Self-adaptive management system for overload and overrun of urban freight

Abstract

The invention relates to the technical field of vehicle overload and over-limit management, in particular to an urban freight overload and over-limit self-adaptive management system, which comprises an acquisition module used for acquiring previous detection data of a truck for overload and over-limit and an image during previous detection; the marking module is used for marking edge trucks close to overload or overrun according to the previous detection data and the corresponding edge intervals; the interaction management module is used for acquiring images of marginal trucks in traveling; the feature recognition module is used for recognizing load change features and size change features of the edge trucks according to the images of the edge trucks; the verification module is used for verifying whether the edge truck with the load change characteristic or the size change characteristic is overloaded or overloaded; and the self-adaptive correction module is used for correcting the edge interval corresponding to the detection data according to the proportion of the number of the edge trucks which are verified to be overloaded and overloaded. The influence of the secondary cargo loading condition on the road surface and the traffic environment is avoided through feature analysis, and the road safety is improved.

Description

Technical Field

[0001] The invention relates to the technical field of vehicle overload and over-limit management, and in particular to an adaptive management system for overload and over-limit of urban freight transport. Background Art

[0002] Truck overload refers to the situation where the length, width, height and weight of a freight vehicle exceeds the limits prescribed by regulations. The main focus is on the relationship between vehicle loading and roads, with a particular focus on the normal use of roads. Overloading refers to the situation where the vehicle is loaded with cargo that exceeds the rated load of the vehicle. The main focus of overloading is on vehicle performance and the resulting driving safety. Overloaded and over-limited trucks pose a threat to road safety and increase the risk of traffic accidents. By effectively identifying and preventing these vehicles from taking to the road, the accident rate can be reduced.

[0003] For example, the prior art discloses a real-time monitoring method for vehicle overload, which monitors the overload condition of the vehicle in real time through a vehicle overload monitoring system, and the vehicle overload monitoring system includes a management server arranged at a control center, and a vehicle information collection unit arranged at a monitoring point; when the vehicle passes through the monitoring point, the vehicle information collection unit obtains the vehicle's license plate image information, the vehicle's contour image information, and the vehicle's weight and axle number data and sends them to the management server; the management server receives the data and image information, and determines whether the vehicle is overloaded, and if the judgment result is that the vehicle is overloaded, an electronic ticket is generated and sent to the mobile terminal of the vehicle owner. The present invention discloses a real-time monitoring method for vehicle overload, which monitors the overload condition of the vehicle in real time through a vehicle overload monitoring system, and can efficiently supervise the overload condition of the vehicle.

[0004] However, the above solution lacks targeted analysis of trucks that are close to being overloaded. If the truck is loaded twice, it cannot be discovered in time, and the timeliness of monitoring cannot be guaranteed. Summary of the invention

[0005] The purpose of the present invention is to provide an adaptive management system for urban freight overload and overlimit, so as to solve the problems in the prior art of lack of targeted analysis of trucks that are close to overlimit, and failure to detect in time if the truck has secondary loading, and failure to ensure the timeliness of monitoring.

[0006] The invention provides an adaptive management system for overload and overlimit of urban freight, comprising a collection module, a marking module, an interactive management module, a feature recognition module, a verification module and an adaptive correction module.

[0007] The acquisition module is used to obtain the previous detection data of the truck for overloading and overrun, as well as the image of the previous detection;

[0008] The marking module is connected to the acquisition module and is used to mark marginal trucks approaching overload or overrun based on the previous detection data and the corresponding marginal interval;

[0009] The interaction management module is connected to the marking module and is used to obtain an image of the moving edge truck;

[0010] The feature recognition module is connected to the interaction management module and is used to recognize the load change feature and size change feature of the marginal truck based on the image of the marginal truck;

[0011] The verification module is connected to the feature recognition module and is used to verify whether the marginal truck with the load change feature or the size change feature is overloaded or out of limit;

[0012] The adaptive correction module is connected to the marking module and the verification module respectively, and is used to correct the edge interval corresponding to the detection data according to the proportion of the number of edge trucks verified to be overloaded and over-limit.

[0013] As an optimal technical solution for the adaptive management system of urban freight overload and overlimit, the load change characteristic is that the contact area between the tire and the ground in the image of the edge truck increases compared with the previous detection, or the distance between the tire and the body decreases compared with the previous detection.

[0014] As a preferred technical solution for the adaptive management system of urban freight overload and overlimit, the size change feature is that the overall height, length or width of the truck in the image of the edge truck increases relative to the previous detection.

