Traffic control method and device, electronic equipment and computer readable medium
By extracting target image sequences from real-time traffic monitoring videos, generating traffic object information, identifying traffic status, and adjusting traffic equipment, the problem that traffic control equipment is difficult to cope with traffic congestion for a fixed-duration traffic control device is solved, real-time adjustment of traffic conditions and data processing are achieved. optimization.
Patent Information
- Application Number
- CN202411185469.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-03
AI Technical Summary
The existing fixed-time traffic control equipment is difficult to effectively solve the problem of traffic congestion, especially in traffic hub locations and peak hours. The real-time nature of traffic surveillance video and the large amount of data lead to insufficient hardware resources, making it difficult to identify traffic objects in a timely and effective manner. .
By obtaining the target image sequence in real-time traffic monitoring video, a collection of traffic object information is generated, including traffic object type, location and behavior type, updating area plan, identifying traffic status, determining traffic equipment information, generating traffic control information, and adjusting traffic equipment in real time To alleviate congestion.
Real-time adjustment of traffic equipment is achieved based on actual traffic conditions, effectively alleviating traffic congestion problems, reducing data processing volume, and reducing the demand for hardware resources.
Smart Images

Figure CN119068674A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a traffic control method, device, electronic device, and computer-readable medium. Background Art
[0002] With the continuous advancement of urbanization and the continuous increase in the number of motor vehicles, the probability of traffic congestion and other problems has increased significantly. At present, the common traffic control method is often to control traffic by setting traffic control equipment with fixed duration.
[0003] However, when the above method is adopted, the following technical problems often occur:
[0004] Traffic congestion often has temporal and spatial characteristics. For example, the probability of congestion is higher at traffic hubs and during peak hours in the morning and evening. It is difficult to solve the problem of traffic congestion by using traffic control equipment with fixed durations.
[0005] In the process of adopting technical solutions to solve the above technical problem 1, the following technical problem 2 is often accompanied:
[0006] Traffic surveillance videos are real-time and have large amounts of data. Traffic object recognition methods based directly on videos require a huge amount of data to be processed. When hardware resources are insufficient, it is difficult to identify traffic objects in a timely and effective manner.
[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention
[0008] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0009] Some embodiments of the present disclosure propose traffic control methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.
[0010] In a first aspect, some embodiments of the present disclosure provide a traffic control method, the method comprising: acquiring a target image sequence, wherein the target image sequence is a time-sequential monitoring video image extracted from a real-time traffic monitoring video, and the real-time traffic monitoring video is a traffic monitoring video for a target area; generating a traffic object information set based on the target image sequence, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object location, and traffic behavior type; performing traffic object update on an area plan corresponding to the target area based on the traffic object information set to obtain an updated area plan; performing traffic state identification on the updated area plan to generate traffic state information, wherein the traffic state information includes: traffic state type and traffic flow; determining a traffic equipment information set, wherein the traffic equipment corresponding to the traffic equipment information is a device for performing traffic control on the target area; generating traffic control information corresponding to each traffic equipment information in the traffic equipment information set based on the traffic state information to obtain a traffic control information set; performing traffic control on the target area based on the traffic control information set.
[0011] In a second aspect, some embodiments of the present disclosure provide a traffic control device, the device comprising: an acquisition unit, configured to acquire a target image sequence, wherein the target image sequence is a time-series continuous surveillance video image extracted from a real-time traffic surveillance video, and the real-time traffic surveillance video is a traffic surveillance video for a target area; a first generation unit, configured to generate a traffic object information set based on the target image sequence, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object location, and traffic behavior type; a traffic object update unit, configured to perform traffic object update on an area plan corresponding to the target area based on the traffic object information set, to obtain to the updated regional plan; a traffic status identification unit is configured to perform traffic status identification on the updated regional plan to generate traffic status information, wherein the traffic status information includes: traffic status type and traffic flow; a determination unit is configured to determine a traffic equipment information set, wherein the traffic equipment corresponding to the traffic equipment information is a device for performing traffic control on the target area; a second generation unit is configured to generate traffic control information corresponding to each traffic equipment information in the traffic equipment information set according to the traffic status information, and obtain a traffic control information set; a traffic control unit is configured to perform traffic control on the target area according to the traffic control information set.
[0012] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.
