Traffic monitoring systems, traffic monitoring methods, and programs

Abstract

This invention provides a distributed optical fiber sensing (DFOS) system and a method for using it. [Solution] The traffic monitoring system comprises a distributed acoustic sensor (DAS) connected to an optical fiber and configured to generate distributed optical fiber sensing (DFOS) data, and a traffic monitoring device configured to receive the DFOS data, receive camera data captured by a camera having a camera capture range, calibrate the DFOS data using the camera data, and monitor traffic outside the camera capture range using the calibrated DFOS data.

Description

Technical Field

[0001] The present disclosure relates to a distributed fiber optic sensing (DFOS) system and methods of using the same.

Background Art

[0002] Optical fibers are present along a very large number of roads. Distributed acoustic sensors (DAS) attached to these optical fibers can detect vibrations at the location where the optical fibers are disposed. In some cases, these vibrations are the result of passing vehicles. DAS can collect data related to the number of vehicles, the lane position of the vehicles, and the vehicle speed.

[0003] DAS generates data based on time and distance to determine traffic parameters. The ability of DAS to detect individual vehicles is related to the amount of noise in the signal detected by DAS.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Improvement in the accuracy of distributed fiber optic sensing (DFOS) data is desired.

Means for Solving the Problems

[0005] Aspects of the present description relate to a traffic monitoring system including a distributed acoustic sensor (DAS) connected to an optical fiber, the DAS being configured to generate distributed fiber optic sensing (DFOS) data. The traffic monitoring system further includes a traffic monitoring device. The traffic monitoring device is configured to receive DFOS data, receive camera data captured by a camera having a camera capture range, calibrate the DFOS data using the camera data, and monitor traffic outside the camera capture range using the calibrated DFOS data.

[0006] Embodiments described herein relate to a traffic monitoring method that includes receiving distributed fiber optic sensing (DFOS) data acquired by a distributed acoustic sensor (DAS) connected to an optical fiber. The traffic monitoring method further includes receiving camera data acquired by a camera having a camera acquisition range. The traffic monitoring method further includes calibrating DFOS data using the camera data. The traffic monitoring method further includes monitoring traffic outside the camera acquisition range using the calibrated DFOS data.

[0007] The embodiments described herein relate to a program that causes a computer to receive distributed fiber optic sensing (DFOS) data acquired by a distributed acoustic sensor (DAS) connected to an optical fiber. The program further causes the computer to receive camera data acquired by a camera having a camera acquisition range, to calibrate DFOS data using the camera data, and to monitor traffic outside the camera acquisition range using the calibrated DFOS data.

[0008] The aspects of this disclosure will be best understood, when read in conjunction with the accompanying drawings, as to the modes for carrying out the following inventions. Note that, in accordance with standard industry practice, various features are not depicted to scale. In fact, the dimensions of various features may be arbitrarily enlarged or reduced for clarity in the description. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram of a distributed acoustic sensor (DAS) system along a road, according to several embodiments. [Figure 2] This diagram shows the correlation between camera data and distributed fiber optic sensing (DFOS) data in several embodiments. [Figure 3] This diagram shows the correlation between camera data and DFOS data in several embodiments. [Figure 4]This diagram shows the correlation between camera data and DFOS data in several embodiments. [Figure 5] This is a flowchart illustrating methods for utilizing camera data and DFOS data according to several embodiments. [Figure 6] This is a flowchart illustrating methods for utilizing camera data and DFOS data according to several embodiments. [Figure 7] This is a block diagram of a system for utilizing camera data and DFOS data, according to several embodiments. [Modes for carrying out the invention]

[0010] The following disclosure provides many different embodiments or examples for implementing different features of the subject matter provided. For the sake of brevity, specific examples of components, values, behaviors, materials, arrangements, etc., are described below. Of course, these are merely examples and not limiting. Other components, values, behaviors, materials, arrangements, etc., are possible. For example, the formation of a first feature over or on a second feature in the following description may include embodiments in which the first and second features are formed in direct contact, and may also include embodiments in which additional features may be formed between the first and second features so that the first and second features do not have to be in direct contact. In addition, the disclosure may repeat reference numerals and / or reference letters in various examples. This repetition is for the sake of brevity and clarity and does not in itself prescribe relationships between the various embodiments and / or configurations described.

[0011] Furthermore, spatial relative terms such as “directly below,” “down,” “below,” “up,” and “above” may be used herein to facilitate descriptions of the relationship between one element or feature and another, as shown in the figures. Spatial relative terms are intended to encompass different orientations of the device in use or operation, in addition to the orientation depicted in the figures. The device may be oriented in other ways (by rotating 90 degrees or to other orientations), and the spatial relative descriptors used herein may be interpreted accordingly.

[0012] Utilizing data from optical fibers along roads is useful for determining traffic volume, speed, accidents, and other events along those roads. To enhance the usefulness of traffic information obtained based on data from optical fibers, the precise location along the road corresponding to the traffic information is determined. Since optical fibers are not always installed precisely parallel to the road, simply determining the distance along the optical fiber corresponding to the received traffic information may not provide sufficient accuracy in some cases. Identifying fixed reference points, such as bridges along the road, helps improve accuracy by enabling a correlation between known geographical locations and distances along the optical fiber. By utilizing these fixed reference points, the positional accuracy of traffic information is improved. In some cases, fixed reference points include known locations of traffic cameras used to capture road images.

[0013] In addition to determining the location of fixed reference points along the optical fiber, identifying the location of additional optical fibers helps improve the positional accuracy of traffic information. Optical fibers installed along roads often have additional sections of optical fiber, such as optical fiber loops, to provide additional optical fibers to assist in the repair or relocation of installed optical fibers. Considering additional sections of optical fiber, such as optical fiber loops, helps improve positional accuracy by taking into account the difference between the optical fiber length and the road length introduced by such additional sections of optical fiber. Higher positional accuracy can be obtained by correlating camera data with distributed optical fiber sensing (DFOS) data. This improvement in positional accuracy improves the accuracy of determining traffic conditions or events, such as accidents or congestion, in locations where traffic cameras are absent or not functioning.

[0014] Improving the location accuracy of traffic information will be more useful for urban planning, for example, by determining which locations along roads are traffic congestion points, where traffic accidents occur more frequently, and how traffic patterns shift within the road system. This information will be useful in planning improvements to existing roads or the construction of new roads.

[0015] Furthermore, accurate location information in traffic data assists in the navigation of vehicles traveling along roads. By providing drivers with more accurate traffic data, navigation systems and / or navigation applications become more useful to drivers. Improved navigation accuracy is also beneficial to autonomous driving or driver assistance functions in vehicles. By accurately determining where traffic congestion or accidents have occurred, autonomous vehicles or driver assistance systems can guide vehicles along more efficient routes.

