Traffic lane change detection system, traffic lane change detection device, traffic lane change detection method, and program
The lane change detection system uses optical fiber-based vehicle vibration data to accurately detect lane changes and track vehicle positions, addressing the limitations of existing systems and improving road monitoring efficiency.
Patent Information
- Application Number
- JP2023209723
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-12-12
- Publication Date
- 2025-06-24
Smart Images
Figure 2025093826000001_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to a lane change detection system, a lane change detection device, a lane change detection method, and a program.
Background Art
[0002] A sensing device connected to an optical fiber buried in a road can measure the vehicle vibration of a vehicle traveling on the road over the entire section where the optical fiber is buried by optical fiber sensing using the optical fiber as a line sensor. Further, the sensing device can visualize the trajectory of the vehicle by generating a visualization image representing the intensity of the measured vehicle vibration as a graph of the distance and time of the optical fiber from the sensing device. Further, by using an existing communication optical fiber as the optical fiber, it is possible to introduce a system for monitoring vehicles at low cost. A system for monitoring vehicles by optical fiber sensing is disclosed in, for example, Patent Documents 1 and 2.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Patent Document 2
Summary of the Invention
Problems to be Solved by the Invention
[0004] By the way, in order to grasp a vehicle traveling on a road by optical fiber sensing, it is necessary to grasp the lane change of the vehicle. However, the techniques disclosed in Patent Documents 1 and 2 have a problem that they cannot detect a lane change of a vehicle traveling on a road.
[0005] Accordingly, an object of the present disclosure is to provide a lane change detection system, a lane change detection device, a lane change detection method, and a program capable of detecting a lane change of a vehicle traveling on a road in view of the above-described problems. **Means for Solving the Problems**
[0006] A lane change detection system according to one aspect includes: an acquisition unit that acquires data of vehicle vibration indicating vibration generated by the traveling of a vehicle on a road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; and a detection unit that detects whether or not the vehicle has changed lanes based on a specific characteristic in the current frame of the vehicle vibration and the travel lane in which the vehicle was traveling in the previous frame of the vehicle vibration.
[0007] A lane change detection device according to one aspect includes: an acquisition unit that acquires data of vehicle vibration indicating vibration generated by the traveling of a vehicle on a road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; and a detection unit that detects whether or not the vehicle has changed lanes based on a specific characteristic in the current frame of the vehicle vibration and the travel lane in which the vehicle was traveling in the previous frame of the vehicle vibration.
[0008] A lane change detection method according to one aspect is a lane change detection method executed by a lane change detection device, the method including: acquiring data of vehicle vibration indicating vibration generated by the traveling of a vehicle on a road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; and detecting whether or not the vehicle has changed lanes based on a specific characteristic in the current frame of the vehicle vibration and the travel lane in which the vehicle was traveling in the previous frame of the vehicle vibration.
[0009] A program according to one aspect is Cause a computer to execute a procedure of obtaining data of vehicle vibrations indicating vibrations generated by the running of a vehicle on a road from a sensing device that measures vibrations generated on the road using an optical fiber buried in the road, and execute a procedure of detecting whether or not the vehicle has changed lanes based on specific characteristics in the current frame of the vehicle vibrations and the driving lane in which the vehicle was running in the previous frame of the vehicle vibrations.
Effect of the Invention
[0010] According to the above aspect, there is an effect that a lane change detection system, a lane change detection device, a lane change detection method, and a program capable of detecting a lane change of a vehicle running on a road can be provided.
Brief Description of the Drawings
[0011]
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18
Figure 19
Figure 20
Figure 21
Figure 22
Embodiments for Carrying Out the Invention
[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that, for the sake of clarity of explanation, the following description and drawings are appropriately omitted and simplified. Also, in each of the following drawings, the same elements are denoted by the same reference numerals, and redundant explanations are omitted as necessary. In addition, the specific numerical values shown below are merely examples for facilitating the understanding of the present disclosure and are not limited thereto.
[0013] <Sensing device used in the present disclosure> Before describing each embodiment of the present disclosure, with reference to FIG. 1, a sensing device 30 which is a data source used in each embodiment will be described.
[0014] As shown in FIG. 1, the sensing device 30 is connected to an optical fiber 20 buried in a road R, and measures vibrations generated on the road R by optical fiber sensing using the optical fiber 20. For example, the sensing device 30 is realized by a DFOS (Distributed Fiber Optic Sensing) device or the like.
[0015] In each embodiment described below, it is assumed that the optical fiber 20 is buried along the road R under the road shoulder or the median strip of the road R. Also, the road R is a two-lane road, and the lane close to the optical fiber 20 among the two lanes is referred to as the first lane, and the lane far from the optical fiber 20 is referred to as the second lane. Also, in FIG. 1, a camera 40 for photographing the road R is installed on the road R, but the presence or absence of the installation of the camera 40 is arbitrary.
[0016] As described above, the sensing device 30 can visualize the trajectory of a vehicle by generating a visualization image representing the intensity of vehicle vibrations measured by optical fiber sensing as a graph of the distance and time of the optical fiber 20 from the sensing device 30. FIG. 2 shows an example of a visualization image generated by the sensing device 30. In FIG. 2, the horizontal axis represents the distance of the optical fiber 20 from the sensing device 30, and the vertical axis represents time.
[0017] In the visualization image shown in FIG. 2, when a vehicle is traveling on the road R, the fact that the vehicle is traveling is represented by a line. For example, the fact that one vehicle is traveling on the road R is represented by a single diagonal line. Also, the slope of the diagonal line represents the traveling speed of the vehicle, and the smaller the slope of the diagonal line, the faster the traveling speed of the vehicle.
[0018] In the visualization image shown in FIG. 2, a single diagonal line corresponding to the trajectory of one vehicle traveling on the road R is surrounded by a dashed line. Also, in the visualization image shown in FIG. 2, by masking all except that single diagonal line, that single diagonal line is highlighted. Further, in the visualization image shown in FIG. 2, a section where it has been confirmed by the camera 40 or the like that the vehicle is traveling in the first lane is surrounded by a dotted line.
