Traffic flow counting method and device based on vibration signal, equipment and storage medium

Abstract

The application provides a kind of traffic flow statistics method, device and equipment based on vibration signal and storage medium, belong to traffic flow statistics technical field, its method includes: obtaining the space-time vibration response graph of section area;The space-time vibration response graph includes multiple initial vehicle driving tracks;Determine at least two selected driving tracks in the multiple initial vehicle driving tracks meet signal attenuation law and at least one first target driving track does not meet signal attenuation law, and determine the second target driving track in the at least two selected driving tracks maximum waveform amplitude;Trajectory straight line extraction is carried out to the first target driving track and the second target driving track, and a plurality of extraction trajectories are obtained;Each extraction trajectory is taken as a vehicle object, and the traffic flow of the section area is determined based on the vehicle object.The application avoids the case that one vehicle corresponds to multiple trajectories, and improves the accuracy of the statistical traffic flow.

Description

Technical Field

[0001] This invention relates to the field of traffic flow statistics technology, specifically to a method, apparatus, equipment, and storage medium for traffic flow statistics based on vibration signals. Background Technology

[0002] Highways have high speeds and dense traffic, making accidents there particularly dangerous and often resulting in severe consequences. Therefore, ensuring traffic safety is the primary task of highway operations. Accurate traffic flow monitoring is crucial for the timely detection of traffic congestion, potential accidents, and other anomalies. Through effective traffic flow monitoring, traffic control and diversion measures can be implemented in advance, reducing the risk of accidents and improving road safety. Furthermore, understanding and optimizing traffic flow distribution, and rationally allocating road resources, can reduce vehicle delays on highways, improve transportation efficiency, and lower transportation costs, which is of great significance for promoting economic development.

[0003] Currently, mainstream traffic flow detection methods include video detection and LiDAR. However, video detection is prone to significant errors in complex traffic environments, such as severe weather or dense traffic. LiDAR, on the other hand, is expensive; the economic cost of achieving real-time, all-area, and all-weather traffic flow statistics makes large-scale implementation impossible. Grating array vibration sensing technology has developed rapidly in recent years. Compared to traditional electrical sensors, it features small size, resistance to electromagnetic interference, high temperature resistance, high precision, low cost, and the ability to perceive vibration signals "all-time, all-area, and all-weather," making it ideal for long-distance moving object detection. It is currently widely used in aerospace, smart ships, intelligent security, and smart transportation. By laying vibration optical cables underground, long-distance vibration object identification can be achieved, making it highly adaptable to real-time, all-area traffic flow detection applications. However, the following technical problems exist when using grating array vibration sensing technology to detect traffic flow: the vibration signal will propagate in the medium, that is: when a vehicle is detected based on a certain measuring point, other measuring points will form false trajectories due to the propagation of vehicle vibration, resulting in inaccurate traffic flow statistics.

[0004] Therefore, there is an urgent need to provide a method, device, equipment, and storage medium for traffic flow statistics based on vibration signals, so as to eliminate the adverse effects of false trajectories on traffic flow results and improve the accuracy of traffic flow statistics for cross-sectional areas. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, apparatus, device and storage medium for traffic flow statistics based on vibration signals, so as to solve the technical problem that the existing technology does not consider the propagation characteristics of vibration signals, resulting in inaccurate traffic flow statistics results.

[0006] On the one hand, in order to solve the above-mentioned technical problems, the present invention provides a traffic flow statistics method based on vibration signals, including:

[0007] Obtain the spatiotemporal vibration response map of the cross-sectional area; the spatiotemporal vibration response map includes multiple initial vehicle travel trajectories;

[0008] Determine at least two candidate driving trajectories that conform to the signal attenuation law and at least one first target driving trajectory that does not conform to the signal attenuation law from the multiple initial vehicle driving trajectories, and determine the second target driving trajectory with the largest waveform amplitude among the at least two candidate driving trajectories;

[0009] Straight lines are extracted from the driving trajectories of the first and second targets to obtain multiple extracted trajectories;

[0010] Each extracted trajectory is used as a vehicle object, and the traffic flow in the cross-sectional area is determined based on the vehicle object.