[0016] Figure 1 is a schematic diagram of a distributed acoustic sensor (DAS) system 100 along a road 130 according to several embodiments. The DAS system 100 includes a traffic monitoring device 111 that communicates with a DAS 112. The DAS system 100 further includes an optical fiber 121 connected to the DAS 112. The optical fiber 121 runs along the road 130. The road 130 includes two lanes. A single vehicle 140 is on the road 130. Those skilled in the art will understand that, in some cases, additional vehicles may be on the road 130. The use of data for multiple vehicles will be described in more detail below. Some vehicles on the road 130 are larger than other vehicles on the road 130. Although the description refers to the optical fiber 121, those skilled in the art will understand that in some embodiments the optical fiber 121 includes a multifiber bundle. The DAS system 100 further includes a first traffic camera 150a and a second traffic camera 150b, collectively referred to as traffic camera 150.

[0017] As vehicle 140 passes along road 130, vehicle 140 generates vibrations. These vibrations alter the way light propagates along optical fiber 121. DAS 112 is connected to optical fiber 121 and sends an optical signal to optical fiber 121, and detects the light returned from optical fiber 121. The resulting data is called waterfall data. Waterfall data provides information related to the number of vehicles on road 130, the direction of travel by the vehicles, vehicle speed, and the lane position of the vehicles.

[0018] The road 130 in Figure 1 is on a firm surface. The firm surface does not vibrate with an amplitude high enough to obscure the detection of vehicles 140 traveling along the road 130. As a result, the DAS 112 can accurately detect vehicles 140 traveling along the road 130. In some embodiments, the road 130 includes at least a bridge (also known as a bridge, hereafter the same) or a small vehicle.

[0019] Unlike a rigid ground, a bridge exhibits different vibration characteristics such as attenuation. The vibration characteristics of a bridge are affected by the length of the bridge, the building materials of the bridge, wind, and other factors. These differences in the vibration characteristics of the bridge can be utilized to determine where the bridge is located along the optical fiber 121. Small vehicles such as small cars or motorcycles also generate small vibrations, which have little impact on the propagation of the optical signal in the optical fiber 121. As a result, it becomes more difficult to detect smaller vehicles with the DFOS data collected by the DAS.

[0020] The traffic camera 150 captures an image of the road 130 including the position of the vehicle 140 along the road 130. In some embodiments, the traffic camera 150 captures a still image. In some embodiments, the traffic camera 150 captures a video image. In some embodiments, the traffic camera 150 uses visible light to capture an image. In some embodiments, the traffic camera 150 uses non-visible light such as infrared light to capture an image. The traffic camera 150 captures camera data that can be used to identify the position of the vehicle 140 on the road. The position of the vehicle 140 includes both the distance from each of the first traffic camera 150a and the second traffic camera 150b, and the lane of the road 130 on which the vehicle 140 is traveling. In some cases, the traffic camera 150 also captures camera data indicating a lane change by the vehicle 140 and the position along the road 130 where the lane change occurred.

[0021] In some embodiments, camera data can be used to identify or classify the vehicle 140. Classifying the vehicle 140 includes determining the type of the vehicle 140. The type of vehicle is determined based on the size of the vehicle 140, the number of axles of the vehicle 140, identifiable markings on the vehicle 140, or other appropriate criteria. Identifying the vehicle 140 includes determining specific identification information for the vehicle 140. In some embodiments, vehicle identification is performed using camera data capturing the license plate of the vehicle 140. In some embodiments, vehicle identification is performed using other identification information, such as a radio frequency identification (RFID) tag attached to the vehicle 140.

[0022] Camera data from traffic camera 150 is correlated with DFOS data from DAS 112 to improve the accuracy of the DFOS data. As mentioned above, additional sections of optical fiber 121, such as loops, degrade the accuracy of the DFOS data. Also, smaller vehicles have reduced vibrations that can cause DFOS data associated with such smaller vehicles to be lost due to external noise in the DFOS data. By correlating camera data with DFOS data, deviations in the DFOS data are identified, improving the accuracy of the DFOS data. This improvement in DFOS data accuracy is useful for traffic monitoring in areas where traffic camera 150 is not present.

[0023] In many situations, traffic cameras 150 are arranged along sections of road 130 with high traffic volume, while sections of road 130 with low traffic volume do not include traffic cameras 150. When an abnormality such as a traffic accident or traffic congestion occurs in a section of road 130 where there is no traffic camera 150, the only way to identify the existence of the abnormality is either a report from other vehicles or only when the abnormality causes congestion in a section of road 130 that is monitored by traffic camera 150. The arrangement of optical fiber 121 along road 130, including sections with low traffic volume, is less expensive and is often part of the Internet connection facility. By using traffic cameras 150 at available locations to improve the accuracy of DFOS data, it becomes possible to use DFOS data when identifying traffic abnormalities in locations where traffic cameras are not available. Therefore, by using the combined DFOS data calibrated using camera data from traffic camera 150, more comprehensive and accurate traffic monitoring along road 130 is possible.

[0024] In the following description, the focus is on the correlation between DFOS data and camera data executed for a single camera capture range. Those skilled in the art will understand that this description is not limited to a single camera capture range, and by calibrating DFOS data in more camera capture ranges along road 130, the accuracy of DFOS data in locations where traffic camera 150 is not available will be further improved.

[0025] Figure 2 is a diagram 200 correlating camera data 250 and distributed fiber optic sensing (DFOS) data 205 in several embodiments. The DFOS data 205 includes a simplified graph for time and distance. Time is based on a timer in the DAS that acquires the DFOS data, e.g., DAS112 (Figure 1). Distance is based on the distance at which the detected vibrations occurred from the DAS, e.g., DAS112 (Figure 1). Since distance includes both the length along the optical fiber and the distance from the fiber, complex traffic patterns such as lane changes are more difficult to identify separately from the DFOS data 205. The DFOS data 205 is a simplified graph that includes only the identified trajectories of vehicles. The raw waterfall data acquired by the DAS, e.g., DAS112 (Figure 1), has more noise in the DFOS data. The simplified graph in Figure 2 omits noise for clarity and ease of understanding.

[0026] DFOS data 205 includes a first trajectory 210 for a first vehicle and a second trajectory 220 for a second vehicle. The weight of the first trajectory 210 is heavier than the weight of the second trajectory 220. This indicates that the first vehicle generates more vibrations than the second vehicle. Therefore, the first vehicle may be larger than the second vehicle. For example, in some cases, the first vehicle is a truck with three or more axles, and the second vehicle is a commuter car. The gradients of the first trajectory 210 and the second trajectory 220 indicate that the two vehicles are moving at similar speeds, as the first trajectory 210 and the second trajectory 220 are nearly parallel. The first trajectory 210 and the second trajectory 220 also indicate that the vehicles are moving in the direction toward the DAS, as the distance between them decreases as time increases.

