means detects an event when the corrected speed is equal to or less than the first threshold and the inaccuracy degree is equal to or less than a predetermined second threshold.
The signal analysis apparatus according to any one of Supplementary Notes 1 to 3, further including: corrected speed calculation means for calculating a corrected speed related to a first estimated speed at a first position by performing the smoothing process on the first estimated speed at the first position at a first time using at least one of an estimated speed at a position near the first position at the first time and an estimated speed at the first position at a time near the first time.
The signal analysis apparatus according to Supplementary Note 4, wherein the corrected speed calculation means calculates a corrected speed related to the first estimated speed by performing the smoothing process using an estimated speed at the first position at a time earlier than the first time.
The signal analysis apparatus according to any one of Supplementary Notes 1 to 5, further including: inaccuracy degree calculation means for calculating the inaccuracy degree at a first estimated speed of a first position at a first time using at least one of an estimated speed at a position near the first position at the first time and an estimated speed at the first position at a time near the first time.
The signal analysis apparatus according to Supplementary Note 6, wherein the inaccuracy degree calculation means calculates the inaccuracy degree using an estimated speed at the first position at a time earlier than the first time.
The signal analysis apparatus according to Supplementary Note 6 or 7, wherein the inaccuracy degree calculation means calculates an index representing a variation between the first estimated speed and at least one of the estimated speed at the position near the first position at the first time and the estimated speed at the first position at a time near the first time as the inaccuracy degree.
The signal analysis apparatus according to Supplementary Note 6 or 7, wherein the inaccuracy degree calculation means calculates the inaccuracy degree so that the inaccuracy degree of the first estimated speed increases as variations in the first estimated speed, the estimated speed at the position near the first position at the first time, and the estimated speed at the first position at the time near the first time increases.
The signal analysis apparatus according to any one of Supplementary Notes 1 to 9, wherein the estimation means estimates the speed of the vehicle using a signal detected using an optical fiber provided along the road.
A signal analysis method including:
The signal analysis method according to Supplementary Note 11, further including detecting an event when the corrected speed is equal to or less than a predetermined first threshold.
The signal analysis method according to Supplementary Note 12, further including detecting an event when the corrected speed is equal to or less than the first threshold and the inaccuracy degree is equal to or less than a predetermined second threshold.
The signal analysis method according to any one of Supplementary Notes 11 to 13, further including calculating a corrected speed related to a first estimated speed at a first position by performing the smoothing process on the first estimated speed at the first position at a first time using at least one of an estimated speed at a position near the first position at the first time and an estimated speed at the first position at a time near the first time.
The signal analysis method according to Supplementary Note 14, further including calculating a corrected speed related to the first estimated speed by performing the smoothing process using an estimated speed at the first position at a time earlier than the first time.
The signal analysis method according to any one of Supplementary Notes 11 to 15, further including calculating the inaccuracy degree at a first estimated speed of a first position at a first time using at least one of an estimated speed at a position near the first position at the first time and an estimated speed at the first position at a time near the first time.
The signal analysis method according to Supplementary Note 16, further including calculating the inaccuracy degree using an estimated speed at the first position at a time earlier than the first time.
The signal analysis method according to Supplementary Note 16 or 17, further including calculating an index representing a variation between the first estimated speed and at least one of the estimated speed at the position near the first position at the first time and the estimated speed at the first position at a time near the first time as the inaccuracy degree.
The signal analysis method according to Supplementary Note 16 or 17, further including calculating the inaccuracy degree so that the inaccuracy degree of the first estimated speed increases as variations in the first estimated speed, the estimated speed at the position near the first position at the first time, and the estimated speed at the first position at the time near the first time increase.
The signal analysis method according to any one of Supplementary Notes 11 to 19, further including estimating the speed of the vehicle using a signal detected using an optical fiber provided along the road.
A non-transitory computer-readable medium storing a program for causing a computer to execute:
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/JP2021/048609 | 12/27/2021 | WO |