[0011] In one possible implementation, obtaining the spatiotemporal vibration response map of the cross-sectional region includes:

[0012] Acquire full-area vehicle vibration signals based on grating array vibration sensing optical cables;

[0013] The target vehicle vibration signal in the global vehicle vibration signal is determined based on the cross-sectional area; the target vehicle vibration signal includes multiple target vehicle vibration sub-signal sequences corresponding to each measuring point of the grating array vibration sensing optical cable, and the target vehicle vibration sub-signal sequence includes multiple target vehicle vibration sub-signals corresponding to multiple acquisition time points;

[0014] The vibration signals of the target vehicle are sorted by the spatial location of the measuring points as rows and time as columns to obtain the spatiotemporal vibration response map.

[0015] In one possible implementation, the signal attenuation law is as follows:

[0016]

[0017] In the formula, The average amplitude of the first candidate driving trajectory; The distance between the first and second candidate driving trajectories; The distance to the first candidate driving trajectory is The average amplitude of the second candidate driving trajectory; The attenuation coefficient; It is the natural logarithm.

[0018] In one possible implementation, after obtaining the spatiotemporal vibration response map of the cross-sectional region, the method further includes:

[0019] Obtain a fully trained image enhancement model, which includes a generator and a discriminator. The generator includes a feature extraction unit, a feature attention learning unit, and an enhancement unit.

[0020] Based on the feature extraction unit, feature extraction is performed on the spatiotemporal vibration response map to obtain initial image features;

[0021] Based on the feature attention learning unit, channel attention learning and spatial attention learning are sequentially performed on the initial image features to obtain image attention features;

[0022] Based on the enhancement unit, feature reconstruction is performed on the image attention features to obtain an enhanced spatiotemporal vibration response map.

[0023] In one possible implementation, the feature attention learning unit includes a spatial attention learning layer and a channel attention learning layer; the step of sequentially performing channel attention learning and spatial attention learning on the initial image features based on the feature attention learning unit to obtain image attention features includes:

[0024] Based on the channel attention learning layer, channel feature learning is performed on the initial image features to obtain channel attention features;

[0025] The channel attention features are multiplied by the initial image features to obtain the channel image features;

[0026] Spatial attention features are obtained by performing spatial feature learning on the channel image features based on the spatial attention learning layer.

[0027] The spatial attention features are multiplied by the channel image features to obtain the image attention features.

[0028] In one possible implementation, the plurality of extracted trajectories includes a first extracted trajectory at the current moment and a second extracted trajectory at a historical moment; then, before treating each of the extracted trajectories as a vehicle object, the method further includes:

[0029] Obtain the first trajectory features of the first extracted trajectory and the second trajectory features of the second extracted trajectory;

[0030] Based on the first trajectory features and the second trajectory features, determine the feature loss values ​​of the first extracted trajectory and the second extracted trajectory;

[0031] When the feature loss value is less than the loss threshold, the first extracted trajectory and the second extracted trajectory are merged to obtain a merged trajectory;

[0032] The step of treating each extracted trajectory as a vehicle object specifically means:

[0033] The merged trajectory is used as the vehicle object.

[0034] In one possible implementation, both the first trajectory feature and the second trajectory feature include speed, energy, lane, and position; determining the feature loss values ​​of the first extracted trajectory and the second extracted trajectory based on the first trajectory feature and the second trajectory feature includes:

[0035] Determine the speed loss value, energy loss value, lane loss value, and position loss value of the first extracted trajectory and the second extracted trajectory;

[0036] The speed loss value, energy loss value, lane loss value, and position loss value are weighted according to preset weights to obtain the feature loss value.