[0027] Camera data 250 includes images of a first vehicle 215 and a second vehicle 225. Camera data 250 is correlated with DFOS data 205 to match the first vehicle 215 to a first trajectory 210 and the second vehicle 225 to a second trajectory 220. The correlation between camera data 250 and DFOS data 205 can also be used to identify a first boundary 230 and a second boundary 240 of the camera capture range. The camera capture range corresponds to a section of road, e.g., road 130 (Figure 1), captured by a traffic camera, e.g., traffic camera 150 (Figure 1). The locations of the first boundary 230 and the second boundary 240 are based on the known locations of the traffic camera along the road.

[0028] The camera data 250 further includes boundary boxes around the first vehicle 215 and boundary boxes around the second vehicle 225. The boundary boxes are useful for classifying the first vehicle 215 and the second vehicle 225. For example, a larger boundary box indicates a larger vehicle compared to a smaller boundary box. The boundary boxes can also be used to reduce the amount of data examined during further analysis if the camera data 250 is subjected to further analysis, such as a vehicle identification process.

[0029] Between the correlation between camera data 250 and DFOS data 205, the reliability of both types of data is determined to assist in the correlation and tracking of vehicles along the road. The reliability of camera data 250 is based on the visibility of the traffic camera and the distance from the traffic camera to the vehicle. For example, environmental conditions such as fog or rain can reduce the visibility of the traffic camera, thereby lowering the reliability score of camera data 250. In addition, as the distance from the traffic camera to the vehicle increases, the risk of error in applying the boundary box to the vehicle increases, resulting in a lower reliability score for camera data 250.

[0030] The reliability of the DFOS data 205 is based on various trajectory characteristics, such as the intensity, thickness, or spread of vehicle vibrations indicated by the trajectory. For example, the first trajectory 210 has a higher reliability score than the second trajectory 220 due to the weighting of the first trajectory 210. The lower reliability score of the second trajectory 220 is due to the increased risk that the second trajectory 220 cannot be identified from the noise in the DFOS data 205. An example of the second trajectory 220 not being identified from the background noise is at position 260 in the DFOS data 205. At position 260, the second trajectory 220 is discontinuous because the detected vibrations of the second vehicle 225 cannot be identified from the background noise. Position 260 is at a distance d2 from the DAS at time t2.

[0031] To improve tracking of the second vehicle 225, DFOS data 205 is correlated with camera data 250. Using camera data 250, it is determined that the second vehicle 225 is at a distance d1 from the DAS at time t3. This determination facilitates matching the driving pattern of the second vehicle 225 in camera data 250 with the second trajectory 220 in DFOS data 205. Furthermore, the identification of the second vehicle 225 at the point where the vehicle crosses the first boundary 230 of the camera capture range also helps in correlating the second trajectory 220 with the second vehicle 225.

[0032] Correlation of DFOS data 205 with camera data 250 indicates that the first vehicle 215 is at a distance d2 from the DAS at time t1. DFOS data 205 also indicates that the first trajectory 210, with a high confidence score, indicates that the first vehicle 215 is at a location other than position 260 at time t2. As a result, by correlating camera data 250 with DFOS data 205 for the second vehicle, the DAS system, for example, DAS system 100 (Figure 1), can determine the position of the second vehicle 225 at position 260 where the DFOS data 205 is incomplete. Using camera data 250 to track the movement of the first vehicle 215 and the second vehicle 225 between the first boundary 230 and the second boundary 240 helps validate the DFOS data 205 for tracking vehicles outside the camera capture range defined by the first boundary 230 and the second boundary 240.

[0033] Figure 3 is a diagram 300 that correlates camera data 350a and 350b with DFOS data 305 according to several embodiments. In some embodiments, camera data 350a and 350b are similar to camera data 250 (Figure 2), and the specific contents of camera data 350a and 350b are not described in detail for brevity. In some embodiments, DFOS data 305 is similar to DFOS data 205 (Figure 2), and the specific contents of DFOS data 305 are not described in detail for brevity. In contrast to diagram 200 (Figure 2), diagram 300 includes two sets of camera data: first camera data 350a and second camera data 350b, collectively referred to as camera data 350. Both sets of camera data 350 capture the same camera capture range 310. Diagram 300 helps illustrate how correlation between camera data 350 and DFOS data 305 is implemented in high vehicle density situations. In some embodiments, correlating camera data 350 with DFOS data 305 in high vehicle density situations is performed using time thresholds and distance thresholds.

[0034] The time threshold can be used to determine the delay duration required for a second vehicle to reach the same distance from the DAS, e.g., DAS112 (Figure 1), as the first vehicle. In some embodiments, the time threshold is a static value. In some embodiments, the time threshold is determined based on the average speed of one or all vehicles during inspection. For example, as the vehicle speed increases, the delay duration required for a vehicle to reach a certain position decreases. As a result, the time threshold is increased to reduce the risk of inaccurate pattern matching between camera data 350 and DFOS data 305. In some embodiments, the time threshold is in the range of 1.5 seconds to 3 seconds.

[0035] A distance threshold can be used to determine the difference in the positions of multiple vehicles at a given time. In some embodiments, the distance threshold is static. In some embodiments, the distance threshold is adjusted based on the number of lanes on a road, for example, road 130 (Figure 1). In some embodiments, the distance threshold decreases as the number of lanes on the road increases. In some embodiments, the distance threshold is in the range of approximately 1 meter to approximately 3 meters. In some embodiments, separate vehicle trajectories in the DFOS data 305 are identified based on at least one of the distance threshold or the time threshold. In some embodiments, separate vehicle trajectories in the DFOS data 305 are identified based on both the time threshold and the distance threshold.

[0036] DFOS data 305 includes the boundary position for the camera capture range 310. DFOS data 305 includes a first trajectory 320 corresponding to the first vehicle 325 of the first camera data 350a, and a second trajectory 330 corresponding to the second vehicle 335 of the first camera data 350a. DFOS data 305 also includes a third trajectory 360 corresponding to the third vehicle 365 of the second camera data 350b, a fourth trajectory 370 corresponding to the fourth vehicle 375 of the second camera data 350b, and a fifth trajectory 380 corresponding to the fifth vehicle 385 of the second camera data 350b.

[0037] The DFOS data 305 includes a time threshold Tt between the first trajectory 320 and the second trajectory 330 at a distance d3. The time threshold Tt is also depicted in the first camera data 350a for illustrative purposes only. The DFOS data 305 further includes a distance threshold Dt between the first trajectory 320 and the second trajectory 330 at time t8. The distance threshold Dt is also depicted in the first camera data 350a for illustrative purposes only.