[0013] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
[0014] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the traffic control method of some embodiments of the present disclosure, the traffic congestion problem is effectively alleviated. Specifically, the reason for the traffic congestion problem is that traffic congestion often has spatiotemporal characteristics, such as a high probability of congestion at a traffic hub, a high probability of congestion during peak hours in the morning and evening, etc. It is difficult to solve the traffic congestion problem by using a fixed-duration traffic control device for traffic control. Based on this, the traffic control method of some embodiments of the present disclosure obtains a target image sequence, wherein the target image sequence is a time-series continuous monitoring video image extracted from a real-time traffic monitoring video, and the real-time traffic monitoring video is a traffic monitoring video for a target area. In practice, due to the large number of traffic cameras and the real-time characteristics of traffic monitoring videos, directly processing traffic monitoring videos will result in a large amount of data and high requirements for hardware resources. Therefore, the present disclosure removes duplicate images by obtaining a target image sequence to reduce the amount of data processing. Secondly, according to the target image sequence, a traffic object information set is generated, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object location, and traffic behavior type. In practice, traffic objects have static and dynamic characteristics. Therefore, the present disclosure describes traffic objects from three perspectives: traffic object type, traffic object location, and traffic behavior type. Then, according to the above-mentioned traffic object information set, the regional plan corresponding to the above-mentioned target area is updated with traffic objects to obtain an updated regional plan. A bird's-eye view description of the traffic state is achieved by mapping. Further, the above-mentioned updated regional plan is subjected to traffic state identification to generate traffic state information, wherein the above-mentioned traffic state information includes: traffic state type and traffic flow. In this way, the current traffic state type and traffic flow in the target area are determined. In addition, a traffic equipment information set is determined, wherein the traffic equipment corresponding to the traffic equipment information is a device for traffic control of the above-mentioned target area. In this way, the traffic equipment that can be used for traffic control in the target area is determined. Then, according to the above-mentioned traffic state information, traffic control information corresponding to each traffic equipment information in the above-mentioned traffic equipment information set is generated to obtain a traffic control information set. Finally, according to the above-mentioned traffic control information set, traffic control is performed on the above-mentioned target area. In this way, the purpose of real-time adjustment of traffic equipment according to the actual traffic conditions of the target area is achieved, and the traffic congestion problem is effectively alleviated. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.
[0016] Figure 1 is a flow chart of some embodiments of the traffic control method according to the present disclosure;
[0017] Figure 2 is a schematic diagram of the structure of some embodiments of the traffic control device according to the present disclosure;
[0018] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION
[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.
[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.
[0025] refer to Figure 1 , shows a process 100 of some embodiments of the traffic control method according to the present disclosure. The traffic control method comprises the following steps:
[0026] Step 101: Acquire a target image sequence.
[0027] In some embodiments, the execution subject of the traffic control method (e.g., a computing device) can obtain the above-mentioned target image sequence through a wired connection or a wireless connection. The target image sequence is a time-series continuous monitoring video image extracted from a real-time traffic monitoring video. The real-time traffic monitoring video is a traffic monitoring video for the target area. In practice, the real-time traffic monitoring video can be obtained in real time by a monitoring camera set in the target area. The target area can be an area with a high frequency of traffic congestion. In practice, the target area can be an intersection area.
[0028] As an example, the execution subject may extract image frames from the real-time traffic monitoring video in a fixed-frequency frame extraction manner at a fixed frame interval to obtain the target image sequence.
[0029] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future.
[0030] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.
[0031] Step 102: Generate a traffic object information set according to the target image sequence.
[0032] In some embodiments, the execution subject may generate a traffic object information set according to the target image sequence. The traffic object information in the traffic object information set includes: traffic object type, traffic object position, and traffic behavior type. The traffic object type characterizes the object type of the corresponding traffic object. In practice, the traffic object type may include: pedestrian type, motor vehicle type, and non-motor vehicle type. Specifically, the motor vehicle type may be further subdivided into: small motor vehicle type, medium motor vehicle type, and large motor vehicle type. The non-motor vehicle type may be further subdivided into: small non-motor vehicle type, medium non-motor vehicle type, and large non-motor vehicle type. For example, the traffic object type of a motorcycle may be a small motor vehicle type. The traffic object type of a truck may be a large motor vehicle type. The traffic object type of a bicycle may be a small non-motor vehicle type. In practice, the execution subject may perform object recognition on the target image sequence through a YOLO (You Only Look Once) model to generate a traffic object information set. The traffic behavior type may characterize the object behavior type of the traffic object. In practice, the traffic behavior type may include: traveling type, stopping type, accelerating type, turning type, and U-turn type.
[0033] In some optional implementations of some embodiments, the above-mentioned step of generating a traffic object information set according to the above-mentioned target image sequence may include the following steps:
[0034] The first step is to obtain the background image corresponding to the above target area.