[0037] On the other hand, the present invention also provides a traffic flow statistics device based on vibration signals, comprising:

[0038] The spatiotemporal vibration response map acquisition unit is used to acquire the spatiotemporal vibration response map of the cross-sectional area; the spatiotemporal vibration response map includes multiple initial vehicle travel trajectories.

[0039] The driving trajectory determination unit is used to determine at least two candidate driving trajectories that conform to the signal attenuation law and at least one first target driving trajectory that does not conform to the signal attenuation law from the plurality of initial vehicle driving trajectories; and to determine the second target driving trajectory with the largest waveform amplitude among the at least two candidate driving trajectories;

[0040] The trajectory straight line extraction unit is used to extract straight lines from the first target driving trajectory and the second target driving trajectory to obtain multiple extracted trajectories;

[0041] The traffic flow determination unit is used to treat each extracted trajectory as a vehicle object and determine the traffic flow of the cross-sectional area based on the vehicle object.

[0042] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein,

[0043] The memory is used to store programs;

[0044] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the vibration signal-based traffic flow statistics method described in any of the above possible implementations.

[0045] On the other hand, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the vibration signal-based traffic flow statistics method described in any of the above possible implementations.

[0046] The beneficial effects of this invention are as follows: The traffic flow statistics method based on vibration signals provided by this invention judges multiple initial vehicle trajectories in the spatiotemporal vibration response map based on the signal attenuation law, and obtains at least two candidate trajectories that conform to the signal attenuation law. It utilizes the characteristic that the energy of vibration signals attenuates due to scattering and absorption during propagation in a medium, avoiding the situation where one vehicle corresponds to multiple trajectories, thus improving the accuracy of the determined second target trajectory and consequently improving the accuracy of the traffic flow statistics. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a schematic flowchart of an embodiment of the traffic flow statistics method based on vibration signals provided by the present invention;

[0049] Figure 2 This is a comparison of trajectory clarity before and after straight line extraction in this invention;

[0050] Figure 3 This is a schematic flowchart of an embodiment of step S101 of the present invention;

[0051] Figure 4 This is a schematic flowchart of an embodiment of the present invention for enhancing spatiotemporal vibration response maps;

[0052] Figure 5 A schematic diagram of an embodiment of the image enhancement model provided by the present invention;

[0053] Figure 6 A schematic diagram of the structure of an embodiment of the feature attention learning unit provided by the present invention;

[0054] Figure 7This is a schematic diagram of an embodiment of the present invention for matching and merging extracted trajectories;

[0055] Figure 8 This is a flowchart of an embodiment of step S702 of the present invention;

[0056] Figure 9 A schematic diagram of an embodiment of the traffic flow statistics device based on vibration signals provided by the present invention;

[0057] Figure 10 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0059] It should be understood that the illustrative drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the invention. It should be understood that the operations in the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed or performed simultaneously. Furthermore, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0060] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0061] This invention provides a method, apparatus, device, and storage medium for traffic flow statistics based on vibration signals, which will be described below.

[0062] Figure 1This is a schematic flowchart of an embodiment of the traffic flow statistics method based on vibration signals provided by the present invention, as shown below. Figure 1 As shown, the traffic flow statistics method based on vibration signals includes:

[0063] S101. Obtain the spatiotemporal vibration response map of the cross-sectional area; the spatiotemporal vibration response map includes multiple initial vehicle travel trajectories.

[0064] S102. Determine at least two candidate driving trajectories that conform to the signal attenuation law and at least one first target driving trajectory that does not conform to the signal attenuation law from multiple initial vehicle driving trajectories, and determine the second target driving trajectory with the largest waveform amplitude among the at least two candidate driving trajectories.

[0065] S103. Extract straight lines from the driving trajectories of the first and second targets to obtain multiple extracted trajectories;

[0066] S104. Treat each extracted trajectory as a vehicle object, and determine the traffic flow of the cross-sectional area based on the vehicle object.