[0019] Also, the sensing device 30 can individually track vehicles whose trajectories appear as diagonal lines in the visualization image. FIG. 3 shows an example of data on vehicle vibrations generated by the sensing device 30 and caused by the traveling of vehicles on the road R. FIG. 3 shows an example of vehicle vibrations occurring at any position on the road R (the distance of the optical fiber 20 from the sensing device 30), where the horizontal axis represents time and the vertical axis represents vibration intensity.
[0020] In each of the embodiments described below, data as shown in FIG. 3 is acquired from the sensing device 30 as data on vehicle vibrations of vehicles traveling on the road R, and using the acquired data, the presence or absence of lane changes of the vehicles is detected. Hereinafter, each embodiment will be described.
[0021] <Embodiment 1> First, with reference to FIG. 4, a schematic configuration example of the lane change detection system 1 will be described. The lane change detection system 1 includes a lane change detection device 10. The lane change detection device 10 includes an acquisition unit 11 and a detection unit 12.
[0022] The acquisition unit 11 acquires, from the sensing device 30, data such as that shown in FIG. 3 as data on the vehicle vibration of a vehicle traveling on the road R. At this time, the acquisition unit 11 also acquires, from the sensing device 30, the position at which the vehicle vibration occurred (the distance of the optical fiber 20 from the sensing device 30).
[0023] The detection unit 12 detects the presence or absence of a lane change of the vehicle using the data on the vehicle vibration of the vehicle acquired by the acquisition unit 11. Here, when the vehicle changes lanes, the distance from the optical fiber 20 to the vehicle changes, and accordingly, the characteristics of the vehicle vibration of the vehicle also change. The characteristics of the vehicle vibration that change with a lane change are, for example, vibration intensity, frequency spectrum characteristics, and the like. Therefore, it is possible to detect the presence or absence of a lane change of the vehicle according to whether the characteristics of the vehicle vibration of the vehicle have changed.
[0024] In addition, the characteristics of the vehicle vibration when the vehicle is traveling in each lane (the first lane and the second lane) are different from each other and can be grasped in advance. Therefore, it is possible to grasp the characteristics of the vehicle vibration immediately before the vehicle from the traveling lane in which the vehicle was traveling immediately before.
[0025] In this way, since it is possible to determine whether the characteristics of the vehicle vibration of the vehicle have changed from the characteristics of the vehicle vibration of the vehicle at the current time and the traveling lane in which the vehicle was traveling immediately before, it is possible to detect the presence or absence of a lane change of the vehicle.
[0026] Therefore, the detection unit 12 divides the data on the vehicle vibration of the vehicle acquired by the acquisition unit 11 in frame units, and based on a specific characteristic in the current frame of the vehicle vibration and the traveling lane in which the vehicle was traveling at the time of the previous frame of the vehicle vibration, detects the presence or absence of a lane change of the vehicle.
[0027] Note that the detection unit 12 shall have grasped in advance, by any method, the driving lane on which the vehicle was traveling in the previous frame. For example, as shown in FIG. 1, when the camera 40 is installed on the road R, the detection unit 12 may determine the driving lane in the previous frame by using the video captured by the camera 40.
[0028] Subsequently, with reference to FIG. 5, a schematic operation example of the lane change detection system 1 will be described. The acquisition unit 11 acquires data on vehicle vibrations generated by the running of the vehicle on the road R from the sensing device 30 (step S11). The detection unit 12 detects the presence or absence of a lane change of the vehicle based on a specific characteristic of the vehicle vibration in the current frame of the vehicle for which data has been acquired by the acquisition unit 11 and the driving lane on which the vehicle was traveling in the previous frame of the vehicle vibration (step S12).
[0029] If the detection unit 12 determines that no lane change of the vehicle has occurred (NO in step S13), it returns to step S12. If it determines that a lane change of the vehicle has occurred (YES in step S13), the process ends. Note that when the detection unit 12 returns to step S12, it sets the current frame and the next frame of the vehicle vibration of the vehicle as the previous frame and the current frame, respectively, and then performs the process of step S12.
[0030] As described above, according to the first embodiment, the acquisition unit 11 acquires data on vehicle vibrations generated by the running of the vehicle on the road R from the sensing device 30. The detection unit 12 detects the presence or absence of a lane change of the vehicle based on a specific characteristic of the vehicle vibration in the current frame of the vehicle and the driving lane on which the vehicle was traveling in the previous frame of the vehicle vibration.
[0031] Thereby, it is possible to detect a lane change of a vehicle traveling on the road R. In addition, since it is possible to detect a lane change of the vehicle, it is also possible to detect the lane in which the vehicle is traveling after the lane change. Therefore, hereafter too, by detecting a lane change of the lane, it is possible to continuously detect the lane in which the vehicle is traveling. As a result, the vehicle detection function implemented by an existing traffic counter or the like can be implemented at an arbitrary position on the road R in which the optical fiber 20 is buried.
[0032] Note that the detection unit 12 may calculate an average vibration intensity as a specific characteristic in the current frame of the vehicle vibration of the vehicle. Then, the detection unit 12 may detect the presence or absence of a lane change of the vehicle based on the traveling lane in which the vehicle was traveling at the time of the previous frame of the vehicle vibration, the comparison result between the average vibration intensity in the current frame of the vehicle vibration, and the threshold value.
[0033] Alternatively, the detection unit 12 may calculate an average vibration intensity in a specific frequency band as a specific characteristic in the current frame of the vehicle vibration of the vehicle. Then, the detection unit 12 may detect the presence or absence of a lane change of the vehicle based on the traveling lane in which the vehicle was traveling at the time of the previous frame of the vehicle vibration, the comparison result between the average vibration intensity in the specific frequency band in the current frame of the vehicle vibration, and the threshold value. In this case, the specific frequency band may be a band in which the difference between the average vibration intensity of the vehicle vibration before the lane change of the vehicle (the average vibration intensity of the vehicle vibration when traveling in the first lane (or the second lane)) and the average vibration intensity of the vehicle vibration after the lane change of the vehicle (the average vibration intensity of the vehicle vibration when traveling in the second lane (or the first lane)) is equal to or greater than a predetermined value.