[0035] The above-mentioned background image is an image of the area without traffic objects. In practice, the above-mentioned execution subject can obtain an image of the area without traffic objects captured by the internal surveillance camera of the target area. Specifically, with the change of seasons or static objects (for example, traffic station lights) in the target area, the image content of the background image will change accordingly. Therefore, the background image of the target area can be collected regularly, and the latest background image corresponding to the target area can be obtained.
[0036] The second step is to determine the image difference between each target image in the target image sequence and the background image to generate a candidate image and obtain a candidate image sequence.
[0037] In practice, candidate image = target image - background image.
[0038] The third step is to perform the following first processing step on each candidate image in the candidate image sequence:
[0039] The first sub-step is to perform corner point detection on the candidate image to generate a set of corner point coordinates.
[0040] In practice, the execution subject may perform corner point detection on the candidate image using the Harris corner point detection algorithm to generate a set of corner point coordinates. Specifically, the candidate image may contain at least one traffic object, and each traffic object corresponds to multiple corner point coordinates. Therefore, when performing corner point detection on the candidate image, the set of corner point coordinates is obtained.
[0041] The second sub-step is to construct a candidate region set based on the above corner point coordinate set.
[0042] The candidate regions in the candidate region set are closed regions surrounded by an even number of corner point coordinates, and there is no region intersection between the candidate regions in the candidate region set. The candidate regions do not contain corner point coordinates.
[0043] As an example, the set of corner point coordinates may include: corner point coordinate A, corner point coordinate B, corner point coordinate C, corner point coordinate D, corner point coordinate E, and corner point coordinate F. For example, S1: Starting with corner point coordinate A, search for K corner point coordinates adjacent to corner point coordinate A, where (K+1)%2=0. In practice, the starting value of K is 3. S2: Enclose a closed area based on corner point coordinate A and K corner point coordinates. Among them, the closed area does not contain the corner point coordinates, and there is no regional intersection between the closed area and other candidate areas (there may be overlap between the regional boundaries). S3: When there are other corner point coordinates, and the number of other corner point coordinates is greater than or equal to 2, K+2, and a new closed area is enclosed based on corner point coordinate A and K corner point coordinates. S4: When the new enclosed area contains the corner point coordinates or does not have a regional intersection with other candidate areas, the closed area enclosed by S2 is used as a candidate area. S5: When the newly enclosed area does not contain the corner point coordinates and does not have an area intersection with other candidate areas, S3 is repeatedly executed.
[0044] The third sub-step is to update the pixel values of the regions in the candidate image other than the closed regions in the closed region set to zero, so as to obtain an updated candidate region image.
[0045] In practice, the execution entity may update the pixel values of the areas in the candidate image other than the closed areas in the closed area set to 0, and obtain an updated candidate area image. Specifically, since the sizes of closed areas are different, if the local image features corresponding to the closed areas are used as the basis for traffic object recognition, it is necessary to train multiple recognition models with different input sizes. In addition, the areas other than the closed areas can be understood as areas that do not contain traffic objects. By updating the pixel values to zero, it is possible to avoid pixels outside the non-closed areas from participating in the calculation, thereby reducing the amount of data processing. At the same time, by generating an updated candidate area image, it is also possible to ensure that the model input size is unified and that the local images corresponding to the closed areas are feature processed in the same feature space.
[0046] The fourth step is to extract image features from the updated candidate region image sequence using an image feature extraction model to obtain an image feature sequence.
[0047] In practice, the above-mentioned image feature extraction model can adopt the Nano-Det-Plus model to perform image feature extraction on each updated candidate region image in the updated candidate region image sequence to generate image features and obtain the above-mentioned image feature sequence.
[0048] The fifth step is to generate a local image feature set through the object detector and the above image feature sequence.
[0049] In practice, the above object detector can frame the image features through the border regression algorithm, and use the framed local features as local image features. Specifically, since the pixel values outside the closed area in the updated candidate area image are 0, the detection frame often expands around the closed area. Therefore, in the process of border regression, the boundary of the closed area can be used as the constraint boundary to avoid generating too many invalid borders during border regression, thereby framing more invalid local image features.
[0050] Step 6: For each local image feature in the local image feature set, perform the following second processing step:
[0051] In the first sub-step, a traffic object type included in the traffic object information corresponding to the local image feature is determined by using a traffic object type classifier and the local image feature.
[0052] Among them, the traffic object type classifier is implemented using multiple fully connected layers connected in series.