[0015] As a preferred technical solution for the adaptive management system of urban freight overload and overlimit, the feature recognition module also includes a fluctuation detection unit. The fluctuation detection unit determines the vibration state of the out-of-range cargo and the vibration state of the vehicle body in response to the size fluctuation characteristics of the marginal truck. In response to the inconsistency of the vibration states of the two, it determines that the cargo state of the marginal truck is faulty and outputs an alarm message to the marginal truck.

[0016] As a preferred technical solution for the adaptive management system of overload and overlimit of urban freight, the fluctuation detection unit determines the vibration state of the cargo and the vibration state of the vehicle body by optical flow method.

[0017] As an optimal technical solution for the adaptive management system of urban freight overload and overlimit, the marking module marks the trucks whose detection data are in the corresponding marginal interval as marginal trucks, and the corresponding marking action is to store the license plate number of the marginal truck and upload it to the interactive management module.

[0018] As a preferred technical solution for the adaptive management system of urban freight overload and overlimit, the interactive management module includes:

[0019] A storage unit, used to store the license plate number of the marginal truck;

[0020] A license plate recognition unit is used to recognize the license plate number of the truck collected by the camera;

[0021] The traversal unit is used to traverse and compare the license plate numbers of trucks and the license plate numbers of marginal trucks to filter out marginal truck images.

[0022] As a preferred technical solution for the adaptive management system of urban freight overload and overlimit, the interactive management module is also used to determine the camera in front of the edge truck according to the lane of the edge truck, and send the collection instruction to the corresponding camera.

[0023] As a preferred technical solution for the adaptive management system of urban freight overload and overlimit, the adaptive correction module corrects the current edge interval [Kmin, Kmax) at a preset period, including:

[0024] Get the total number of marginal trucks that are verified within a preset period;

[0025] Get the number of marginal trucks verified as overloaded and over-limit;

[0026] Determine the proportion P of marginal trucks verified as overloaded and over-limit based on the total number of marginal trucks verified within the preset period;

[0027] Compare the quantity proportion P with the preset ratio. If the two are the same or the quantity proportion P is greater than the preset ratio, maintain the current edge interval. If the quantity proportion P is less than the preset ratio, increase Kmin.

[0028] When the quantity proportion P is less than the preset ratio, the adjustment amount of Kmin is inversely proportional to the quantity proportion P.

[0029] As a preferred technical solution for the adaptive management system for overload and overlimit of urban freight, the preset period is one week and the preset ratio is 75%.

[0030] The beneficial effects of the present invention are:

[0031] The present invention provides an adaptive management system for overload and overlimit of urban freight. The adaptive management system for overload and overlimit of urban freight can effectively determine whether the truck has been loaded after the previous detection through image acquisition and data acquisition of the truck in the previous detection, and the vehicle on the edge of overload and overlimit is subjected to targeted image screening and feature analysis through cameras in the traffic network. If loaded, the possibility of overload and overlimit of the edge vehicle is high. The impact on the road surface and traffic environment in the case of secondary loading of goods is avoided through image analysis of corresponding features, and overload and overlimit can be discovered in advance before detection, thereby improving road safety.

[0032] Furthermore, the adaptive correction module of the present invention corrects the edge interval to avoid excessive computing power consumption of the system due to too many demarcated edge vehicles, thereby improving the operating efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a structural block diagram of an adaptive management system for overload and overlimit of urban freight transport in an embodiment of the present invention;

[0034] Figure 2 is a structural block diagram of an interaction management module in an embodiment of the present invention;

[0035] Figure 3 4 is a flowchart of the working process of the adaptive correction module in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] In the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. Among them, the terms "first position" and "second position" are two different positions, and the first feature "above", "above" and "above" the second feature include the first feature being directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. The first feature "below", "below" and "below" the second feature include the first feature being directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0038] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0040] See also Figure 1-Figure 3 As shown, this embodiment provides an adaptive management system for overload and overlimit of urban freight, which includes a collection module, a marking module, an interactive management module, a feature recognition module, a verification module and an adaptive correction module.