[0038] When tracking vehicles using DFOS, using time thresholds or distance thresholds helps distinguish individual vehicles for vehicle tracking purposes. When vehicles are close in time or location, the accuracy of vehicle tracking decreases. By correlating camera data 350 with DFOS data 305, vehicles detected by DFOS data 305 at a particular time or location can be corroborated by camera data 350. This corroboration helps improve the accuracy of vehicle tracking using DFOS data 305 outside the camera acquisition range 310. For example, by using camera data 350 to corroborate the position of a second vehicle 335 at times t7 and t8 detected by DFOS data 305, it is determined that the second trajectory 330 corresponds to the second vehicle 335, thus enabling tracking of the second vehicle outside the camera acquisition range 310.

[0039] By applying time and distance thresholds to the DFOS data 305, the third trajectory 360, the fourth trajectory 370, and the fifth trajectory 380 are identified within the DFOS data. By correlating the DFOS data 305 with the second camera data 350b, the positions of the third vehicle 365, the fourth vehicle 375, and the fifth vehicle 385 are corroborated by the positions and times detected by the DFOS data 305. As a result, the DFOS data 305 can track the third vehicle 365, the fourth vehicle 375, and the fifth vehicle 385 outside the camera acquisition range 310.

[0040] Figure 4 is a diagram 400 that correlates camera data 450a and 450b with DFOS data 405 according to several embodiments. In some embodiments, camera data 450a and 450b are similar to camera data 250 (Figure 2), and the specific contents of camera data 450a and 450b are not described in detail for brevity. In some embodiments, DFOS data 405 is similar to DFOS data 205 (Figure 2), and the specific contents of DFOS data 405 are not described in detail for brevity. In contrast to diagram 200 (Figure 2), diagram 400 includes two sets of camera data: first camera data 450a and second camera data 450b, collectively referred to as camera data 450. Both sets of camera data 450 capture the same camera capture range 410. Diagram 400 helps illustrate how correlation between camera data 450 and DFOS data 405 is implemented in high vehicle density and vehicle overtaking situations.

[0041] DFOS data 405 includes the boundary position for the camera capture range 410. DFOS data 405 includes a first trajectory 420 corresponding to the first vehicle 425 of the first camera data 450a, and a second trajectory 430 corresponding to the second vehicle 435 of the first camera data 450a. DFOS data 405 also includes a third trajectory 460 corresponding to the third vehicle 465 of the second camera data 450b, a fourth trajectory 470 corresponding to the fourth vehicle 475 of the second camera data 450b, and a fifth trajectory 480 corresponding to the fifth vehicle 485 of the second camera data 450b.

[0042] The DFOS data 405 further includes a first position 490 where the first trajectory 420 and the second trajectory 430 are too close to each other for separate identification and tracking. The first position 490 indicates the position where the first vehicle 425 overtakes the second vehicle 435. Due to the interval between the first trajectory 420 and the second trajectory 430 being smaller than the time threshold and distance threshold, respectively, it is not possible to track the first vehicle 425 and the second vehicle 435 separately at distance d5. At distance d4, the first trajectory 420 can be distinguished from the second trajectory 430 by at least one of the time threshold or distance threshold. To facilitate the assignment of trajectories in the DFOS data 405 to corresponding vehicles at distance d4, the DFOS data 405 is correlated with the first camera data 450a. The DFOS data 405 is correlated with the first camera data 450a in a similar manner to that described above with respect to diagram 200 (Figure 2). In some embodiments, the correlation further takes into account the gradients of the first trajectory 420 and the second trajectory 430 at a point in time prior to the first position 490, as well as the gradients of unassigned trajectories at a point in time after the first position 490. Matching the gradients of the various trajectories in the DFOS data 405 helps to improve the accuracy of vehicle assignment to trajectories after the first position 490. Once the trajectories in the DFOS data 405 are assigned to the corresponding vehicles, the DFOS data 405 can be used to track the first vehicle 425 and the second vehicle 435 outside the camera acquisition range 410.

[0043] The DFOS data 405 further includes a second location 495 where the third trajectory 460, the fourth trajectory 470, and the fifth trajectory 480 are too close to each other for separate identification and tracking. The second location 495 indicates the location where the third vehicle 465, the fourth vehicle 475, and the fifth vehicle 485 are close to each other, for example, due to high traffic density. Due to the intervals between the third trajectory 460, the fourth trajectory 470, and the fifth trajectory 480 being smaller than the time threshold and the distance threshold, respectively, it is not possible to track the third vehicle 465, the fourth vehicle 475, and the fifth vehicle 485 separately at a distance d5. The third trajectory 460, the fourth trajectory 470, and the fifth trajectory 480 are distinguishable from each other at a distance d4 by at least one of the time threshold or the distance threshold. To facilitate the assignment of trajectories in the DFOS data 405 to corresponding vehicles at distance d4, the DFOS data 405 is correlated with second camera data 450b. The DFOS data 405 is correlated with the second camera data 450b in a similar manner to that described above with respect to diagram 200 (Figure 2). In some embodiments, the correlation further takes into account the gradient of at least one of the third trajectories 460, fourth trajectories 470, or fifth trajectories 480 at a point in time prior to the second position 495, as well as the gradient of the unassigned trajectories at a point in time after the second position 495. Matching the gradients of the various trajectories in the DFOS data 405 helps to improve the accuracy of vehicle assignment to trajectories after the second position 495. Once the trajectory of the DFOS data 405 is assigned to the corresponding vehicle, the DFOS data 405 can be used to track the third vehicle 465, the fourth vehicle 475, and the fifth vehicle 485 outside the camera acquisition range 410.

[0044] In situations where the DFOS data 405 can no longer accurately track a vehicle, such as at the first location 490 or the second location 495, the DFOS data 405 is correlated with the camera data 450 for the time after it has become impossible to accurately track a separately trackable vehicle. This correlation between the DFOS data 405 and the camera data 450 at a later time helps to re-establish the trajectory assignment of the DFOS data 405 based on the information available from the camera data 450. Compared to other methods, the correlation between the camera data 450 and the DFOS data 405 helps to improve the accuracy of tracking vehicles outside the camera acquisition range 410. This improved vehicle tracking accuracy is useful for traffic monitoring outside the camera acquisition range 410.

[0045] Figure 5 is a flowchart of Method 500 for utilizing camera data and DFOS data in several embodiments. Method 500 can be used for utilizing camera data and DFOS data for traffic monitoring. In some embodiments, Method 500 can be used to perform the functions described with respect to Diagram 200 (Figure 2), Diagram 300 (Figure 3), or Diagram 400 (Figure 4). In some embodiments, Method 500 can be used to perform functions other than those described above. In some embodiments, Method 500 is implemented using DAS System 100 (Figure 1) or System 700 (Figure 7). In some embodiments, Method 500 is implemented using a system other than DAS System 100 (Figure 1) or System 700 (Figure 7).

