High-speed freight overload and overrun automatic detection system based on intelligent perception

Abstract

The invention relates to the technical field of vehicle overload detection, in particular to a high-speed freight overload and overrun automatic detection system based on intelligent perception, which obtains the load of each axle and obtains a truck image through a perception module, judges whether a truck is overloaded or overrun through a category division module, and divides truck overrun tendency categories. Through the detection and analysis module, a load fluctuation value is calculated and combined with a truck over-limit difference value to calculate an early warning characterization parameter, whether an over-limit early warning signal is sent out or not is judged according to the early warning characterization parameter, or a truck over-limit parameter change value is obtained according to a truck image, whether the over-limit early warning signal is sent out or not is judged, and a signal sending unit sends out the early warning signal. According to the invention, while the detection reliability is ensured, the detection efficiency is improved, the detection cost is reduced, the over-limit condition is prevented, and the safety of the road is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle overload detection, and in particular to an automatic detection system for high-speed freight overload and over-limit based on intelligent perception. Background Art

[0002] Truck overload and over-limit detection is crucial to ensure road traffic safety, maintain road infrastructure and improve transportation efficiency. 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] The prior art discloses a rapid detection system for overloaded freight vehicles based on a Zigbee network, including a truck terminal, a mobile law enforcement terminal, a fixed law enforcement terminal and a remote monitoring center; the truck terminal includes a truck terminal microprocessor, a weight detection unit, a vehicle information storage module and a truck terminal human-machine interface; the mobile law enforcement terminal includes a mobile law enforcement terminal microprocessor, a mobile terminal GPS module, a mobile video capture module, a remote communication module and a mobile law enforcement terminal human-machine interface; the fixed law enforcement terminal includes a fixed law enforcement terminal microprocessor, a current road section overload information storage unit, a fixed terminal GPS module, a fixed video capture module and a remote communication module; the remote monitoring center includes a database server and a remote communication module. The system can not only provide overloaded and overloaded reminders to the driver of the freight vehicle, but also perform load weight inspection and illegal evidence collection without interfering with the normal driving of the freight vehicle. However, the prior art does not consider the classification of overload risk tendency of trucks, and does not consider pre-interference in the overload situation of trucks, which leads to low detection efficiency and high detection cost for overloaded and overloaded trucks, and cannot more effectively improve road safety.

[0004] Therefore, there is an urgent need for an automatic high-speed freight overload and over-limit detection system based on intelligent perception that can classify truck over-limit tendency categories according to truck types and truck images, and take into account changes in the truck state during driving. It can improve detection efficiency and reduce detection costs while ensuring detection reliability, and prevent over-limit situations, thereby improving road safety. Summary of the invention

[0005] The purpose of the present invention is to provide an automatic detection system for high-speed freight overload and overlimit based on intelligent perception, which divides the overlimit tendency categories of trucks according to the truck type and the truck image, and takes into account the changes in the state of the truck during the driving of the truck. It can improve the detection efficiency and reduce the detection cost while ensuring the detection reliability, and prevent overlimit situations, thereby improving road safety.

[0006] The present invention provides an automatic detection system for high-speed freight overload and over-limit based on intelligent perception, and the automatic detection system for high-speed freight overload and over-limit based on intelligent perception comprises:

[0007] A perception module, comprising a weighing detection unit arranged on each axle of the truck for obtaining the load of each axle and an image acquisition unit for obtaining an image of the truck;

[0008] A classification module, connected to the perception module, is used to determine whether the truck is overloaded or over-limited based on the load of each axle and the truck image, and to classify the truck over-limited tendency category based on the truck type and the truck image;

[0009] A detection and analysis module, connected to each of the perception modules and the classification module, including a strategy selection unit and a signal sending unit;

[0010] The strategy selection unit is used to select a detection strategy according to the over-limit tendency category, including:

[0011] Calculate the load fluctuation value based on the load of each axle and calculate the warning characterization parameter in combination with the truck overrun difference value, wherein the truck overrun difference value includes the difference between the truck length and a preset truck length comparison threshold, the difference between the truck width and a preset truck width comparison threshold, and the difference between the truck height and a preset truck height comparison threshold, and determine whether to issue an overrun warning signal based on the warning characterization parameter;

[0012] Or, obtaining the change value of the over-limit parameters of the truck according to the truck image, wherein the over-limit parameters of the truck include the length, width and height of the truck, and determining whether to issue an over-limit warning signal;

[0013] The signal issuing unit is used to issue a warning signal.