[0034] Alternatively, the detection unit 12 may calculate a spectral centroid of the frequency spectrum as a specific characteristic in the current frame of the vehicle vibration of the vehicle. Then, the detection unit 12 may calculate a centroid shift amount that is the difference between the spectral centroid in the current frame of the vehicle vibration and the spectral centroid in the previous frame of the vehicle vibration. Then, the detection unit 12 may detect the presence or absence of a lane change of the vehicle based on the traveling lane in which the vehicle was traveling at the time of the previous frame of the vehicle vibration, the comparison result between the centroid shift amount in the current frame of the vehicle vibration, and the threshold value.
[0035] Alternatively, the detection unit 12 may be provided with a learning model that has previously learned the feature amounts when a lane change of the vehicle occurs. Then, the detection unit 12 uses, as feature amounts, a specific characteristic in the current frame of the vehicle vibration of the vehicle and the travel lane on which the vehicle was traveling at the time of the previous frame of the vehicle vibration, inputs them into the learning model, and may detect the presence or absence of a lane change of the vehicle based on the output of the learning model.
[0036] Further, when it is determined by the detection unit 12 that a lane change of the vehicle has occurred, the lane change detection device 10 may further include a specifying unit that specifies the position on the road R where the lane change of the vehicle has occurred, and when the lane change has occurred a predetermined number of times or more at the position, specifies the position as an abnormal occurrence position.
[0037] <Embodiment 2> First, with reference to FIG. 6, a schematic configuration example of the lane change detection system 1A will be described. The lane change detection system 1A includes a lane change detection device 10A. The lane change detection device 10A has a configuration in which the detection unit 12 is replaced with a detection unit 12A as compared with the lane change detection device 10.
[0038] As described above, the acquisition unit 11 acquires data as shown in FIG. 3 as data on the vehicle vibration of the vehicle traveling on the road R from the sensing device 30. However, the data on the vehicle vibration of the vehicle acquired by the acquisition unit 11 has variations in the instantaneous vibration intensity.
[0039] Therefore, the detection unit 12A uses the average vibration intensity in the frame. Thereby, the stabilization of the detection accuracy of the lane change can be achieved. That is, the detection unit 12A calculates the average vibration intensity as a specific characteristic in the current frame of the vehicle vibration of the vehicle. Further, the detection unit 12A detects whether or not the vehicle has changed lanes based on the travel lane in which the vehicle was traveling when the vehicle vibrated in the previous frame and the comparison result between the average vibration intensity in the current frame of the vehicle vibration and the threshold value.
[0040] Note that the detection unit 12A is assumed to have preset the above-described threshold value by performing prior measurement or the like. Also, the detection unit 12A is assumed to have grasped in advance the travel lane in which the vehicle was traveling in the previous frame by an arbitrary method (for example, a method using an image captured by the camera 40 installed on the road R).
[0041] Subsequently, with reference to FIG. 7, a schematic operation example of the lane change detection system 1A will be described. When the acquisition unit 11 acquires vehicle vibration data of a vehicle traveling on the road R from the sensing device 30, the detection unit 12A calculates the average vibration intensity in the current frame of the vehicle vibration (step S21). Next, the detection unit 12A determines whether the travel lane in which the vehicle was traveling when the vehicle vibrated in the previous frame is the first lane or the second lane (step S22).
[0042] When the travel lane in the previous frame is the first lane close to the optical fiber 20, the detection unit 12A determines whether the average vibration intensity is less than the threshold value (step S23). If the detection unit 12A determines that the average vibration intensity is less than the threshold value (YES in step S23), it determines that a lane change of the vehicle has occurred (step S25). On the other hand, if the detection unit 12A determines that the average vibration intensity is not less than the threshold value (NO in step S23), it returns to step S21.
[0043] Also, when the travel lane of the previous frame is the second lane far from the optical fiber 20, the detection unit 12A determines whether the average vibration intensity is equal to or greater than the threshold value (step S24). When the average vibration intensity is equal to or greater than the threshold value (YES in step S24), the detection unit 12A determines that a lane change of the vehicle has occurred (step S25). On the other hand, when the average vibration intensity is not equal to or greater than the threshold value (NO in step S24), the detection unit 12A returns to step S21.
[0044] Note that when the detection unit 12A returns to step S21, after setting the current frame and the next frame of the vehicle vibration of the vehicle as the previous frame and the current frame, respectively, the process of step S21 is performed.
[0045] As described above, according to the second embodiment, the detection unit 12A calculates the average vibration intensity in the current frame of the vehicle vibration of the vehicle, and based on the travel lane in which the vehicle was traveling at the time of the previous frame of the vehicle vibration, the comparison result between the average vibration intensity in the current frame of the vehicle vibration and the threshold value, detects the presence or absence of a lane change of the vehicle. Thereby, it is possible to detect a lane change of a vehicle traveling on the road R. Other effects are the same as those of the first embodiment described above.
[0046] <Embodiment 3> First, with reference to FIG. 8, a schematic configuration example of the lane change detection system 1B will be described. The lane change detection system 1B includes a lane change detection device 10B. The lane change detection device 10B has a configuration in which the detection unit 12 is replaced with a detection unit 12B as compared with the lane change detection device 10.
[0047] As described above, the acquisition unit 11 acquires data as shown in FIG. 3 as data of the vehicle vibration of a vehicle traveling on the road R from the sensing device 30. However, the data of the vehicle vibration of the vehicle acquired by the acquisition unit 11 has variations in the instantaneous vibration intensity. Therefore, the detection unit 12B uses the average vibration intensity in the frame. Thereby, the detection accuracy of lane change can be stabilized.