[0053] The second sub-step is to determine the traffic behavior type included in the traffic object information corresponding to the above-mentioned local image features through a traffic behavior type classifier and the above-mentioned local image features.
[0054] Among them, the traffic behavior type classifier is implemented using multiple fully connected layers connected in series.
[0055] The third sub-step is to map the traffic object position included in the traffic object information corresponding to the local image feature according to the relative position of the image feature corresponding to the local image feature in the updated candidate area image.
[0056] In practice, since the position of the surveillance camera is fixed, under the premise of the surveillance camera calibration, the pixel coordinates in the image can be converted from the pixel coordinate system to the earth coordinate system by means of coordinate system conversion. Among them, the above-mentioned image feature extraction model, the above-mentioned object detector, the above-mentioned traffic object type classifier and the above-mentioned traffic behavior type classification model are included in the traffic object information generation model. Specifically, the traffic object information generation model is trained by a supervised model training method, that is, the surveillance video image is used as the model input, and the pre-labeled traffic object information set corresponding to the surveillance video image is used as the label for training.
[0057] The above-mentioned content of "in some optional implementations of some embodiments" as an inventive point of the present disclosure solves the second technical problem mentioned in the background technology, namely, "traffic monitoring video has the characteristics of real-time and large data volume. The traffic object recognition method directly based on the video has a huge amount of data processing. When the hardware resources are insufficient, it is difficult to timely and effectively recognize traffic objects." Specifically, first, by subtracting the target image from the background image, pixels different from the static background are extracted, thereby reducing the amount of data processing. Secondly, directly combining the model for object detection often requires processing the entire image, which has a large amount of data processing and high hardware requirements. Therefore, the present disclosure first adopts the traditional corner point detection method to determine the intersection coordinate set. Based on the corner point coordinates, the candidate area (region of interest) is enclosed, and the pixel value of the area in the above candidate image, except for the closed area in the above closed area set, is updated to zero to obtain the updated candidate area image, which further reduces the amount of data processing. In addition, since the candidate area belongs to the content change area compared to the background image, it often contains traffic objects. On this basis, the image features are extracted. Furthermore, through the object detector, local image features are generated to further reduce the subsequent data processing amount. Finally, the type of traffic object, the type of traffic behavior and the location of the traffic object are determined. This method can greatly reduce the amount of data processing in the process of traffic object recognition.
[0058] Step 103 , based on the traffic object information set, the regional plan map corresponding to the target area is updated with traffic objects to obtain an updated regional plan map.
[0059] In some embodiments, the execution subject may update the regional plan corresponding to the target area with traffic objects according to the traffic object information set to obtain an updated regional plan. In practice, the regional plan may be a plan marked with road conditions in the target area. Specifically, the regional plan may indicate the location of traffic signs and traffic equipment in the target area.
[0060] In some optional implementations of some embodiments, the execution subject updates the traffic object on the area plan corresponding to the target area according to the traffic object information set, which may include the following steps:
[0061] For each traffic object information in the above traffic object information set, perform the following traffic object update steps:
[0062] The first step is to determine the initial thermal area according to the traffic object type included in the above traffic object information.
[0063] Among them, the area of the initial thermal area corresponding to traffic objects of different traffic object types can be preset. In practice, due to the different sizes of different traffic objects, for example, the volume of traffic objects of small motor vehicle type is smaller than that of traffic objects of medium motor vehicle type. Therefore, the size of the initial thermal area corresponding to the traffic object of small motor vehicle type is smaller than the initial thermal area corresponding to the traffic object of medium motor vehicle type. Specifically, the above-mentioned execution subject can determine the initial thermal area corresponding to the traffic object type included in the traffic object information by mapping the traffic object type and the initial thermal area.
[0064] In the second step, based on the traffic object position, traffic behavior type and the initial thermal area included in the traffic object information, the thermal value of the position corresponding to the traffic object position included in the traffic object information is updated.
[0065] Among them, in practice, different traffic behavior types correspond to different thermal values. For example, when the traffic behavior type belongs to the type of traffic behavior that causes traffic congestion, the corresponding thermal value is high. When the traffic behavior type belongs to the type of traffic behavior that does not cause traffic congestion, the corresponding thermal value is low. Therefore, firstly, the above-mentioned execution subject can map the thermal value that matches the traffic behavior type by means of thermal value mapping. Then, by obtaining the thermal value that matches the traffic behavior type, the thermal value of the area surrounded by the above-mentioned initial thermal area centered on the position of the traffic object is updated. Specifically, the pixel value in the initial thermal area can be updated to the pixel value that is the same as the thermal value.