[0014] The classification module determines whether the truck is overloaded or over-limited based on the load of each axle and the truck image.

[0015] Obtain the load of each axle and calculate the total weight of the truck based on the load of each axle;

[0016] Compare the gross weight of the truck with the preset truck overload comparison threshold,

[0017] If the total weight of the truck is greater than the preset truck overload comparison threshold, the truck is determined to be overloaded;

[0018] Get the truck image, extract the truck outline image, and get the length, width and height of the truck based on the truck outline image.

[0019] The length, width and height of the truck are compared with the preset truck length comparison threshold, the preset truck width comparison threshold and the preset truck height comparison threshold respectively.

[0020] If the first preset condition is met, it is determined that the truck is overloaded;

[0021] The first preset condition is that the length of the truck is greater than a preset truck length comparison threshold, or the width of the truck is greater than a preset truck width comparison threshold, or the height of the truck is greater than a preset truck height comparison threshold.

[0022] The classification module classifies trucks into overload tendency categories according to the truck type and the truck image.

[0023] According to the truck image, the truck type is divided into closed truck and non-closed truck.

[0024] The length, width and height of the truck are compared with the preset warning truck length comparison threshold, the preset warning truck width comparison threshold and the preset warning truck height comparison threshold respectively.

[0025] If the second preset condition is met, the truck overload tendency category is classified as a high warning overload category;

[0026] If the second preset condition is not met, the truck overload tendency category is classified as a low warning overload category;

[0027] The second preset condition is that the truck type is a non-enclosed truck and the length of the truck is greater than the preset warning truck length comparison threshold, or the truck type is a non-enclosed truck and the width of the truck is greater than the preset warning truck width comparison threshold, or the truck type is a non-enclosed truck and the height of the truck is greater than the preset warning truck height comparison threshold.

[0028] The strategy selection unit is used to select a detection strategy according to the over-limit tendency category, wherein:

[0029] If the overload tendency category of the truck is a high warning overload category, the load fluctuation value is calculated according to the load of each axle and the warning characterization parameter is calculated in combination with the overload difference of the truck. The overload difference of the truck includes the difference between the length of the truck and the preset truck length comparison threshold, the difference between the width of the truck and the preset truck width comparison threshold, and the difference between the height of the truck and the preset truck height comparison threshold. It is determined whether to issue an overload warning signal according to the warning characterization parameter;

[0030] If the truck overload tendency category is a low warning overload category, the truck overload parameter change value is obtained based on the truck image, and the truck overload parameters include the truck length, truck width and truck height, to determine whether to issue an overload warning signal.

[0031] The strategy selection unit calculates the load fluctuation value according to the load of each axle.

[0032] Obtain the load of each axle at a preset time interval;

[0033] Calculate the difference between the maximum and minimum loads on each axle;

[0034] Select the maximum difference as the load fluctuation value.

[0035] The strategy selection unit calculates the warning characteristic parameter according to formula (1):

[0036]

[0037] In formula (1), D represents the warning characterization parameter, B represents the load fluctuation value, B0 represents the preset load fluctuation value threshold, Lc represents the truck length excess difference value, Lc0 represents the preset truck length excess difference value threshold, Hc represents the truck height excess difference value, Hc0 represents the preset truck height excess difference value threshold, Wc represents the truck width excess difference value, and Wc0 represents the preset truck width excess difference value threshold.

[0038] The strategy selection unit determines whether to issue an over-limit warning signal according to the warning characteristic parameter.

[0039] Compare the warning characteristic parameter with the preset warning characteristic parameter comparison threshold,

[0040] If the warning characteristic parameter is greater than the preset warning characteristic parameter comparison threshold, it is determined that an over-limit warning signal is issued.

[0041] The strategy selection unit obtains the truck overrun parameter change value according to the truck image,

[0042] Extract two adjacent truck images;

[0043] The difference in the length of the truck in the truck outer contour image is the truck length change value, the difference in the width of the truck in the truck outer contour image is the truck width change value, and the difference in the height of the truck in the truck outer contour image is the truck height change value.