[0067] In step S101, the method for obtaining the spatiotemporal vibration response map of the cross-sectional area can be as follows: obtain the spatiotemporal vibration response map of the entire area, and then crop the spatiotemporal vibration response map of the entire area based on the cross-sectional area to obtain the spatiotemporal vibration response map of the cross-sectional area. Alternatively, it can be as follows: directly obtain the spatiotemporal vibration response map of the cross-sectional area.

[0068] It should be understood that in step S102, the at least two candidate driving trajectories that conform to the signal attenuation law are multiple trajectories caused by a single vehicle. These multiple trajectories include one true trajectory and at least one false trajectory generated due to vibration propagation characteristics. The trajectory with the largest waveform amplitude is the true trajectory. Therefore, only the second target driving trajectory with the largest waveform amplitude among the at least two candidate driving trajectories is retained, and the other candidate driving trajectories are eliminated.

[0069] The trajectory line extraction method in step S103 can be probabilistic Hough extraction.

[0070] Since vehicles typically travel at a stable, constant speed or accelerate during operation, their trajectories are clearly defined curves with stable and continuous characteristics. Therefore, straight-line detection methods are well-suited for trajectory extraction.

[0071] By extracting straight lines from the travel trajectories of the first and second targets, trajectory clarity can be improved. Specifically, for example... Figure 2 As shown, Figure 2 The left side shows the driving trajectory before straight line extraction, and the white line represents the driving trajectory before straight line extraction. Figure 2The right side shows the driving trajectory after straight-line extraction; the solid red line represents the extracted driving trajectory. Figure 2 It can be seen that extracting straight lines from the trajectory improves the clarity of the extracted trajectory.

[0072] Specifically, step S104 involves determining the total number of vehicles in the cross-sectional area within the statistical time period based on the vehicle objects. This total number is the traffic flow.

[0073] Compared with existing technologies, the traffic flow statistics method based on vibration signals provided in this invention determines at least two candidate trajectories that conform to the signal attenuation law by judging multiple initial vehicle trajectories in the spatiotemporal vibration response map based on the signal attenuation law. It utilizes the characteristic that the energy of vibration signals attenuates due to scattering and absorption during propagation in a medium, avoiding the situation where one vehicle corresponds to multiple trajectories, thus improving the accuracy of the determined second target trajectory and consequently improving the accuracy of the traffic flow statistics.

[0074] In specific embodiments of the present invention, such as Figure 3 As shown, step S101 includes:

[0075] S301. Acquire the full-domain vehicle vibration signal based on the grating array vibration sensing optical cable.

[0076] S302. Determine the target vehicle vibration signal in the whole-domain vehicle vibration signal based on the cross-sectional area; the target vehicle vibration signal includes multiple target vehicle vibration sub-signal sequences corresponding to each measuring point of the grating array vibration sensing optical cable, and the target vehicle vibration sub-signal sequence includes multiple target vehicle vibration sub-signals corresponding to multiple acquisition time points.

[0077] S303. Sort the vibration signals of the target vehicle by taking the spatial location of the measuring point as the row and time as the column to obtain the spatiotemporal vibration response diagram.

[0078] Specifically, the grating array vibration sensing optical cable is composed of a large number of vibration sensing gratings, with each vibration sensing grating serving as a measuring point.

[0079] In a specific embodiment of the present invention, the signal attenuation law is as follows:

[0080]

[0081] In the formula, The average amplitude of the first candidate driving trajectory; The distance between the first and second candidate driving trajectories; The distance to the first candidate driving trajectory is The average amplitude of the second candidate driving trajectory; The attenuation coefficient; It is the natural logarithm.

[0082] Due to the propagation and attenuation characteristics of vibration signals, the initial vehicle trajectory in the spatiotemporal vibration response map has discontinuities or fluctuations, meaning the image quality of the initial vehicle trajectory is poor. To improve the accuracy of traffic flow statistics, it is necessary to ensure the image quality of the spatiotemporal vibration response map. To achieve this, in some embodiments of the present invention, such as... Figure 4 and Figure 5 As shown, after step S101, the following steps are also included:

[0083] S401. Obtain a fully trained image enhancement model. The image enhancement model includes a generator and a discriminator. The generator includes a feature extraction unit, a feature attention learning unit, and an enhancement unit.