[0048] Also, referring to FIG. 9, the frequency spectrum characteristics obtained by performing FFT (Fast Fourier Transform) on the vehicle vibration data when the vehicle is traveling in the first lane and the frequency spectrum characteristics obtained by performing FFT on the vehicle vibration data when the vehicle is traveling in the second lane are shown. As can be seen from FIG. 9, there is a frequency band in which the difference in vibration intensity is significant between when the vehicle is traveling in the first lane and when it is traveling in the second lane.
[0049] Therefore, the detection unit 12B previously obtains, as a specific frequency band, a frequency band in which the difference between the average vibration intensity of the vehicle vibration when the vehicle is traveling in the first lane and the average vibration intensity of the vehicle vibration when the vehicle is traveling in the first lane is equal to or greater than a predetermined value. Then, the detection unit 12B uses the average vibration intensity of the specific frequency band in the frame. Thereby, further stabilization of the detection accuracy of lane change can be achieved.
[0050] That is, the detection unit 12B calculates the average vibration intensity of the specific frequency band as a specific characteristic in the current frame of the vehicle vibration. Further, the detection unit 12B detects the presence or absence of a lane change of the vehicle based on the traveling lane in which the vehicle was traveling in the previous frame of the vehicle vibration and the comparison result between the average vibration intensity of the specific frequency band in the current frame of the vehicle vibration and the threshold value.
[0051] Note that the detection unit 12B presets the above-described threshold value by performing prior measurement or the like. Also, the detection unit 12B is assumed to have grasped in advance the traveling lane in which the vehicle was traveling in the previous frame by an arbitrary method (for example, a method using an image captured by the camera 40 installed on the road R).
[0052] Next, with reference to FIG. 10, a schematic operation example of the lane change detection system 1B will be described. When the acquisition unit 11 acquires data on the vehicle vibration of a vehicle traveling on the road R from the sensing device 30, the detection unit 12B performs FFT on the portion of the current frame of the vehicle vibration of the vehicle (step S31), and calculates the average vibration intensity in a specific frequency band in the current frame (step S32). Next, the detection unit 12B determines whether the traveling lane in which the vehicle was traveling in the previous frame of the vehicle vibration is the first lane or the second lane (step S33).
[0053] When the traveling lane in the previous frame is the first lane close to the optical fiber 20, the detection unit 12B determines whether the average vibration intensity is less than the threshold value (step S34). When the average vibration intensity is less than the threshold value (YES in step S34), the detection unit 12B determines that a lane change of the vehicle has occurred (step S36). On the other hand, when the average vibration intensity is not less than the threshold value (NO in step S34), the process returns to step S31.
[0054] When the traveling lane in the previous frame is the second lane far from the optical fiber 20, the detection unit 12B determines whether the average vibration intensity is equal to or greater than the threshold value (step S35). When the average vibration intensity is equal to or greater than the threshold value (YES in step S35), the detection unit 12B determines that a lane change of the vehicle has occurred (step S36). On the other hand, when the average vibration intensity is not equal to or greater than the threshold value (NO in step S35), the process returns to step S31.
[0055] When the detection unit 12B returns to step S31, after setting the current frame and the next frame of the vehicle vibration of the vehicle as the previous frame and the current frame, respectively, the process of step S31 is performed.
[0056] As described above, according to the third embodiment, the detection unit 12B calculates the average vibration intensity in a specific frequency band in the current frame of the vehicle vibration, and based on the travel lane in which the vehicle was traveling in the previous frame of the vehicle vibration and the comparison result between the average vibration intensity in the specific frequency band in the current frame of the vehicle vibration and the threshold value, detects whether or not the vehicle has changed lanes. Thereby, it is possible to detect a lane change of a vehicle traveling on the road R. Other effects are the same as those of the first embodiment described above.
[0057] <Embodiment 4> First, with reference to FIG. 11, a schematic configuration example of the lane change detection system 1C will be described. The lane change detection system 1C includes a lane change detection device 10C. The lane change detection device 10C has a configuration in which the detection unit 12 is replaced with a detection unit 12C as compared with the lane change detection device 10.
[0058] Referring to FIG. 12, the frequency spectrum characteristics obtained by performing FFT on the vehicle vibration data when the vehicle is traveling in the first lane and the frequency spectrum characteristics obtained by performing FFT on the vehicle vibration data when the vehicle is traveling in the second lane are shown. As can be seen from FIG. 12, the frequency spectrum characteristics are different when the vehicle is traveling in the first lane and when the vehicle is traveling in the second lane. Therefore, the detection unit 12C uses the spectral centroid as an index representing the characteristics of the frequency spectrum characteristics.
[0059] That is, the detection unit 12C calculates the spectral centroid of the frequency spectrum as a specific characteristic in the current frame of the vehicle vibration. Further, the detection unit 12C calculates a centroid shift amount that is the difference between the spectral centroid in the current frame of the vehicle vibration and the spectral centroid in the previous frame of the vehicle vibration. In addition, the detection unit 12C detects whether or not the vehicle has changed lanes based on the travel lane in which the vehicle was traveling in the previous frame of the vehicle vibration and the comparison result between the centroid shift amount in the current frame of the vehicle vibration and the threshold value.
[0060] Note that the detection unit 12C shall be set in advance by performing prior measurement or the like for the above-described threshold value. Also, for the driving lane in which the vehicle was traveling in the previous frame, the detection unit 12C shall be grasped in advance by an arbitrary method (for example, a method using an image captured by the camera 40 installed on the road R).
[0061] Subsequently, with reference to FIG. 13, a schematic operation example of the lane change detection system 1C will be described. When the acquisition unit 11 acquires data on the vehicle vibration of the vehicle traveling on the road R from the sensing device 30, the detection unit 12C performs FFT on the current frame portion of the vehicle vibration of the vehicle (step S41), and calculates the spectral centroid of the frequency spectrum in the current frame of the vehicle vibration (step S42). Further, the detection unit 12C calculates the centroid shift amount, which is the difference between the spectral centroid in the current frame of the vehicle vibration and the spectral centroid in the previous frame of the vehicle vibration (step S43). Next, the detection unit 12C determines whether the driving lane in which the vehicle was traveling in the previous frame of the vehicle vibration is the first lane or the second lane (step S44).