[0066] Step 104 , traffic status recognition is performed on the updated regional plan to generate traffic status information.
[0067] In some embodiments, the execution subject may identify the traffic status of the updated regional plan to generate traffic status information. The traffic status information includes: traffic status type and traffic flow. In practice, the traffic status type may include: congested state and non-congested state.
[0068] In some optional implementations of some embodiments, the execution subject performs traffic status identification on the updated regional plan to generate traffic status information, which may include the following steps:
[0069] In the first step, the thermal feature extraction model is used to extract the graph features of the updated regional plan to generate traffic status features.
[0070] In practice, the above-mentioned thermal feature extraction model can be composed of a convolutional neural network model with a U-shaped structure. Specifically, the thermal feature extraction model can adopt a U-net model structure. In addition, since the updated regional plan has been updated to a plan containing thermal values, and the thermal values are displayed in block form (initial thermal area), the convolution layer used for small feature processing can be removed to reduce the model depth and data processing volume. Specifically, the thermal feature extraction model can use 3 layers of serially connected convolution layers as a downsampling network. 3 layers of serially connected convolution layers are used as upsampling networks.
[0071] In the second step, the traffic state type and traffic flow included in the above traffic state information are obtained through the above traffic state characteristics, traffic state type classifier and traffic flow mapper.
[0072] The above-mentioned thermal feature extraction model, the above-mentioned traffic state classifier and the above-mentioned traffic flow mapper are included in the traffic state recognition model. In practice, the traffic state type classifier is implemented by multiple fully connected layers connected in series. The traffic flow mapper adopts a convolutional neural network model. Specifically, the traffic flow predictor can use regression prediction to predict the traffic flow.
[0073] Step 105: Determine a traffic equipment information set.
[0074] In some embodiments, the execution subject may determine a set of traffic equipment information, wherein the traffic equipment corresponding to the traffic equipment information is a device used to perform traffic control on the target area.
[0075] In some optional implementations of some embodiments, the execution subject determines the traffic equipment information set, which may include the following steps:
[0076] In the first step, a temporary communication line between traffic signal controllers corresponding to the above target areas is created.
[0077] The traffic signal controller is a device for controlling the signals of traffic equipment in a certain area. In practice, the execution subject may establish a socket connection with the traffic signal controller as a temporary communication link.
[0078] The second step is to scan the working traffic equipment in the target area in the form of broadcasting in response to the successful creation, and obtain a set of traffic equipment identifications.
[0079] The third step is to scan the traffic equipment information database for each traffic equipment identification in the traffic equipment identification set using the traffic equipment identification as a keyword to obtain the traffic equipment information corresponding to the traffic equipment identification as candidate traffic equipment information.
[0080] The candidate traffic equipment information includes: a first traffic equipment type, a second traffic equipment type and a device communication address, wherein the first traffic equipment type includes: a traffic control type and a non-traffic control type. The second traffic equipment type characterizes the specific device type of the traffic equipment. For example, the second traffic equipment type may be a traffic light type or an information display screen type. The device communication address may be a communication address for directly communicating with the corresponding traffic equipment. For example, an IP address.
[0081] The fourth step is to select candidate traffic equipment information whose first traffic equipment type is a traffic control type from the obtained candidate traffic equipment information set as traffic equipment information to obtain the above traffic equipment information set.
[0082] Step 106: Generate traffic control information corresponding to each traffic equipment information in the traffic equipment information set according to the traffic state information to obtain a traffic control information set.
[0083] In some embodiments, the execution subject may generate traffic control information corresponding to each traffic device in the traffic device information set according to the traffic status information to obtain the traffic control information set, wherein the traffic control information represents the specific control method of the traffic device.
[0084] In some optional implementations of some embodiments, the execution subject generates, according to the traffic state information, traffic control information corresponding to each traffic equipment information in the traffic equipment information set, which may include the following steps:
[0085] The first step is to activate a traffic control information prediction model that matches the second traffic equipment type included in the above traffic equipment information.
[0086] In practice, different traffic equipment may have different equipment characteristics. For example, a single-light traffic light and a multi-light traffic light. For a multi-light traffic light, it may be necessary to generate traffic control information corresponding to different lights. For example, the control duration of a red light and the control duration of a green light. Specifically, the traffic control information prediction models all use a weak neural network model, that is, a lightweight model structure is used to predict the control duration by regression. In order to further reduce the cost of using the model, different traffic control information prediction models can be trained by transfer learning. The traffic control information prediction model can use a convolutional neural network model.