[0041] The acquisition module is used to obtain the previous inspection data of overload and overlimit of trucks, as well as the images of the previous inspection; (the inspection data includes vehicle size data and load data)

[0042] The marking module is connected to the acquisition module and is used to mark the edge trucks that are close to being overloaded or over-limit according to the previous detection data and the corresponding edge interval; (For different types of detection data, the corresponding edge intervals are different, which can be set in combination with the actual scenario)

[0043] The interactive management module is connected to the marking module and is used to obtain images of the moving edge trucks;

[0044] The feature recognition module is connected to the interaction management module and is used to recognize the load change feature and size change feature of the edge truck based on the image of the edge truck;

[0045] The verification module is connected to the feature recognition module to verify whether the marginal truck with load change feature or size change feature is overloaded or out of limit;

[0046] The adaptive correction module is connected to the marking module and the verification module respectively, and is used to correct the edge interval corresponding to the detection data according to the proportion of the edge trucks verified to be overloaded and over-limit.

[0047] In the above embodiment, by collecting images and data collected from the truck in the previous time, targeted image screening and feature analysis are performed on the vehicles on the edge of overloading and over-limit through cameras in the traffic network, so that it can be effectively determined that the truck has been loaded after the previous detection. If loaded, the possibility of overloading and over-limit of the marginal vehicle is high. Through the image analysis of the corresponding features, the impact on the road surface and traffic environment in the case of secondary loading of goods is avoided, and overloading and over-limit can be discovered in advance before detection, thereby improving road safety.

[0048] In detail, the acquisition module is used to obtain the overload and overrun data and image information of the truck in the previous detection. Specifically, the acquisition module collects key parameters including truck load, cargo size and the contact area between the truck tire and the ground during each detection, and records the truck image at that time. This module ensures the data integrity during each detection and provides a basis for the subsequent marking of marginal vehicles. The marking module is directly connected to the acquisition module, and uses the previous detection data and the corresponding marginal interval to mark the truck that is close to being overloaded or overrun (called "marginal truck"). Based on the set marginal threshold, the marking module combines the characteristics of load, size and tire contact area changes to mark marginal trucks that may be overloaded or overrun. If the weight or size of a truck is close to the set threshold, the marking module will set it as a marginal truck and enter the subsequent interactive management and feature recognition process through special marking. The interactive management module is connected to the marking module and is used to obtain the image of the marked marginal truck from the traffic camera. The module retrieves real-time images through the intelligent camera network and dynamically monitors the status of the marginal truck in motion. The image acquisition capability of the interactive management module ensures that the system obtains the latest image data during the movement of the truck, providing image support for subsequent feature recognition. The feature recognition module is connected to the interactive management module, and receives and analyzes the images of edge trucks to identify their load change and size change characteristics. The module identifies the actual overload and overrun trends of the trucks by calculating the load and size change parameters in the image, including the tire contact area and cargo height change. Through the image processing algorithm, the module can accurately identify whether further cargo loading behavior has occurred after the previous detection. The verification module is connected to the feature recognition module and is responsible for verifying whether the edge trucks with load change or size change characteristics are indeed overloaded or overrun. The verification module compares the previous detection data with the current image to confirm whether the marked edge trucks exceed the safe load or size threshold in the current driving state, and finally generates the corresponding verification results. The adaptive correction module is connected to the marking module and the verification module respectively, and its main function is to correct the edge interval range based on the current proportion of overloaded and overrun trucks. According to the feedback data of the verification module, this module adjusts the edge interval of the system to make the detection range more accurate.

[0049] When the load of a truck increases, the contact area between the tire and the ground tends to increase because the additional weight causes the tire to compress further. In the collected image, by identifying the contact area between the tire and the ground and comparing it with the previous detection data, if the contact area is found to increase, it can be preliminarily determined that the load has an increasing trend. In addition, the increase in load will also affect the distance between the tire and the body. The system analyzes the distance between the top of the tire and the bottom of the body in the image. If the distance decreases relative to the previous detection, the truck also has an overload trend. Therefore, the load change feature is set to the increase in the contact area between the tire and the ground in the image of the edge truck relative to the previous detection, or the decrease in the distance between the tire and the body relative to the previous detection. The size change feature detects the possibility of overloading of goods. By comparing the previous detection data, if the overall height, length or width of the current truck increases in the image, it indicates that the loading size of the truck is at risk of overloading. For example, if the height of the truck is detected to increase, the system will determine it as a potential overloading truck. The feature recognition module will automatically analyze the outline of the truck in the image to determine whether its dimensions in each direction exceed the previous detection threshold, thereby identifying the overloading trend of the truck. Therefore, the size change feature is set to be that the height, length or width of the entire truck in the image of the edge truck increases relative to the previous detection.