[0062] When the driving lane in the previous frame is the first lane close to the optical fiber 20, the detection unit 12C determines whether the centroid shift amount is less than the threshold value (step S45). If the centroid shift amount is less than the threshold value (YES in step S45), the detection unit 12C determines that a lane change of the vehicle has occurred (step S47). On the other hand, if the centroid shift amount is not less than the threshold value (NO in step S45), the process returns to step S41.
[0063] Also, when the driving lane of the previous frame is the second lane far from the optical fiber 20, the detection unit 12C determines whether the center-of-gravity shift amount is equal to or greater than a threshold value (step S46). When the center-of-gravity shift amount is equal to or greater than the threshold value (YES in step S46), the detection unit 12C determines that a lane change of the vehicle has occurred (step S47). On the other hand, when the center-of-gravity shift amount is not equal to or greater than the threshold value (NO in step S46), the detection unit 12C returns to step S41.
[0064] Note that when the detection unit 12C returns to step S41, after setting the current frame and the next frame of the vehicle vibration of the vehicle as the previous frame and the current frame, respectively, the detection unit 12C performs the process of step S41.
[0065] As described above, according to the fourth embodiment, the detection unit 12C calculates the spectral centroid of the frequency spectrum in the current frame of the vehicle vibration of the vehicle, and further calculates the center-of-gravity shift amount, which is the difference between the spectral centroid in the current frame of the vehicle vibration and the spectral centroid in the previous frame of the vehicle vibration. Then, the detection unit 12C detects the presence or absence of a lane change of the vehicle based on the driving lane in which the vehicle was traveling when the previous frame of the vehicle vibration and the comparison result between the center-of-gravity shift amount in the current frame of the vehicle vibration and the threshold value. Thereby, it is possible to detect a lane change of a vehicle traveling on the road R. Other effects are the same as those of the first embodiment described above.
[0066] <Embodiment 5> First, with reference to FIG. 14, a schematic configuration example of the lane change detection system 1D will be described. The lane change detection system 1D includes a lane change detection device 10D. The lane change detection device 10D has a configuration in which the detection unit 12 is replaced with a detection unit 12D as compared with the lane change detection device 10.
[0067] The detection unit 12D includes a learning model 120 that has learned in advance the feature amounts when a lane change of the vehicle occurs. The feature quantities learned by the learning model 120 include at least a specific characteristic of the vehicle vibration in the current frame of the vehicle and the driving lane on which the vehicle was traveling at the time of the previous frame of the vehicle vibration.
[0068] Therefore, the detection unit 12D inputs, as feature quantities, a specific characteristic of the vehicle vibration in the current frame of the vehicle and the driving lane on which the vehicle was traveling at the time of the previous frame of the vehicle vibration, into the learning model 120.
[0069] Then, from the learning model 120, for example, the probability that a lane change of the vehicle has occurred is output. Therefore, the detection unit 12D detects the presence or absence of a lane change of the vehicle based on the output of the learning model 120.
[0070] Note that the feature quantities learned by the learning model 120 may be added. For example, the learning model 120 may add, in addition to the driving lane, the driving speed, the vehicle type, etc. as the feature quantities of the vehicle at the time of the previous frame of the vehicle vibration. By adding the feature quantities, the stabilization of the detection accuracy of the lane change can be achieved.
[0071] Subsequently, with reference to FIGS. 15 to 17, a schematic operation example of the lane change detection system 1D will be described. In FIGS. 15 to 17, it is assumed that the learning model 120 has learned the driving lane, the driving speed, and the vehicle type as the feature quantities of the vehicle at the time of the previous frame of the vehicle vibration.
[0072] First, with reference to FIG. 15, an operation example in the case of using the average vibration intensity as a specific characteristic in the current frame of the vehicle vibration will be described in the same manner as in the above-described Embodiment 2. When the acquisition unit 11 acquires the vehicle vibration data of the vehicle traveling on the road R from the sensing device 30, the detection unit 12D calculates the average vibration intensity in the current frame of the vehicle vibration of the vehicle, and inputs the calculated average vibration intensity into the learning model 120 (step S51). In addition, the detection unit 12D inputs the driving lane, the driving speed, and the vehicle type into the learning model 120 as the vehicle information of the vehicle at the time of the previous frame of the vehicle vibration (step S52).
[0073] Then, for example, the probability of a lane change of the vehicle is output from the learning model 120 (step S53). Therefore, the detection unit 12D detects the presence or absence of a lane change of the vehicle based on the output of the learning model 120 (step S54).
[0074] Subsequently, with reference to FIG. 16, in the same manner as in the above-described Embodiment 3, an operation example in the case of using the average vibration intensity in a specific frequency band as a specific characteristic in the current frame of vehicle vibration will be described.
[0075] When the acquisition unit 11 acquires the vehicle vibration data of the vehicle traveling on the road R from the sensing device 30, the detection unit 12D performs FFT on a part of the current frame of the vehicle vibration of the vehicle (step S61). Further, the detection unit 12D calculates the average vibration intensity in a specific frequency band in the current frame, and inputs the calculated average vibration intensity to the learning model 120 (step S62). In addition, the detection unit 12D inputs the traveling lane, traveling speed, and vehicle type to the learning model 120 as the vehicle information of the vehicle at the previous frame of the vehicle vibration (step S63).
[0076] Then, for example, the probability of a lane change of the vehicle is output from the learning model 120 (step S64). Therefore, the detection unit 12D detects the presence or absence of a lane change of the vehicle based on the output of the learning model 120 (step S65).
[0077] Subsequently, with reference to FIG. 17, in the same manner as in the above-described Embodiment 4, an operation example in the case of using the spectral centroid of the frequency spectrum as a specific characteristic in the current frame of vehicle vibration will be described.