[0087] The second step is to generate a control duration in response to successful activation based on the traffic control information prediction model and the traffic flow.
[0088] In practice, the execution entity may input the traffic flow into the traffic control information prediction model to obtain the control duration. Specifically, for a traffic light with multiple lights, the control duration corresponding to different light types may be generated.
[0089] The third step is to generate traffic control information of the traffic equipment corresponding to the traffic equipment information according to the control duration and the traffic equipment information.
[0090] For example, traffic control information: second traffic equipment type: multi-light traffic signal light; equipment communication address: C; red light control time: A seconds; green light control time: B seconds.
[0091] Step 107: Perform traffic control on the target area according to the traffic control information set.
[0092] In some embodiments, the execution subject may perform traffic control on the target area according to the traffic control information set. In practice, the execution subject may control the operation of the traffic equipment according to the traffic signal control information with the control duration as the duration to achieve traffic control on the target area.
[0093] In some optional implementations of some embodiments, the execution subject performs traffic control on the target area according to the traffic control information set, which may include the following steps:
[0094] The first step is to perform a logical check on the traffic control information in the above traffic control information set.
[0095] In practice, for example, traffic equipment itself has an execution order, such as red light-yellow light-green light. For another example, there is a linkage logic relationship between traffic equipment used to direct motor vehicles and traffic equipment used to direct pedestrians. Therefore, the above-mentioned execution subject can perform logic verification on the traffic control information in the traffic control information set through the execution logic between the traffic equipment itself and the traffic, so as to avoid erroneous traffic control that increases traffic congestion and even causes traffic accidents.
[0096] The second step is to distribute the traffic control information in the traffic control information set to corresponding traffic equipment through the traffic signal controller in response to passing the verification, so that traffic control is performed on the target area through the traffic equipment.
[0097] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the traffic control method of some embodiments of the present disclosure, the traffic congestion problem is effectively alleviated. Specifically, the reason for the traffic congestion problem is that traffic congestion often has spatiotemporal characteristics, such as a high probability of congestion at a traffic hub, a high probability of congestion during peak hours in the morning and evening, etc. It is difficult to solve the traffic congestion problem by using a fixed-duration traffic control device for traffic control. Based on this, the traffic control method of some embodiments of the present disclosure obtains a target image sequence, wherein the target image sequence is a time-series continuous monitoring video image extracted from a real-time traffic monitoring video, and the real-time traffic monitoring video is a traffic monitoring video for a target area. In practice, due to the large number of traffic cameras and the real-time characteristics of traffic monitoring videos, directly processing traffic monitoring videos will result in a large amount of data and high requirements for hardware resources. Therefore, the present disclosure removes duplicate images by obtaining a target image sequence to reduce the amount of data processing. Secondly, according to the target image sequence, a traffic object information set is generated, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object location, and traffic behavior type. In practice, traffic objects have static and dynamic characteristics. Therefore, the present disclosure describes traffic objects from three perspectives: traffic object type, traffic object location, and traffic behavior type. Then, according to the above-mentioned traffic object information set, the regional plan corresponding to the above-mentioned target area is updated with traffic objects to obtain an updated regional plan. A bird's-eye view description of the traffic state is achieved by mapping. Further, the above-mentioned updated regional plan is subjected to traffic state identification to generate traffic state information, wherein the above-mentioned traffic state information includes: traffic state type and traffic flow. In this way, the current traffic state type and traffic flow in the target area are determined. In addition, a traffic equipment information set is determined, wherein the traffic equipment corresponding to the traffic equipment information is a device for traffic control of the above-mentioned target area. In this way, the traffic equipment that can be used for traffic control in the target area is determined. Then, according to the above-mentioned traffic state information, traffic control information corresponding to each traffic equipment information in the above-mentioned traffic equipment information set is generated to obtain a traffic control information set. Finally, according to the above-mentioned traffic control information set, traffic control is performed on the above-mentioned target area. In this way, the purpose of real-time adjustment of traffic equipment according to the actual traffic conditions of the target area is achieved, and the traffic congestion problem is effectively alleviated.
[0098] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a traffic control device. These device embodiments are Figure 1 Corresponding to the method embodiments shown, the traffic control device can be specifically applied to various electronic devices.