[0046] In operation 505, camera data is received. The camera data includes an image of a road, including one or more vehicles traveling along the road. In some embodiments, the camera data is captured using a traffic camera 150 (Figure 1). In some embodiments, the camera data is captured using a camera other than the traffic camera 150 (Figure 1). In some embodiments, the camera data includes camera data 250 (Figure 2), camera data 350 (Figure 3), or camera data 450 (Figure 4). In some embodiments, the camera data is received via a wired connection. In some embodiments, the camera data is received wirelessly.

[0047] In operation 510, DFOS data is received. The DFOS data includes data indicating the position of a vehicle along the road at different times. In some embodiments, the DFOS data is acquired using a DAS system 100 (Figure 1). In some embodiments, the DFOS data is acquired using a system different from the DAS system 100 (Figure 1). In some embodiments, the DFOS data includes DFOS data 205 (Figure 2), DFOS data 305 (Figure 3), or DFOS data 405 (Figure 4). In some embodiments, the DFOS data is received via a wired connection. In some embodiments, the DFOS data is received wirelessly.

[0048] In operation 515, a vehicle is detected using camera data. In some embodiments, the vehicle is detected using an object recognition algorithm applied to the camera data. In some embodiments, a bounding box is placed around the detected vehicle to help distinguish between identified vehicles.

[0049] In operation 520, parameters for each vehicle are estimated. In some embodiments, the parameters include at least one of the following: the vehicle's position along the road, the vehicle's type, the vehicle's lane of travel, or vehicle identification information. In some embodiments, the vehicle's position along the road is determined based on a measured distance between the detected vehicle and a known landmark along the road, such as a sign. In some embodiments, the vehicle's type is determined based on the number of axles of the detected vehicle. In some embodiments, the vehicle's lane of travel is determined based on a measured distance between the vehicle and the edge of the road, or based on the identification of lane markings along the road. In some embodiments, vehicle identification information is determined based on the acquisition of vehicle identification information, such as a license plate or RFID tag.

[0050] In operation 525, a vehicle reliability score is calculated based on camera data. The vehicle reliability score indicates the reliability level of the accuracy of the vehicle parameters estimated in operation 520. The reliability score is affected by environmental conditions such as rain or fog, as well as the distance between the traffic camera and the detected vehicle. In some embodiments, the size of the vehicle also affects the reliability score, with larger vehicles having a higher reliability score. In some embodiments, the size of the vehicle is determined based on the size of the bounding box around the vehicle or the number of axles of the vehicle.

[0051] In operation 530, the camera capture range is determined. The camera capture range represents the area of ​​the received DFOS data that overlaps with the field of view of the traffic camera. In some embodiments, the camera capture range is determined based on input from the operator. In some embodiments, the camera capture range is determined based on previous traffic monitoring iterations.

[0052] In operation 535, the DFOS data is calibrated based on the camera acquisition range. The DFOS data is calibrated by adjusting the determined boundary of the camera acquisition range with the distance from the DAS used to acquire the DFOS data.

[0053] In operation 540, a reliable matching location is identified based on the correlation between the processed camera data and the DFOS data. The processed camera data includes estimated vehicle parameters from operation 520. In some embodiments, the processed camera data further includes a vehicle reliability score. Reliable location matching is performed for specific distances and times in the DFOS data by correlating the vehicle detected in the camera data with vibration sources from the DFOS data. Based on the identified matching location, the trajectory from the DFOS data passing through the matching location is assigned to the corresponding detected vehicle from the camera data. In some embodiments, details for identifying a reliable matching location are described above with respect to diagram 200 (Figure 2), diagram 300 (Figure 3), or diagram 400 (Figure 4).

[0054] In operation 545, DFOS data is used to continue tracking the vehicle's trajectory both within and outside the camera's capture range. Within the camera's capture range, the DFOS data can be corroborated by the camera data. Outside the camera's capture range, the DFOS data provides information about the vehicle's movement that cannot be determined by the camera data.

[0055] In operation 550, traffic monitoring is performed. Traffic monitoring is performed both within and outside the camera's capture range. Traffic monitoring includes identifying traffic anomalies such as accidents or congestion based on vibrations detected in the DFOS data. Because the positional information of the DFOS data is calibrated based on the camera data, the location of traffic anomalies can be accurately determined using the DFOS data. Traffic monitoring can be used to identify local authorities for traffic anomalies such as traffic accidents in order to facilitate the dispatch of emergency services. Traffic monitoring is also useful for planning future road developments, such as the installation of traffic signals or adjustment of road widths. By performing traffic monitoring using DFOS data, information that is completely unavailable in systems that rely solely on camera data becomes available. In addition, because DFOS data can capture information about traffic anomalies before traffic congestion returns to points within the camera's capture range, DFOS data can provide faster traffic monitoring outside the camera's capture range.

[0056] Those skilled in the art will recognize that modifications to Method 500 are within the scope of this description. In some embodiments, at least one further operation is included in Method 500. For example, in some embodiments, this includes determining a distance threshold or a time threshold for identifying trajectories in DFOS data. In some embodiments, at least one operation of Method 500 is omitted. For example, in some embodiments, operation 525 is omitted from Method 500. In some embodiments, the order of operations within Method 500 is adjusted. For example, in some embodiments, operation 525 is performed before operation 520 to avoid processing time and load when attempting to estimate vehicle parameters in situations where camera visibility is severely affected by environmental conditions.

[0057] Figure 6 is a flowchart of Method 600 for utilizing camera data and DFOS data in several embodiments. Method 600 can be used for utilizing camera data and DFOS data for traffic monitoring. In some embodiments, Method 600 can be used to perform the functions described with respect to Diagram 200 (Figure 2), Diagram 300 (Figure 3), or Diagram 400 (Figure 4). In some embodiments, Method 600 can be used to perform functions other than those described above. In some embodiments, Method 600 is implemented using DAS System 100 (Figure 1) or System 700 (Figure 7). In some embodiments, Method 600 is implemented using a system other than DAS System 100 (Figure 1) or System 700 (Figure 7). Some operations of Method 600 are similar to those of Method 500 (Figure 5), and these operations are not described in detail for brevity.

[0058] In operation 605, camera data is received. In some embodiments, operation 605 is the same as operation 505 (Figure 5).

[0059] In operation 610, DFOS data is received. In some embodiments, operation 610 is the same as operation 510 (Figure 5).

[0060] In operation 615, the vehicle is detected using camera data. In some embodiments, operation 615 is the same as operation 515 (Figure 5).

[0061] In operation 620, the traffic situation is classified. The traffic situation is classified based on the likelihood that the DFOS data can consistently track the vehicle across the entire camera capture range. The traffic situation is classified as complex if the likelihood that the DFOS data can consistently track the vehicle across the entire camera capture range is low. The traffic situation is classified as simple if the likelihood that the DFOS data can consistently track the vehicle across the entire camera capture range is high. In some embodiments, the determination that the likelihood that the DFOS data can consistently track the vehicle across the entire camera capture range is low is made in response to identifying a vehicle changing lanes, a vehicle overtaking another vehicle, or a high density of vehicles within the camera capture range.