[0078] When the acquisition unit 11 acquires data on vehicle vibration of a vehicle traveling on the road R from the sensing device 30, the detection unit 12D performs FFT on the portion of the current frame of the vehicle vibration of the vehicle (step S71), and calculates the spectral centroid of the frequency spectrum in the current frame of the vehicle vibration (step S72). Further, the detection unit 12D calculates the centroid shift amount, which is the difference between the spectral centroid in the current frame of the vehicle vibration and the spectral centroid in the previous frame of the vehicle vibration, and inputs the calculated centroid shift amount to the learning model 120 (step S73). In addition, the detection unit 12D inputs the travel lane, travel speed, and vehicle type as vehicle information of the vehicle at the time of the previous frame of the vehicle vibration to the learning model 120 (step S74).
[0079] Then, the learning model 120 outputs, for example, the probability that a lane change of the vehicle has occurred (step S75). Therefore, the detection unit 12D detects the presence or absence of a lane change of the vehicle based on the output of the learning model 120 (step S76).
[0080] As described above, according to the fifth embodiment, the detection unit 12D includes a learning model 120 that has previously learned the feature amount when a lane change of the vehicle occurs. The detection unit 12D inputs a feature amount including at least a specific characteristic in the current frame of the vehicle vibration of the vehicle and the travel lane on which the vehicle was traveling at the time of the previous frame of the vehicle vibration to the learning model 120. Then, the detection unit 12D detects the presence or absence of a lane change of the vehicle based on the output of the learning model 120. Thereby, it is possible to detect a lane change of a vehicle traveling on the road R. Other effects are the same as those of the first embodiment described above.
[0081] <Embodiment 6> First, with reference to FIG. 18, a schematic configuration example of the lane change detection system 1E will be described. The lane change detection system 1E includes a lane change detection device 10E. The lane change detection device 10E has a configuration in which a specific unit 13 is added as compared with the lane change detection device 10.
[0082] Here, referring to FIG. 19, consider the case where there is a fallen object or a broken-down vehicle on the road R. Here, the fallen object or the broken-down vehicle is present in the second lane far from the optical fiber 20. In this case, when a vehicle traveling in the second lane notices the presence of the fallen object or the broken-down vehicle, it is considered that the vehicle will change lanes to the first lane in order to avoid the fallen object or the broken-down vehicle.
[0083] Therefore, at the position where there is a fallen object or a broken-down vehicle on the road R, it is considered that the number of vehicles changing lanes will increase. Thus, the specific part 13 specifies the position where lane changes frequently occur as an abnormal occurrence position such as the presence of a fallen object or a broken-down vehicle.
[0084] Specifically, when the detection part 12 determines that a lane change of a vehicle has occurred, first, the specific part 13 specifies the position on the road R where the lane change of the vehicle has occurred. Here, the specific part 13 specifies the position where the vehicle vibration for which data has been acquired by the acquisition part 11 has occurred (the distance from the optical fiber 20 of the sensing device 30) as the position where the lane change has occurred.
[0085] Next, the specific part 13 determines whether or not lane changes have occurred a predetermined number of times or more at the position specified above. If lane changes have occurred a predetermined number of times or more at the position specified above, the specific part 13 specifies the position specified above as an abnormal occurrence position such as the presence of a fallen object or a broken-down vehicle.
[0086] Subsequently, referring to FIG. 20, a schematic operation example of the lane change detection system 1E will be described. First, the processes of steps S81 to S83 similar to steps S11 to S13 in FIG. 5 are performed. In step S83, when the detection part 12 determines that a lane change of a vehicle has occurred (YES in step S83), the specific part 13 specifies the position on the road R where the lane change of the vehicle has occurred (step S84).
[0087] Next, the specifying unit 13 determines whether lane changes have occurred a predetermined number of times or more at the position specified in step S84 (step S85). When the specifying unit 13 determines that lane changes have occurred a predetermined number of times or more at the position specified in step S84 (YES in step S85), the specifying unit 13 specifies the position specified in step S84 as the abnormal occurrence position (step S86). On the other hand, when the specifying unit 13 determines that lane changes have not occurred a predetermined number of times or more at the position specified in step S84 (NO in step S85), the process ends.
[0088] As described above, according to the sixth embodiment, when the specifying unit 13 determines that a lane change of the vehicle has occurred by the detection unit 12, the specifying unit 13 specifies the position where the lane change of the vehicle on the road R has occurred. When lane changes have occurred a predetermined number of times or more at that position, the specifying unit 13 specifies that position as the abnormal occurrence position. Thereby, it is possible to specify an abnormal occurrence position such as the presence of a fallen object or a breakdown vehicle. Other effects are the same as those of the first embodiment described above.
[0089] In the sixth embodiment, the number of lane changes that have occurred is used as a parameter for determining whether lane changes occur frequently, but it is not limited to this. As the above-described parameter, other parameters such as the number of lane changes per unit time and the ratio of vehicles that have changed lanes among the vehicles traveling in the corresponding lane may be used.
[0090] Also, in the sixth embodiment, the lane change detection device 10E is provided with the detection unit 12, but any one of the detection units 12A, 12B, 12C, and 12D may be provided instead of the detection unit 12.
[0091] <Other Embodiments> In the above-described Embodiments 1 to 6, the acquisition unit 11, the detection units 12, 12A, 12B, 12C, 12D, and the specifying unit 13 are provided inside the lane change detection devices 10, 10A, 10B, 10C, 10D, 10E. However, the present invention is not limited to this. The acquisition unit 11, the detection units 12, 12A, 12B, 12C, 12D, and the specifying unit 13 may be provided in different separate devices from each other, or may be provided on the cloud. FIG. 21 shows a configuration example of a lane change detection system 1F in which the acquisition unit 11 and the detection unit 12 are provided in different separate devices from each other or on the cloud. Note that in the lane change detection system 1F shown in FIG. 21, any one of the detection units 12A, 12B, 12C, 12D may be provided instead of the detection unit 12, or the specifying unit 13 may be additionally provided.