[0099] like Figure 2 As shown, the traffic control device 200 of some embodiments includes: an acquisition unit 201, a first generation unit 202, a traffic object update unit 203, a traffic state recognition unit 204, a determination unit 202, a second generation unit 206 and a traffic control unit 207. The acquisition unit 201 is configured to acquire a target image sequence, wherein the target image sequence is a time-series continuous monitoring video image extracted from a real-time traffic monitoring video, and the real-time traffic monitoring video is a traffic monitoring video for a target area; the first generation unit 202 is configured to generate a traffic object information set according to the target image sequence, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object location, and traffic behavior type; the traffic object update unit 203 is configured to perform traffic object update on the area plan corresponding to the target area according to the traffic object information set to obtain an updated area plan; the traffic state recognition unit 204 is configured to obtain a traffic object update on the area plan corresponding to the target area according to the traffic object information set, and obtain an updated area plan; The identification unit 204 is configured to identify the traffic status of the updated regional plan to generate traffic status information, wherein the traffic status information includes: traffic status type and traffic flow; the determination unit 202 is configured to determine a traffic equipment information set, wherein the traffic equipment corresponding to the traffic equipment information is a device used to perform traffic control on the target area; the second generation unit 206 is configured to generate traffic control information corresponding to each traffic equipment information in the traffic equipment information set according to the traffic status information, and obtain a traffic control information set; the traffic control unit 207 is configured to perform traffic control on the target area according to the traffic control information set.
[0100] It is understood that the units described in the traffic control device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the traffic control device 200 and the units included therein, and will not be described in detail here.
[0101] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0102] like Figure 3As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. Various programs and data required for the operation of the electronic device 300 are also stored in the random access memory 303. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other via a bus 304. An input / output interface 305 is also connected to the bus 304.
[0103] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0104] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.
[0105] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0106] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0107] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a target image sequence, wherein the target image sequence is a time-sequential monitoring video image extracted from a real-time traffic monitoring video, and the real-time traffic monitoring video is a traffic monitoring video for a target area; generates a traffic object information set according to the target image sequence, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object location, and traffic behavior type; performs traffic object update on the area plan corresponding to the target area according to the traffic object information set to obtain an updated area plan; performs traffic state recognition on the updated area plan to generate traffic state information, wherein the traffic state information includes: traffic state type and traffic flow; determines a traffic equipment information set, wherein the traffic equipment corresponding to the traffic equipment information is a device for performing traffic control on the target area; generates traffic control information corresponding to each traffic equipment information in the traffic equipment information set according to the traffic state information to obtain a traffic control information set; performs traffic control on the target area according to the traffic control information set.
[0108] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0109] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0110] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be arranged in a processor, for example, may be described as: a processor includes an acquisition unit, a first generation unit, a traffic object update unit, a traffic state recognition unit, a determination unit, a second generation unit and a traffic control unit. The names of these units do not constitute limitations on the units themselves in certain cases, for example, the acquisition unit may also be described as "acquiring a target image sequence, wherein the target image sequence is a time-series continuous monitoring video image extracted from a real-time traffic monitoring video, and the real-time traffic monitoring video is a unit of traffic monitoring video for a target area".
[0111] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0112] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.
Claims
1. A traffic control method, comprising: Acquire a target image sequence, wherein the target image sequence is a time-sequential monitoring video image extracted from a real-time traffic monitoring video, and the real-time traffic monitoring video is a traffic monitoring video for a target area; Generate a traffic object information set according to the target image sequence, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object location, and traffic behavior type; According to the traffic object information set, the regional plan map corresponding to the target area is updated with traffic objects to obtain an updated regional plan map; Performing traffic state recognition on the updated regional plan to generate traffic state information, wherein the traffic state information includes: traffic state type and traffic flow; Determine a set of traffic equipment information, wherein the traffic equipment corresponding to the traffic equipment information is a device used to perform traffic control on the target area; Generate traffic control information corresponding to each traffic equipment information in the traffic equipment information set according to the traffic state information to obtain a traffic control information set; Traffic control is performed on the target area according to the traffic control information set.
2. The method according to claim 1, wherein: The updating of the traffic object on the area plan corresponding to the target area according to the traffic object information set includes: For each piece of traffic object information in the traffic object information set, the following traffic object updating steps are performed: Determining an initial thermal area according to the traffic object type included in the traffic object information; According to the traffic object position, traffic behavior type and the initial thermal area included in the traffic object information, the thermal value of the position corresponding to the traffic object position included in the traffic object information in the regional plan is updated.
3. The method according to claim 2, wherein: The performing traffic status recognition on the updated regional plan to generate traffic status information includes: Extracting graph features from the updated regional plan map using a thermal feature extraction model to generate traffic state features; The traffic state type and traffic flow included in the traffic state information are obtained through the traffic state characteristics, traffic state type classifier and traffic flow mapper, wherein the thermal feature extraction model, the traffic state classifier and the traffic flow mapper are included in the traffic state recognition model.