[0050] Specifically, the feature recognition module also includes a fluctuation detection unit. The fluctuation detection unit determines the vibration state of the goods and the vibration state of the vehicle body that are out of range in response to the size fluctuation feature of the edge truck. In response to the inconsistency of the vibration states of the two, the cargo state fault of the edge truck is determined and an alarm information is output to the edge truck. The fluctuation detection unit determines the vibration state of the goods and the vibration state of the vehicle body by the optical flow method. The fluctuation detection unit tracks the motion trajectory of key points in the truck image by the optical flow algorithm. The algorithm calculates the vibration state of the goods and the vibration state of the vehicle body respectively by analyzing the pixel motion of the goods and the vehicle body in the image sequence. The optical flow method has high accuracy and is suitable for real-time dynamic scene detection. The system collects a continuous image sequence of the truck passing through the traffic camera and identifies the feature points of the vehicle body and the goods through the image processing algorithm. Next, the optical flow method tracks the motion changes of these feature points to obtain the vibration amplitude and frequency information of the goods and the vehicle body. The fluctuation detection unit compares the vibration state of the goods with the vibration state of the vehicle body. When the vibration frequency or amplitude of the goods and the vehicle body is inconsistent (for example, the vibration of the goods is large and the vehicle body is small), the system determines that the cargo state is abnormal, that is, there may be looseness or loose fixation. When the fluctuation detection unit determines that there is an abnormal situation of inconsistent vibration, the system immediately generates an alarm message and sends it to the driver of the marginal truck or the dispatch management platform. The alarm message can include a description of the specific abnormal situation, the location and recommended safety inspection measures for timely processing to ensure freight safety.

[0051] To facilitate subsequent analysis, the marking module marks the trucks whose detection data are in the corresponding marginal interval as marginal trucks, and the corresponding marking action is to store the license plate number of the marginal truck and upload it to the interaction management module. In detail, the interaction management module includes:

[0052] a storage unit for storing a license plate number of a marginal truck;

[0053] A license plate recognition unit is used to identify the license plate number of the truck collected by the camera;

[0054] The traversal unit is used to traverse and compare the license plate numbers of trucks and the license plate numbers of marginal trucks to filter out marginal truck images. The storage unit of the interactive management module is used to centrally store all license plate numbers marked as marginal trucks and continuously update them for subsequent analysis and screening. The license plate recognition unit collects images obtained by traffic cameras and automatically extracts the license plate number of the current truck through the license plate recognition algorithm, and transmits it to the traversal unit in real time. After each new license plate number is recognized, the traversal unit automatically retrieves the license plate number of the marginal truck in the storage unit and compares it with the recognized license plate number one by one. If a consistent license plate number is found, the truck is immediately marked as a marginal truck, and its image is sent to the feature recognition module for further detection.

[0055] In detail, the interactive management module is provided with an advance command output function, which can determine the camera in front of the edge truck according to the lane of the edge truck and send the acquisition command to the corresponding camera. It is convenient for the camera to prepare and focus for edge vehicle image acquisition and improve the coordination of work between cameras. The interactive management module predicts the position of the camera that needs to participate in image acquisition on the path ahead by reading the position information of the lane where the edge truck is currently located. The system calculates the distance between the edge truck and the adjacent camera in real time, and sends the acquisition command to the target camera in advance according to the position of the camera in the direction of the truck. In this way, the camera can complete the preparation of image acquisition before the edge truck arrives, including focusing on the corresponding lane, setting appropriate exposure and aperture parameters, etc. The advance command output function effectively improves the coordination of work between the cameras, so that the system can efficiently obtain high-quality images that meet the requirements, thereby improving the accuracy and timeliness of edge truck image acquisition. Of course, in the implementation, if there are multiple routes in front of the truck, there should also be multiple cameras in front, and acquisition commands should be sent to multiple cameras at the same time.

[0056] In order to reduce computing power consumption, the adaptive correction module corrects the current edge interval [Kmin, Kmax) at a preset period. Kmax reaches the overload threshold. For different vehicle models and axle numbers, it can be directly obtained when the previous detection data is obtained. The correction process includes:

[0057] Step S1, obtaining the total number of marginal trucks verified within a preset period;

[0058] Step S2, obtaining the number of marginal trucks verified to be overloaded or over-limit;

[0059] Step S3, determining the proportion P of marginal trucks verified as overloaded and over-limit based on the total number of marginal trucks verified within a preset period;

[0060] Step S4, compare the quantity proportion P with the preset ratio. If the two are the same or the quantity proportion P is greater than the preset ratio, maintain the current edge interval. If the quantity proportion P is less than the preset ratio, increase Kmin.