[0084] S402. Based on the feature extraction unit, feature extraction is performed on the spatiotemporal vibration response map to obtain initial image features;

[0085] S403. Based on the feature attention learning unit, channel attention learning and spatial attention learning are performed sequentially on the initial image features to obtain image attention features;

[0086] S404. Based on the enhancement unit, feature reconstruction is performed on the image attention features to obtain the enhanced spatiotemporal vibration response map.

[0087] The discriminator is only used in the training phase of the image enhancement model. The training objective of the image enhancement model is to train the generator and the discriminator alternately, so that the generator gradually learns to generate image data that is close to the real enhanced spatiotemporal vibration response map, and the discriminator cannot distinguish whether the image data generated by the generator is real data or image data generated by the generator.

[0088] The feature extraction unit can be an existing mature backbone network, such as ResNet and UNet. The enhancement unit consists of multiple convolutional layers and activation function layers.

[0089] This invention enhances the spatiotemporal vibration response map using an image enhancement model, thereby improving the clarity of the enhanced spatiotemporal vibration response map and thus improving the accuracy of traffic flow statistics using the enhanced spatiotemporal vibration response map.

[0090] Furthermore, in this embodiment of the invention, a feature attention learning unit is set up to perform channel attention learning and spatial attention learning on the initial image features in sequence, so as to more effectively represent the image features from both channel and spatial dimensions, and greatly improve the clarity of the enhanced spatiotemporal vibration response map.

[0091] In specific embodiments of the present invention, such as Figure 6As shown, the feature attention learning unit includes a spatial attention learning layer and a channel attention learning layer. Therefore, step S403 specifically involves:

[0092] Channel attention features are obtained by learning channel features from the initial image features using a channel attention learning layer.

[0093] The channel attention features are multiplied by the initial image features to obtain the channel image features;

[0094] Spatial attention features are obtained by learning spatial features of channel image features based on a spatial attention learning layer.

[0095] The spatial attention features are multiplied by the channel image features to obtain the image attention features.

[0096] Among them, the channel attention learning layer and the spatial attention learning layer are existing mature architectures, which will not be elaborated here.

[0097] After step S102, only false trajectories caused by vehicle vibration are removed. Some noise trajectories still exist in the spatiotemporal vibration response map. Furthermore, abnormal noise lines are introduced when extracting straight lines from the first target's driving trajectory and the second target's driving trajectory. In order to eliminate the above-mentioned noise trajectories and further improve the accuracy of vehicle objects, in some embodiments of the present invention, multiple extracted trajectories include a first extracted trajectory at the current time and a second extracted trajectory at a historical time; wherein, the current time is an adjacent sampling time of the historical time.

[0098] Because the vehicle's movement is relatively stable—that is, the trajectory characteristics of the same vehicle at different times do not differ much, while the trajectory characteristics of noise trajectories differ significantly from those of vehicle trajectories—based on this characteristic, in some embodiments of the present invention, such as... Figure 7 As shown, before step S104, the traffic flow statistics method based on vibration signals further includes:

[0099] S701, Obtain the first trajectory features of the first extracted trajectory and the second trajectory features of the second extracted trajectory;

[0100] S702. Determine the feature loss values ​​of the first extracted trajectory and the second extracted trajectory based on the first trajectory features and the second trajectory features;

[0101] S703. When the feature loss value is less than the loss threshold, the first extraction trajectory and the second extraction trajectory are merged to obtain the merged trajectory.

[0102] Then, in step S104, each extracted trajectory is treated as a vehicle object, specifically as follows:

[0103] Treat the merged trajectory as a vehicle object.

[0104] It should be understood that when the feature loss value is greater than or equal to the loss threshold, the first extracted trajectory and the second extracted trajectory do not belong to the driving trajectory of the same vehicle.