[0092] In the above-described Embodiments 1 to 6, the two-lane road R has been described as an example. However, the road R may be a road with three or more lanes. In the case of a road R with three or more lanes, for example, in FIGS. 7, 10, and 13 described above, branches may be added for each lane in steps S22, S33, and S44.
[0093] <Hardware Configuration of Lane Change Detection Device According to Embodiment> Subsequently, with reference to FIG. 22, a hardware configuration example of a computer 90 that realizes the above-described lane change detection devices 10, 10A, 10B, 10C, 10D, 10E will be described.
[0094] As shown in FIG. 22, the computer 90 includes a processor 91, a memory 92, a storage 93, an input / output interface (input / output I / F) 94, a communication interface (communication I / F) 95, and the like. The processor 91, the memory 92, the storage 93, the input / output interface 94, and the communication interface 95 are connected by a data transmission path for transmitting and receiving data to and from each other.
[0095] The processor 91 is an arithmetic processing device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The memory 92 is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The storage 93 is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a memory card. Also, the storage 93 may be a memory such as a RAM or a ROM.
[0096] A program is stored in the storage 93. When this program is loaded into a computer, it includes a set of instructions (or software code) for causing the computer 90 to perform one or more functions in the above-described lane change detection devices 10, 10A, 10B, 10C, 10D, 10E. The components in the above-described lane change detection devices 10, 10A, 10B, 10C, 10D, 10E may be realized by the processor 91 reading and executing the program stored in the storage 93. Also, the storage function in the above-described lane change detection devices 10, 10A, 10B, 10C, 10D, 10E may be realized by the memory 92 or the storage 93.
[0097] Also, the above-described program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, a computer-readable medium or a tangible storage medium includes a RAM, a ROM, a flash memory, an SSD, or other memory technologies, a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disc), a Blu-ray (registered trademark) disc, or other optical disc storage, a magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, a transitory computer-readable medium or a communication medium includes electrical, optical, acoustic, or other forms of propagated signals.
[0098] The input / output interface 94 is connected to a display device 941, an input device 942, a sound output device 943, etc. The display device 941 is a device that displays a screen corresponding to drawing data processed by the processor 91, such as an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube) display, or a monitor. The input device 942 is a device that receives the operator's operation input, and examples thereof include a keyboard, a mouse, and a touch sensor. The display device 941 and the input device 942 may be integrated and realized as a touch panel. The sound output device 943 is a device that acoustically outputs sound corresponding to acoustic data processed by the processor 91, such as a speaker.
[0099] The communication interface 95 transmits and receives data to and from an external device. For example, the communication interface 95 communicates with an external device via a wired communication path or a wireless communication path.
[0100] As described above, the present disclosure has been described with reference to the embodiments, but the present disclosure is not limited to the above-described embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure. And each embodiment can be combined with other embodiments as appropriate.
[0101] Also, each drawing is merely an example for explaining one or more embodiments. Each drawing is not associated with only one specific embodiment, but may be associated with one or more other embodiments. As can be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with the features or steps shown in one or more other drawings to create, for example, embodiments that are not explicitly illustrated or described. Not all of the features or steps shown in any one drawing for explaining exemplary embodiments are necessarily essential, and some features or steps may be omitted. The order of the steps described in any drawing may be changed as appropriate.
[0102] Also, some or all of the above embodiments may be described as follows, but are not limited thereto. (Appendix 1) An acquisition unit that acquires data of vehicle vibration indicating vibration generated by the running of a vehicle on a road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; A detection unit that detects whether or not the vehicle has changed lanes based on a specific characteristic in the current frame of the vehicle vibration and the driving lane in which the vehicle was traveling in the previous frame of the vehicle vibration. Lane change detection system. (Appendix 2) The detection unit Calculates an average vibration intensity as a specific characteristic in the current frame of the vehicle vibration, Detects whether or not the vehicle has changed lanes based on the driving lane in which the vehicle was traveling in the previous frame of the vehicle vibration and the comparison result between the average vibration intensity in the current frame of the vehicle vibration and a threshold value. The lane change detection system according to Appendix 1. (Appendix 3) The detection unit Calculates an average vibration intensity in a specific frequency band as a specific characteristic in the current frame of the vehicle vibration, Detects whether or not the vehicle has changed lanes based on the driving lane in which the vehicle was traveling in the previous frame of the vehicle vibration and the comparison result between the average vibration intensity in the specific frequency band in the current frame of the vehicle vibration and a threshold value. The lane change detection system according to Appendix 1. (Appendix 4) The specific frequency band is a band in which the difference between the average vibration intensity of the vehicle vibration before the lane change of the vehicle and the average vibration intensity of the vehicle vibration after the lane change of the vehicle is equal to or greater than a predetermined value. The lane change detection system according to Appendix 3. (Appendix 5) The detection unit As a specific characteristic in the current frame of the vehicle vibration, calculate the spectral centroid of the frequency spectrum, Calculate the centroid shift amount, which is the difference between the spectral centroid in the current frame of the vehicle vibration and the spectral centroid in the previous frame of the vehicle vibration, Based on the driving lane on which the vehicle was traveling in the previous frame of the vehicle vibration and the comparison result between the centroid shift amount in the current frame of the vehicle vibration and the threshold value, detect whether the vehicle has changed lanes. The lane change detection system according to Supplementary Note 1. (Supplementary Note 6) The detection unit Is equipped with a learning model that has previously learned the feature amounts when a lane change of the vehicle occurs, Using the specific characteristic in the current frame of the vehicle vibration and the driving lane on which the vehicle was traveling in the previous frame of the vehicle vibration as feature amounts, input them into the learning model, Based on the output of the learning model, detect whether the vehicle has changed lanes. The lane change detection system according to Supplementary Note 1. (Supplementary Note 7) When it is determined by the detection unit that a lane change of the vehicle has occurred, specify the position where the lane change of the vehicle on the road has occurred. If the lane change has occurred a predetermined number of times or more at the position, further include a specifying unit that specifies the position as an abnormal occurrence position. The lane change detection system according to Supplementary Note 1. (Supplementary Note 8) An acquisition unit that acquires data of vehicle vibration indicating the vibration generated by the running of the vehicle on the road from a sensing device that measures the vibration generated on the road using an optical fiber buried in the road, A detection unit that detects whether the vehicle has changed lanes based on the specific characteristic in the current frame of the vehicle vibration and the driving lane on which the vehicle was traveling in the previous frame of the vehicle vibration. Lane change detection device. (Supplementary Note 9) A lane change detection method executed by a lane change detection device, Obtaining data of vehicle vibrations indicating vibrations generated by the running of a vehicle on a road from a sensing device that measures vibrations generated on the road using an optical fiber embedded in the road; detecting whether the vehicle has changed lanes based on a specific characteristic in the current frame of the vehicle vibration and the driving lane on which the vehicle was running in the previous frame of the vehicle vibration. Lane change detection method. (Appendix 10) Causing a computer to execute a procedure of obtaining data of vehicle vibrations indicating vibrations generated by the running of a vehicle on the road from a sensing device that measures vibrations generated on the road using an optical fiber embedded in the road; and execute a procedure of detecting whether the vehicle has changed lanes based on a specific characteristic in the current frame of the vehicle vibration and the driving lane on which the vehicle was running in the previous frame of the vehicle vibration. Program.