[0061] Among them, when the quantity proportion P is less than the preset ratio, the adjustment amount for Kmin is inversely proportional to the quantity proportion P. Optionally, the preset period is one week and the preset ratio is 75%. The purpose of the above correction is to reduce computing power consumption and avoid useless feature analysis for too many vehicles. Of course, in implementation, the preset period and preset ratio can be adaptively adjusted in combination with actual scenarios.

[0062] In this embodiment, the verification module is a number of existing detection points for detecting overload and overrun. In addition to the verification module, the modules involved in the embodiments described in this application can be implemented by software or hardware. The modules described can also be set in the processor.

[0063] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the device, method and computer program product according to various embodiments of the present application. In this regard, each 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 alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two 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 box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0064] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. An adaptive management system for overload and overlimit of urban freight, characterized in that: include: The acquisition module is used to obtain the previous detection data of overload and overlimit of the truck, as well as the image of the previous detection; A marking module, connected to the acquisition module, for marking marginal trucks approaching overload or overrun according to previous detection data and corresponding marginal intervals; An interactive management module, connected to the marking module, for acquiring an image of a moving edge truck; a feature recognition module, connected to the interaction management module, for recognizing the load change feature and size change feature of the marginal truck according to the image of the marginal truck; A verification module, connected to the feature recognition module, for verifying whether the marginal truck with the load change feature or the size change feature is overloaded or out of limit; The adaptive correction module is connected to the marking module and the verification module respectively, and is used to correct the edge interval corresponding to the detection data according to the proportion of the number of edge trucks verified to be overloaded and over-limit.

2. The adaptive management system for overload and overlimit of urban freight according to claim 1 is characterized in that: The load change feature is that the contact area between the tire and the ground in the image of the edge truck increases compared with the previous detection, or the distance between the tire and the vehicle body decreases compared with the previous detection.

3. The adaptive management system for overload and overlimit of urban freight according to claim 2 is characterized in that: The size change feature is that the height, length or width of the entire truck in the image of the edge truck increases compared with the previous detection.

4. The adaptive management system for overload and overlimit of urban freight according to claim 1 is characterized in that: The feature recognition module also includes a fluctuation detection unit, which determines the vibration state of the out-of-range cargo and the vibration state of the vehicle body in response to the size fluctuation characteristics of the marginal truck, and determines that the cargo state of the marginal truck is faulty in response to the inconsistency of the vibration states of the two, and outputs an alarm message to the marginal truck.

5. The adaptive management system for overload and overlimit of urban freight according to claim 4 is characterized in that: The fluctuation detection unit determines the vibration state of the cargo and the vibration state of the vehicle body by an optical flow method.

6. The adaptive management system for overload and overlimit of urban freight according to claim 1 is characterized in that: The marking module marks a truck whose detection data is in a corresponding marginal interval as a marginal truck, and the corresponding marking action is to store the license plate number of the marginal truck and upload it to the interaction management module.

7. The adaptive management system for overload and overlimit of urban freight according to claim 6 is characterized in that: The interaction management module includes: A storage unit, used to store the license plate number of the marginal truck; A license plate recognition unit is used to recognize the license plate number of the truck collected by the camera; The traversal unit is used to traverse and compare the license plate numbers of trucks and the license plate numbers of marginal trucks to filter out marginal truck images.

8. The adaptive management system for overload and overlimit of urban freight according to claim 7 is characterized in that: The interaction management module is also used to determine the camera in front of the edge truck according to the lane of the edge truck, and send a collection instruction to the corresponding camera.

9. The adaptive management system for overload and overlimit of urban freight according to claim 8 is characterized in that: The adaptive correction module adjusts the current edge interval [K min , K max ) to be amended, including: Get the total number of marginal trucks that are verified within a preset period; Get the number of marginal trucks verified as overloaded and over-limit; Determine the proportion P of marginal trucks verified as overloaded and over-limit based on the total number of marginal trucks verified within the preset period; The quantity proportion P is compared with the preset ratio. If the two are the same or the quantity proportion P is greater than the preset ratio, the current edge interval is maintained. If the quantity proportion P is less than the preset ratio, K min Adjust up; Among them, when the quantity proportion P is less than the preset ratio, for K min The adjustment amount is inversely proportional to the quantity proportion P.

10. The adaptive management system for overload and overlimit of urban freight according to claim 9, characterized in that: The preset period is one week, and the preset ratio is 75%.

Images