[0105] This invention utilizes the driving stability of vehicles to track and match extracted trajectories at different times, avoiding misidentification of the same vehicle's features at multiple different times as two different vehicle objects, thus improving the accuracy of the identified vehicle objects and consequently improving the accuracy of traffic flow statistics.

[0106] Furthermore, by using trajectory feature matching, noisy trajectories can be eliminated, further ensuring the accuracy of the identified vehicle objects.

[0107] It should be understood that the loss threshold can be set or adjusted according to the actual application scenario, and no specific limitation is made here.

[0108] To ensure the accuracy of the feature loss values, in a specific embodiment of the present invention, both the first trajectory feature and the second trajectory feature include speed, energy, lane, and position; then, as follows Figure 8 As shown, step S702 includes:

[0109] S801. Determine the speed loss value, energy loss value, lane loss value, and position loss value of the first extraction trajectory and the second extraction trajectory;

[0110] S802. Based on preset weights, the speed loss value, energy loss value, lane loss value and position loss value are weighted to obtain the feature loss value.

[0111] This invention determines the feature loss value through four physical features: speed, energy, lane, and position. This avoids the problem of inaccurate trajectory tracking and matching caused by a single-dimensional physical feature, ensuring the accuracy and reliability of trajectory tracking and matching, thereby improving the accuracy of the identified vehicle objects.

[0112] The expression for the feature loss value is as follows:

[0113]

[0114] In the formula, The feature loss value; The trajectory features of the first extracted trajectory at the current moment; The trajectory features of the second extracted trajectory at a historical moment; Feature weights.

[0115] In summary, the vibration signal-based traffic flow statistics method proposed in this invention achieves long-distance, all-weather, real-time vibration signal acquisition using a grating array vibration sensing optical cable, thereby enabling long-distance, all-weather, real-time traffic flow statistics. Furthermore, by setting signal attenuation rules, image enhancement, and trajectory tracking matching, the accuracy of identified vehicle objects is improved, resulting in accurate traffic flow statistics and providing strong support for subsequent vehicle route planning and rational vehicle diversion.

[0116] To better implement the vibration signal-based traffic flow statistics method in this embodiment of the invention, this embodiment also provides a vibration signal-based traffic flow statistics device, such as... Figure 9 As shown, the traffic flow counting device 900 based on vibration signals includes:

[0117] The spatiotemporal vibration response map acquisition unit 901 is used to acquire the spatiotemporal vibration response map of the cross-sectional area; the spatiotemporal vibration response map includes multiple initial vehicle travel trajectories.

[0118] The driving trajectory determination unit 902 is used to determine at least two candidate driving trajectories that conform to the signal attenuation law and at least one first target driving trajectory that does not conform to the signal attenuation law from multiple initial vehicle driving trajectories; and to determine the second target driving trajectory with the largest waveform amplitude among the at least two candidate driving trajectories.

[0119] The trajectory straight line extraction unit 903 is used to extract straight lines from the driving trajectory of the first target and the driving trajectory of the second target to obtain multiple extracted trajectories;

[0120] The traffic flow determination unit 904 is used to treat each extracted trajectory as a vehicle object and determine the traffic flow of the cross-sectional area based on the vehicle object.

[0121] The vibration signal-based traffic flow statistics device 900 provided in the above embodiments can realize the technical solutions described in the above embodiments of the vibration signal-based traffic flow statistics method. The specific implementation principles of each module or unit can be found in the corresponding content of the above embodiments of the vibration signal-based traffic flow statistics method, which will not be repeated here.

[0122] like Figure 10 As shown, the present invention also provides an electronic device 1000. The electronic device 1000 includes a processor 1001, a memory 1002, and a display 1003. Figure 10 Only some components of the electronic device 1000 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0123] In some embodiments, processor 1001 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in memory 1002 or process data, such as the traffic flow statistics method based on vibration signals in this invention.