[0062] In operation 625, the parameters of each vehicle are estimated. In some embodiments, operation 625 is the same as operation 520 (Figure 5).

[0063] In operation 630, a vehicle reliability score is calculated based on camera data. In some embodiments, operation 630 is similar to operation 525 (Figure 5).

[0064] In operation 635, the camera capture range is determined. In some embodiments, operation 635 is the same as operation 530 (Figure 5).

[0065] In operation 640, the DFOS data is calibrated based on the camera capture range. In some embodiments, operation 640 is the same as operation 535 (Figure 5).

[0066] In operation 645, the vehicle matching position is determined. In response to operation 620, which classifies the traffic situation as simple, operation 645 is the same as operation 540 (Figure 5). In response to operation 620, which classifies the traffic situation as complex, the vehicle matching position is set to a position in the DFOS data where the vehicles can be identified separately at a point after the DFOS data could not reliably identify separate vehicles. In some embodiments, vehicle position matching for complex traffic situations is the same as the method described above with respect to diagram 400 (Figure 4).

[0067] In operation 650, DFOS data is used to continue tracking the vehicle's trajectory both within and outside the camera's capture range. In some embodiments, operation 650 is similar to operation 545 (Figure 5).

[0068] In operation 655, traffic monitoring is performed. In some embodiments, operation 655 is the same as operation 550 (Figure 5).

[0069] Those skilled in the art will recognize that modifications to Method 600 are within the scope of this description. In some embodiments, at least one further operation is included in Method 600. For example, in some embodiments, this includes determining a distance threshold or a time threshold for identifying trajectories in DFOS data. In some embodiments, at least one operation of Method 600 is omitted. For example, in some embodiments, operation 630 is omitted from Method 600. In some embodiments, the order of operations within Method 600 is adjusted. For example, in some embodiments, operation 630 is performed before operation 625 to avoid processing time and load when attempting to estimate vehicle parameters in situations where camera visibility is severely affected by environmental conditions.

[0070] Figure 7 is a block diagram of a system 700 for utilizing camera data and DFOS data according to several embodiments. The system 700 includes a hardware processor 702 and a non-temporary computer-readable storage medium 704 that stores computer program code 706, i.e., a set of executable instructions. The computer-readable storage medium 704 is also encoded with instructions 707 for interfacing with external devices. The processor 702 is electrically coupled to the computer-readable storage medium 704 via a bus 708. The processor 702 is also electrically coupled to an input / output (I / O) interface 710 via the bus 708. A network interface 712 is also electrically connected to the processor 702 via the bus 708. The network interface 712 is connected to a network 714, and as a result, the processor 702 and the computer-readable storage medium 704 can connect to external elements via the network 714. The processor 702 is configured to execute computer program code 706 encoded in a computer-readable storage medium 704 in order to make the system 700 available to perform some or all of the operations described with respect to the DAS system 100 (Figure 1), method 500 (Figure 5), or method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data.

[0071] In some embodiments, the processor 702 is a central processing unit (CPU), a multiprocessor, a distributed processing system, an application-specific integrated circuit (ASIC), and / or a suitable processing unit.

[0072] In some embodiments, the computer-readable storage medium 704 is an electronic, magnetic, optical, electromagnetic, infrared, and / or semiconductor system (or apparatus or device). For example, the computer-readable storage medium 704 includes semiconductor memory or solid-state memory, magnetic tape, removable computer diskette, random access memory (RAM), read-only memory (ROM), rigid magnetic disk, and / or optical disk. In some embodiments using optical disks, the computer-readable storage medium 704 includes compact disc read-only memory (CD-ROM), compact disc read / write (CD-R / W), and / or digital video disc (DVD).

[0073] In some embodiments, the storage medium 704 stores computer program code 706 configured to cause system 700 to perform some or all of the operations described with respect to DAS system 100 (Figure 1), method 500 (Figure 5), or method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data. In some embodiments, the storage medium 704 also stores information used to perform some or all of the operations described with respect to the DAS system 100 (Figure 1), method 500 (Figure 5), or method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data, as well as information generated while performing some or all of the operations described with respect to the DAS system 100 (Figure 1), method 500 (Figure 5), or method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data, such as DFOS data parameter 716, camera data parameter 718, reliability score parameter 720, vehicle parameter 722, traffic condition parameter 724, and / or a set of instructions that can be executed to perform some or all of the operations described with respect to the DAS system 100 (Figure 1), method 500 (Figure 5), or method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data.

[0074] In some embodiments, the storage medium 704 stores instructions 707 for interfacing with an external device. The instructions 707 enable the processor 702 to generate instructions readable by an external device in order to effectively perform some or all of the operations described with respect to the DAS system 100 (Figure 1), method 500 (Figure 5), or method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data.

[0075] The system 700 includes an I / O interface 710. The I / O interface 710 is coupled to external circuitry. In some embodiments, the I / O interface 710 includes a keyboard, keypad, mouse, trackball, trackpad, and / or cursor directional keys for communicating information and commands to the processor 702.

[0076] System 700 also includes a network interface 712 coupled to processor 702. The network interface 712 enables System 700 to communicate with a network 714 to which one or more other computer systems are connected. The network interface 712 includes wireless network interfaces such as BLUETOOTH®, Wi-Fi®, WiMAX, GPRS, or WCDMA®, or wired network interfaces such as ETHERNET, USB, or IEEE-1394. In some embodiments, some or all of the operations described with respect to DAS system 100 (Figure 1), method 500 (Figure 5), or method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data are performed in two or more systems 700, and information such as DFOS data, camera data, reliability scores, vehicle parameters, and traffic conditions are exchanged between different systems 700 via the network 714.

[0077] In some embodiments, the external device uses data from a DAS, e.g., DAS100 (Figure 1), to determine at least one monitored traffic characteristic within a city or town area. In some embodiments, the external device uses at least one traffic characteristic to determine, for example, whether a vehicle traveling along a road exceeds the road's weight limit, based on the width and amplitude of vibration lines caused by a vehicle crossing the road. In some embodiments, the external device uses at least one traffic characteristic to develop a navigation plan for a GPS device. In some embodiments, the external device uses at least one traffic characteristic to assist in route setting for emergency vehicles, for example, by generating a navigation plan and / or by detecting large vibration amplitudes to specifically identify the location of a vehicle accident. In some embodiments, the external device uses at least one traffic pattern to detect landslides based on very high vibration amplitudes and / or damage to optical fibers.