4. The method according to claim 3, wherein: The determining of the traffic equipment information set includes: creating a temporary communication link between traffic signal controllers corresponding to the target area; In response to successful creation, scanning the traffic equipment in working state in the target area in the form of broadcasting through the temporary communication line to obtain a set of traffic equipment identifications; For each traffic equipment identification in the traffic equipment identification set, using the traffic equipment identification as a keyword, scanning a traffic equipment information database, obtaining traffic equipment information corresponding to the traffic equipment identification as candidate traffic equipment information, wherein the candidate traffic equipment information includes: a first traffic equipment type, a second traffic equipment type and a device communication address, wherein the first traffic equipment type includes: a traffic control type and a non-traffic control type; The candidate traffic equipment information including the first traffic equipment type of the traffic control type is screened out from the obtained candidate traffic equipment information set as the traffic equipment information to obtain the traffic equipment information set.
5. The method according to claim 4, wherein: The generating, according to the traffic state information, traffic control information corresponding to each traffic equipment information in the traffic equipment information set comprises: activating a traffic control information prediction model that matches a second traffic equipment type included in the traffic equipment information; In response to successful activation, generating a control duration according to the traffic control information prediction model and the traffic flow; Traffic control information of the traffic equipment corresponding to the traffic equipment information is generated according to the control duration and the traffic equipment information.
6. The method according to claim 5, wherein: The performing traffic control on the target area according to the traffic control information set includes: Performing a logic check on the traffic control information in the traffic control information set; In response to passing the verification, the traffic control information in the traffic control information set is distributed to corresponding traffic equipment through the traffic signal controller, so that traffic control is performed on the target area through the traffic equipment.
7. The method according to claim 6, wherein: Generating a traffic object information set according to the target image sequence includes: Acquire a background image corresponding to the target area, wherein the background image is an image of the area in a state where no traffic objects are included; Determine an image difference between each target image in the target image sequence and the background image to generate a candidate image, thereby obtaining a candidate image sequence; For each candidate image in the candidate image sequence, the following first processing step is performed: Performing corner point detection on the candidate image to generate a set of corner point coordinates; According to the set of corner point coordinates, a candidate region set is constructed, wherein the candidate regions in the candidate region set are closed regions surrounded by an even number of corner point coordinates, there is no region intersection between the candidate regions in the candidate region set, and the candidate regions do not contain corner point coordinates; updating pixel values of regions in the candidate image other than the closed regions in the closed region set to zero to obtain an updated candidate region image; By using the image feature extraction model, image features are extracted from the obtained updated candidate region image sequence to obtain an image feature sequence; Generate a local image feature set by using an object detector and the image feature sequence; and perform the following second processing step for each local image feature in the local image feature set: Determine the traffic object type included in the traffic object information corresponding to the local image feature by using a traffic object type classifier and the local image feature; Determine the traffic behavior type included in the traffic object information corresponding to the local image feature by using the traffic behavior type classifier and the local image feature; According to the relative position of the image feature corresponding to the local image feature in the updated candidate area image, the position of the traffic object included in the traffic object information corresponding to the local image feature is mapped, wherein the image feature extraction model, the object detector, the traffic object type classifier and the traffic behavior type classification model are included in the traffic object information generation model.
8. A traffic control device comprising: An acquisition unit is configured to acquire a target image sequence, wherein the target image sequence is a time-sequentially continuous surveillance video image extracted from a real-time traffic surveillance video, and the real-time traffic surveillance video is a traffic surveillance video for a target area; A first generating unit is configured to generate a traffic object information set according to the target image sequence, wherein the traffic object information in the traffic object information set includes: traffic object type, traffic object position, and traffic behavior type; A traffic object updating unit is configured to perform traffic object updating on the area plan corresponding to the target area according to the traffic object information set to obtain an updated area plan; A traffic state identification unit is configured to perform traffic state identification on the updated regional plan to generate traffic state information, wherein the traffic state information includes: traffic state type and traffic flow; A determination unit is configured to determine a set of traffic equipment information, wherein the traffic equipment corresponding to the traffic equipment information is a device for performing traffic control on the target area; A second generating unit is configured to generate traffic control information corresponding to each traffic equipment information in the traffic equipment information set according to the traffic state information, so as to obtain a traffic control information set; The traffic control unit is configured to perform traffic control on the target area according to the traffic control information set.
9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.
10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