[0124] In some embodiments of the present invention, the processor 1001 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, the processor 1001 may be local or remote. In some embodiments, the processor 1001 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, multiple clouds, etc., or any combination thereof.

[0125] In some embodiments, memory 1002 may be an internal storage unit of electronic device 1000, such as a hard disk or memory of electronic device 1000. In other embodiments, memory 1002 may also be an external storage device of electronic device 1000, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 1000.

[0126] Furthermore, the memory 1002 may include both internal storage units of the electronic device 1000 and external storage devices. The memory 1002 is used to store application software and various types of data installed on the electronic device 1000.

[0127] In some embodiments, display 1003 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 1003 is used to display information from electronic device 1000 and to display a visual user interface. Components 1001-1003 of electronic device 1000 communicate with each other via a system bus.

[0128] In some embodiments of the present invention, when the processor 1001 executes the traffic flow statistics program based on vibration signals in the memory 1002, the following steps can be implemented:

[0129] Obtain the spatiotemporal vibration response map of the cross-sectional area; the spatiotemporal vibration response map includes multiple initial vehicle travel trajectories;

[0130] Determine at least two candidate driving trajectories that conform to the signal attenuation law from multiple initial vehicle driving trajectories, and at least one first target driving trajectory that does not conform to the signal attenuation law, and determine the second target driving trajectory with the largest waveform amplitude among the at least two candidate driving trajectories;

[0131] Straight lines are extracted from the driving trajectories of the first and second targets to obtain multiple extracted trajectories;

[0132] Each extracted trajectory is treated as a vehicle object, and the traffic flow in the cross-sectional area is determined based on the vehicle object.

[0133] It should be understood that when the processor 1001 executes the traffic flow statistics program based on vibration signals in the memory 1002, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0134] Furthermore, the embodiments of the present invention do not specifically limit the type of the electronic device 1000 mentioned. The electronic device 1000 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices. It should also be understood that in some other embodiments of the present invention, the electronic device 1000 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0135] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions of the vibration signal-based traffic flow statistics method provided in the above-described method embodiments.

[0136] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0137] The present invention provides a detailed description of a traffic flow statistics method, apparatus, device, and storage medium based on vibration signals. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A traffic volume counting method based on a vibration signal, characterized by, The method comprises the following steps: acquiring a time-space vibration response graph of a section area; the time-space vibration response graph comprises a plurality of initial vehicle driving tracks; determining at least two selected driving tracks conforming to a signal attenuation rule and at least one first target driving track not conforming to the signal attenuation rule in the plurality of initial vehicle driving tracks, and determining a second target driving track with the largest waveform amplitude in the at least two selected driving tracks; extracting a straight line of the first target driving track and the second target driving track to obtain a plurality of extracted tracks; determining a vehicle flow of the section area based on a vehicle object of each extracted track; the signal attenuation rule is: In the formula, is the average amplitude of the first candidate driving trajectory; is the distance between the first candidate driving trajectory and the second candidate driving trajectory; is the second candidate driving trajectory with a distance of is the average amplitude of the second candidate driving trajectory with a distance of is the attenuation coefficient; is the natural logarithm.

2. The traffic volume counting method based on a vibration signal according to claim 1, characterized by, the acquiring of the time-space vibration response graph of the section area comprises: acquiring a global vehicle vibration signal collected based on a grating array vibration sensing optical cable; determining a target vehicle vibration signal in the global vehicle vibration signal based on the section area; the target vehicle vibration signal comprises a plurality of target vehicle vibration sub-signal sequences corresponding to each measuring point of the grating array vibration sensing optical cable, and the target vehicle vibration sub-signal sequence comprises a plurality of target vehicle vibration sub-signals corresponding to a plurality of collection time points; sorting the target vehicle vibration signal by taking the spatial position of the measuring point as the row and the time as the column to obtain the time-space vibration response graph.