[0103] Note that some or all of the elements (for example, configurations and functions) described in Appendices 2 to 7 that are subordinate to Appendix 1 may be subordinate to Appendices 8 to 10 in the same subordinate relationship as Appendices 2 to 7. Some or all of the elements described in any appendix can be applied to various hardware, software, recording means for recording software, systems, and methods.
Explanation of Signs
[0104] 1, 1A, 1B, 1C, 1D, 1E, 1F Lane change detection system 10, 10A, 10B, 10C, 10D, 10E Lane change detection device 11 Acquisition unit 12, 12A, 12B, 12C, 12D Detection unit 120 Learning model 13 Identification unit 20 Optical fiber 30 Sensing device 40 Camera 90 Computer 91 Processor 92 Memory 93 Storage 94 Input / Output Interface 941 Display Device 942 Input Device 943 Audio Output Device 95 Communication Interface R Road
Claims
1. An acquisition unit that acquires data of vehicle vibration indicating vibration generated by the running of a vehicle on a road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; A detection unit that detects whether or not the vehicle has changed lanes based on a specific characteristic in the current frame of the vehicle vibration and the driving lane in which the vehicle was running in the previous frame of the vehicle vibration. A lane change detection system comprising: Lane change detection system.
2. The detection unit: As a specific characteristic in the current frame of the vehicle vibration, calculates an average vibration intensity; Detects whether or not the vehicle has changed lanes based on the driving lane in which the vehicle was running in the previous frame of the vehicle vibration and the comparison result between the average vibration intensity in the current frame of the vehicle vibration and a threshold value. The lane change detection system according to claim 1. The lane change detection system according to claim 1.
3. The detection unit: As a specific characteristic in the current frame of the vehicle vibration, calculates an average vibration intensity in a specific frequency band; Detects whether or not the vehicle has changed lanes based on the driving lane in which the vehicle was running in the previous frame of the vehicle vibration and the comparison result between the average vibration intensity in the specific frequency band in the current frame of the vehicle vibration and a threshold value. The lane change detection system according to claim 1. The lane change detection system according to claim 1.
4. The specific frequency band is a band in which the difference between the average vibration intensity of the vehicle vibration before the vehicle changes lanes and the average vibration intensity of the vehicle vibration after the vehicle changes lanes is equal to or greater than a predetermined value. The lane change detection system according to claim 3. The lane change detection system according to claim 3.
5. The detection unit: As a specific characteristic in the current frame of the vehicle vibration, calculates the spectral centroid of the frequency spectrum; Calculates a centroid shift amount that is the difference between the spectral centroid in the current frame of the vehicle vibration and the spectral centroid in the previous frame of the vehicle vibration; Detects whether or not the vehicle has changed lanes based on the driving lane in which the vehicle was running in the previous frame of the vehicle vibration and the comparison result between the centroid shift amount in the current frame of the vehicle vibration and a threshold value. The lane change detection system according to claim 1. The lane change detection system according to claim 1.
6. The detection unit: Is provided with a learning model that has previously learned the feature amounts when the lane change of the vehicle occurs; Inputs, as feature amounts, a specific characteristic in the current frame of the vehicle vibration and the driving lane in which the vehicle was running in the previous frame of the vehicle vibration into the learning model. Detecting whether there is a lane change of the vehicle based on the output of the learning model. The lane change detection system according to claim 1.
7. When it is determined by the detection unit that a lane change of the vehicle has occurred, specifying the position where the lane change of the vehicle on the road has occurred, and when the lane change has occurred a predetermined number of times or more at the position, further comprising a specifying unit that specifies the position as an abnormal occurrence position. The lane change detection system according to claim 1.
8. An acquisition unit that acquires data of vehicle vibration indicating vibration generated by the running of a vehicle on the road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; A detection unit that detects whether there is a lane change of the vehicle based on a specific characteristic in the current frame of the vehicle vibration and the driving lane in which the vehicle was traveling when in the previous frame of the vehicle vibration. Lane change detection device.
9. A lane change detection method executed by a lane change detection device, acquiring data of vehicle vibration indicating vibration generated by the running of a vehicle on the road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; detecting whether there is a lane change of the vehicle based on a specific characteristic in the current frame of the vehicle vibration and the driving lane in which the vehicle was traveling when in the previous frame of the vehicle vibration. Lane change detection method.
10. On a computer, a procedure for acquiring data of vehicle vibration indicating vibration generated by the running of a vehicle on the road from a sensing device that measures vibration generated on the road using an optical fiber buried in the road; a procedure for detecting whether there is a lane change of the vehicle based on a specific characteristic in the current frame of the vehicle vibration and the driving lane in which the vehicle was traveling when in the previous frame of the vehicle vibration, and causing the procedure to be executed. Program.