[0078] Compared to other methods, System 700, used to implement some or all of the operations described for DAS System 100 (Figure 1), Method 500 (Figure 5), or Method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data, can improve the accuracy of determining traffic anomalies outside the camera capture range. Wireless communication is avoided by using optical fiber as a measuring instrument instead of a visual monitoring device. In some cases, wireless communication can be interrupted or interfere with other wireless communication devices. Wireless communication also introduces more noise into the transmitted signal than a wired connection provided by optical fiber. In addition, System 700 can be connected to optical fiber already installed along the road. This minimizes the amount of infrastructure used to install System 700 and / or to implement some or all of the operations described for DAS System 100 (Figure 1), Method 500 (Figure 5), or Method 600 (Figure 6), or another suitable system for utilizing camera data and DFOS data.

[0079] (Note 1) The traffic monitoring system includes a distributed acoustic sensor (DAS) connected to an optical fiber and configured to generate distributed optical fiber sensing (DFOS) data. The traffic monitoring system further includes a traffic monitoring device configured to receive the DFOS data, receive camera data captured by a camera having a camera capture range, calibrate the DFOS data using the camera data, and monitor traffic outside the camera capture range using the calibrated DFOS data.

[0080] (Note 2) The traffic monitoring system according to Appendix 1, wherein the traffic monitoring device is configured to calibrate the DFOS data based on matching the position of a first vehicle trajectory in the DFOS data with a first detected vehicle in the camera data.

[0081] (Note 3) The traffic monitoring system according to Appendix 1 or 2, wherein the traffic monitoring device is configured to match the position of the first vehicle trajectory with the first detected vehicle based on the trajectory features of the DFOS and the determined vehicle type of the first detected vehicle, and the trajectory features of the DFOS include at least one of the intensity, thickness, or spread of vibrations indicated by the first vehicle trajectory in the DFOS data.

[0082] (Note 4) The traffic monitoring system according to any one of appendices 1 to 3, wherein the traffic monitoring device is configured to match the position of the first vehicle trajectory with the first detected vehicle in response to the first vehicle trajectory being separated from all other vehicle trajectories in the DFOS data by at least one of a time threshold or a distance threshold.

[0083] (Note 5) The traffic monitoring system according to any one of the appendices 1 to 4, wherein the traffic monitoring device is configured to determine whether the first vehicle trajectory is within the time threshold and distance threshold of at least one other vehicle trajectory in the DFOS data in a first time, and in response to the first vehicle trajectory being within the time threshold and distance threshold of the at least one other vehicle trajectory in a first time, to match the position of the first vehicle trajectory with the first detected vehicle based on the DFOS data and camera data in a second time after the first time.

[0084] (Note 6) The traffic monitoring system according to any one of appendices 1 to 5, wherein the traffic monitoring device is configured to match the position of the first vehicle trajectory with the first detected vehicle based on the gradient of the first vehicle trajectory in a third time prior to the first time, in response that the first vehicle trajectory is within the time threshold and distance threshold of the at least one other vehicle trajectory in the first time.

[0085] (Note 7) The traffic monitoring system according to any one of the appendices 1 to 6, wherein the traffic monitoring device is configured to determine the vehicle types of a first vehicle and a second vehicle based on the camera data, and to correlate the first vehicle trajectory of the DFOS data with the first vehicle and the second vehicle trajectory of the DFOS data with the second vehicle based on the determined vehicle type of the first vehicle and the second vehicle.

[0086] (Note 8) A traffic monitoring method includes receiving distributed fiber optic sensing (DFOS) data acquired by a distributed acoustic sensor (DAS) connected to an optical fiber. The traffic monitoring method further includes receiving camera data acquired by a camera having a camera acquisition range. The traffic monitoring method further includes calibrating the DFOS data using the camera data. The traffic monitoring method further includes monitoring traffic outside the camera acquisition range using the calibrated DFOS data.

[0087] (Note 9) The traffic monitoring method according to Appendix 8, wherein calibrating the DFOS data includes matching the position of the first vehicle trajectory in the DFOS data with the first detected vehicle in the camera data.

[0088] (Note 10) The traffic monitoring method according to Appendix 8 or 9, wherein matching the position of the first vehicle trajectory with the first detected vehicle includes matching the position of the first vehicle trajectory with the first detected vehicle based on the trajectory features of the DFOS and the determined vehicle type of the first detected vehicle, the trajectory features of the DFOS include at least one of the intensity, thickness, or spread of vibrations indicated by the first vehicle trajectory in the DFOS data.

[0089] (Note 11) A traffic monitoring method according to any one of appendices 8 to 10, wherein the position of the first vehicle trajectory is matched with the first detected vehicle in response to the first vehicle trajectory being separated from all other vehicle trajectories in the DFOS data by at least one of a time threshold or a distance threshold.

[0090] (Note 12) A traffic monitoring method according to any one of appendices 8 to 11, further comprising: determining whether the first vehicle trajectory falls within the time threshold and distance threshold of at least one other vehicle trajectory in the DFOS data in a first time; and, in response to the first vehicle trajectory falling within the time threshold and distance threshold of the at least one other vehicle trajectory in a first time, matching the position of the first vehicle trajectory with the first detected vehicle based on the DFOS data and camera data in a second time after the first time.

[0091] (Note 13) A traffic monitoring method according to any one of appendices 8 to 12, wherein matching the position of the first vehicle trajectory with the first detected vehicle includes matching the position of the first vehicle trajectory with the first detected vehicle based on the gradient of the first vehicle trajectory in a third time prior to the first time, in response that the first vehicle trajectory is within the time threshold and distance threshold of the at least one other vehicle trajectory in the first time.

[0092] (Note 14) A traffic monitoring method according to any one of appendices 8 to 13, further comprising determining the vehicle types of a first vehicle and a second vehicle based on the camera data, and correlating the first vehicle trajectory of the DFOS data with the first vehicle and the second vehicle trajectory of the DFOS data with the second vehicle based on the determined vehicle type of each of the first vehicle and the second vehicle.

[0093] (Note 15) The program causes the computer to perform the following actions: receive distributed fiber optic sensing (DFOS) data acquired by a distributed acoustic sensor (DAS) connected to an optical fiber; receive camera data acquired by a camera having a camera acquisition range; calibrate the DFOS data using the camera data; and monitor traffic outside the camera acquisition range using the calibrated DFOS data.

[0094] (Note 16) The program described in Appendix 15, which causes the computer to perform calibration of the DFOS data, which includes matching the position of a first vehicle trajectory in the DFOS data with the first detected vehicle in the camera data.

[0095] (Note 17) Matching the position of the first vehicle trajectory with the first detected vehicle includes matching the position of the first vehicle trajectory with the first detected vehicle based on the trajectory features of the DFOS and the determined vehicle type of the first detected vehicle, wherein the trajectory features of the DFOS include at least one of the intensity, thickness, or spread of vibrations indicated by the first vehicle trajectory in the DFOS data, according to the program in Appendix 15 or 16.

[0096] (Note 18) A program according to any one of appendices 15 to 17, which causes the computer to match the position of the first vehicle trajectory with the first detected vehicle in response to the first vehicle trajectory being separated from all other vehicle trajectories in the DFOS data by at least one of a time threshold or a distance threshold.