3. The traffic volume counting method based on a vibration signal according to claim 1, characterized by, After the acquiring of the time-space vibration response graph of the section area, the method further comprises: acquiring a trained complete image enhancement model, the image enhancement model comprising a generator and a discriminator, the generator comprising a feature extraction unit, a feature attention learning unit and an enhancement unit; performing feature extraction on the time-space vibration response graph based on the feature extraction unit to obtain initial image features; performing channel attention learning and spatial attention learning on the initial image features in sequence based on the feature attention learning unit to obtain image attention features; performing feature reconstruction on the image attention features based on the enhancement unit to obtain an enhanced time-space vibration response graph.

4. The traffic volume counting method based on a vibration signal according to claim 3, characterized by, The feature attention learning unit comprises a spatial attention learning layer and a channel attention learning layer; the performing of channel attention learning and spatial attention learning on the initial image features in sequence based on the feature attention learning unit to obtain image attention features comprises: performing channel feature learning on the initial image features based on the channel attention learning layer to obtain channel attention features; multiplying the channel attention features and the initial image features to obtain channel image features; performing spatial feature learning on the channel image features based on the spatial attention learning layer to obtain spatial attention features; multiplying the spatial attention features and the channel image features to obtain the image attention features.

5. The method of claim 1, wherein The plurality of extracted tracks comprises a first extracted track at a current time and a second extracted track at a historical time; before the taking of each extracted track as a vehicle object, the method further comprises: acquiring a first track feature of the first extracted track and a second track feature of the second extracted track; determine a feature loss value of the first extracted trajectory and the second extracted trajectory based on the first trajectory feature and the second trajectory feature; merge the first extracted trajectory and the second extracted trajectory to obtain a merged trajectory when the feature loss value is less than a loss threshold value; the first extracted trajectory and the second extracted trajectory are taken as vehicle objects, and specifically: the merged trajectory is taken as the vehicle object.

6. The traffic volume counting method based on a vibration signal according to claim 5, characterized by, The first trajectory feature and the second trajectory feature both include speed, energy, lane, and position. The feature loss value of the first extracted trajectory and the second extracted trajectory is determined based on the first trajectory feature and the second trajectory feature, including: determining a speed loss value, an energy loss value, a lane loss value, and a position loss value of the first extracted trajectory and the second extracted trajectory; weighting the speed loss value, the energy loss value, the lane loss value, and the position loss value based on a preset weight to obtain the feature loss value.

7. A traffic flow statistics device based on vibration signals, characterized in that, including: a space-time vibration response map acquisition unit configured to acquire a space-time vibration response map of a section area; the space-time vibration response map includes a plurality of initial vehicle driving trajectories; a driving trajectory judgment unit configured to determine at least two selected driving trajectories conforming to a signal attenuation rule and at least one first target driving trajectory not conforming to the signal attenuation rule among the plurality of initial vehicle driving trajectories, and determine a second target driving trajectory with the largest waveform amplitude among the at least two selected driving trajectories; a trajectory straight line extraction unit configured to perform trajectory straight line extraction on the first target driving trajectory and the second target driving trajectory to obtain a plurality of extracted trajectories; a traffic volume determination unit configured to take each of the extracted trajectories as a vehicle object, and determine a traffic volume of the section area based on the vehicle object; the signal attenuation rule is: In the formula, is the average amplitude of the first candidate driving trajectory; is the distance between the first candidate driving trajectory and the second candidate driving trajectory; is the average amplitude of the second candidate driving trajectory with a distance of from the first candidate driving trajectory; is the decay coefficient; is the natural logarithm.

8. An electronic device, comprising: including a memory and a processor, wherein the memory is configured to store a program; the processor is coupled with the memory and is configured to execute the program stored in the memory to implement the steps in the vehicle traffic volume counting method based on vibration signals in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, a computer readable program or instruction for storing, which can implement the steps in the vehicle traffic volume counting method based on vibration signals in any one of claims 1 to 6 when executed by a processor. a computer readable program or instruction for storing, which can implement the steps in the vehicle traffic volume counting method based on vibration signals in any one of claims 1 to 6 when executed by a processor.

Images