[0097] (Note 19) A program according to any one of appendices 15 to 18, which causes the computer to perform the following actions: determine whether the first vehicle trajectory is within the time threshold and distance threshold of at least one other vehicle trajectory in the DFOS data in a first time; and, in response to the first vehicle trajectory being within the time threshold and distance threshold of at least one other vehicle trajectory in a first time, match the position of the first vehicle trajectory with the first detected vehicle based on the DFOS data and camera data in a second time after the first time.

[0098] (Note 20) A program according to any one of the appendices 15 to 19, which causes the computer to perform the following actions: determine the vehicle types of the first vehicle and the second vehicle based on the camera data; and correlate the first vehicle trajectory of the DFOS data to the first vehicle and the second vehicle trajectory of the DFOS data to the second vehicle based on the determined vehicle type of the first vehicle and the second vehicle.

[0099] The above outlines some features of embodiments so that those skilled in the art may better understand aspects of the disclosure. Those skilled in the art should understand that the disclosure can be readily used as a basis for designing or modifying other processes and structures to accomplish the same objectives and / or achieve the same advantages of the embodiments described herein. Those skilled in the art should also understand that such equivalent structures will not depart from the spirit and scope of the disclosure, and that they may be modified, replaced, and altered in various ways herein without departing from the spirit and scope of the disclosure.

[0100] This application claims priority based on U.S. Patent Application No. 19 / 002559, filed on 26 December 2024, and incorporates all of its disclosures herein. [Explanation of Symbols]

[0101] 100 Dispersive Acoustic Sensor (DAS) Systems 111 Traffic monitoring equipment 112 Dispersive Acoustic Sensor (DAS) 121 Optical Fiber 130 Road 140 vehicles 150 traffic cameras 150a First traffic camera 150b Second traffic camera 200 diagrams 205 Distributed Fiber Optic Sensing (DFOS) Data 210 The First Trajectory 215 First vehicle 220 The Second Trajectory 225 Second vehicle 230 The first boundary 240 The Second Boundary 250 Camera Data 300 diagrams 305 DFOS data 310 Camera capture range 320 The First Trajectory 325 First vehicle 330 The Second Trajectory 335 Second vehicle 350 Camera Data 350a First camera data 350b Second camera data 360 The Third Trajectory 365 Third vehicle 370 The Fourth Trajectory 375 The fourth vehicle 380 The Fifth Trajectory 385 Fifth vehicle 400 diagrams 405 DFOS data 410 Camera capture range 420 The First Trajectory 425 First vehicle 430 The Second Trajectory 435 Second vehicle 450 Camera Data 450a First camera data 450b Second camera data 460 The Third Trajectory 465 Third vehicle 470 The Fourth Trajectory 475 The fourth vehicle 480 The Fifth Trajectory 485 Fifth vehicle 490 First position 495 Second position 500, 600 ways 505, 510, 515, 520, 525, 530, 535, 540, 545, 550, 605, 610, 615, 620, 625, 630, 635, 640, 645, 650, 655 operation 700 System 702 Hardware Processors 704 Non-temporary computer-readable storage medium 706 Computer program code 707 Command 708 Bus 710 Input / Output (I / O) Interfaces 712 Network Interfaces 714 Network 716 DFOS data parameters 718 Camera Data Parameters 720 Reliability Score Parameters 722 Vehicle Parameters 724 Traffic Conditions Parameters

Claims

1. A distributed acoustic sensor (DAS) connected to an optical fiber and configured to generate distributed optical fiber sensing (DFOS) data, Receiving the aforementioned DFOS data, Receiving camera data captured by a camera with a camera capture range, Calibrating the DFOS data using the aforementioned camera data, Using the calibrated DFOS data, the system monitors traffic outside the camera's capture range. A traffic monitoring device configured to perform the following: A traffic monitoring system equipped with the following features.

2. The traffic monitoring system according to claim 1, wherein the traffic monitoring device is configured to calibrate the DFOS data based on matching the position of a first vehicle trajectory in the DFOS data with a first detected vehicle in the camera data.

3. The traffic monitoring system according to claim 2, wherein the traffic monitoring device is configured to match the position of the first vehicle trajectory with the first detected vehicle based on the trajectory features of the DFOS and the determined vehicle type of the first detected vehicle, and the trajectory features of the DFOS include at least one of the intensity, thickness, or spread of vibrations indicated by the first vehicle trajectory in the DFOS data.

4. The traffic monitoring system according to claim 2, wherein the traffic monitoring device is configured to match the position of the first vehicle trajectory with the first detected vehicle in response to the first vehicle trajectory being separated from all other vehicle trajectories in the DFOS data by at least one of a time threshold or a distance threshold.

5. The aforementioned traffic monitoring device, Determine whether the first vehicle trajectory falls within the time threshold and distance threshold of at least one other vehicle trajectory in the DFOS data at the first time. In response that the first vehicle trajectory falls within the time threshold and distance threshold of at least one other vehicle trajectory at the first time, the position of the first vehicle trajectory is matched with the first detected vehicle based on the DFOS data and camera data at a second time after the first time. The traffic monitoring system according to claim 4, configured as described above.

6. The traffic monitoring system according to claim 5, wherein the traffic monitoring device is configured to match the position of the first vehicle trajectory with the first detected vehicle based on the gradient of the first vehicle trajectory in a third time prior to the first time, in response that the first vehicle trajectory is within the time threshold and distance threshold of the at least one other vehicle trajectory in the first time.

7. The aforementioned traffic monitoring device, Based on the aforementioned camera data, the vehicle types of the first and second vehicles are determined. Based on the determined vehicle type of the first vehicle and the second vehicle, the first vehicle trajectory of the DFOS data is correlated to the first vehicle, and the second vehicle trajectory of the DFOS data is correlated to the second vehicle. The traffic monitoring system according to claim 1, configured as follows.

8. Receiving distributed optical fiber sensing (DFOS) data captured by a distributed acoustic sensor (DAS) connected to an optical fiber, Receiving camera data captured by a camera with a camera capture range, Calibrating the DFOS data using the aforementioned camera data, Using the calibrated DFOS data, the system monitors traffic outside the camera's capture range. Traffic monitoring methods, including those mentioned above.

9. The traffic monitoring method according to claim 8, wherein calibrating the DFOS data includes matching the position of the first vehicle trajectory in the DFOS data with the first detected vehicle in the camera data.

10. Receiving distributed optical fiber sensing (DFOS) data captured by a distributed acoustic sensor (DAS) connected to an optical fiber, Receiving camera data captured by a camera with a camera capture range, Calibrating the DFOS data using the aforementioned camera data, Using the calibrated DFOS data, the system monitors traffic outside the camera's capture range. A program that causes a computer to execute something.

Images