[0044] The strategy selection unit obtains the change value of the truck overload parameter according to the truck image and determines whether to issue an overload warning signal.

[0045] The truck length change value is compared with the preset truck length change value comparison threshold, the truck height change value is compared with the preset truck height change value comparison threshold, and the truck width change value is compared with the preset truck width change value comparison threshold.

[0046] If the third preset condition is met, it is determined that an over-limit warning signal is issued;

[0047] The third preset condition is that the change value of the truck length is greater than the preset truck length change value comparison threshold, or the change value of the truck width is greater than the preset truck width change value comparison threshold, or the change value of the truck height is greater than the preset truck height change value comparison threshold.

[0048] The signal issuing unit obtains the judgment results of the category classification module and the strategy selection unit, and issues an overload signal, an over-limit signal, or an early warning signal.

[0049] The beneficial effects of the present invention are:

[0050] The present invention provides an automatic detection system for high-speed freight overload and overlimit based on intelligent perception. The automatic detection system for high-speed freight overload and overlimit based on intelligent perception divides truck overlimit tendency categories according to truck types combined with truck images, and takes into account changes in the state of the truck during the driving of the truck. While ensuring detection reliability, it can improve detection efficiency, reduce detection costs, prevent overlimit situations, and improve road safety.

[0051] Furthermore, the category classification module of the present invention classifies truck overloading tendency categories according to truck type and truck image. In actual situations, there are fixed restrictions on the length, width and height of closed trucks, while there are no fixed restrictions on the length, width or height of non-closed trucks, which leads to the situation that the goods in non-closed trucks easily exceed the original length or height of the truck. The current situation of the truck can be obtained by identifying the length, width and height of the truck through the truck image. If the current length, width and height of the truck are already close to the over-limit value, it is more likely to overload. By classifying the truck overloading tendency categories, different detection strategies can be adopted for trucks with different overloading tendencies, thereby improving detection efficiency and reducing detection costs while ensuring detection reliability.

[0052] Furthermore, the strategy selection unit of the present invention calculates the load fluctuation value based on the load of each axle and calculates the warning characterization parameter in combination with the over-limit difference of the truck. During the operation of the truck, the cargo loaded on the truck may shift or shake. When the cargo shifts or shakes, the loads of each axle obtained will also change to a certain extent. When the over-limit difference of the truck is small, the truck is more likely to exceed the limit. If the cargo loaded on the truck also shifts or shakes to a certain extent, the length or width of the truck may exceed the limit. By calculating the warning characterization parameters, trucks that are more prone to over-limit situations can be obtained. Warning signals can be issued by such trucks, thereby preventing over-limit situations and improving road safety.

[0053] Furthermore, the strategy selection unit of the present invention obtains the change value of the truck's over-limit parameter based on the truck image to determine whether to issue an over-limit warning signal. For trucks in the low-warning over-limit category, over-limit situations are less likely to occur. By obtaining the change value of the truck's over-limit parameter, changes in the truck's state during the truck's driving process can be obtained. When the change value of the truck's over-limit parameter is large, the truck's state has changed significantly during the truck's driving process. Even if the truck is less likely to over-limit, a warning signal should be issued for the truck, thereby preventing over-limit situations and improving road safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a system structure diagram of a high-speed freight overload and over-limit automatic detection system based on intelligent perception in an embodiment of the present invention;

[0055] Figure 2 This is a structural diagram of the detection and analysis module in an embodiment of the present invention;

[0056] Figure 3 A logical decision diagram for classifying truck overload tendency categories by a category classification module in an embodiment of the present invention;

[0057] Figure 4 This is a logic decision diagram of whether to issue an over-limit warning signal according to the warning characteristic parameter by the strategy selection unit in the embodiment of the present invention. DETAILED DESCRIPTION

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] See also Figure 1-Figure 2 As shown, the system structure diagram of the high-speed freight overload and over-limit automatic detection system based on intelligent perception in an embodiment of the present invention, Figure 2 : is a structural diagram of the detection and analysis module in an embodiment of the present invention. This embodiment provides a high-speed freight overload and over-limit automatic detection system based on intelligent perception. The high-speed freight overload and over-limit automatic detection system based on intelligent perception includes:

[0063] A perception module, comprising a weighing detection unit arranged on each axle of the truck for obtaining the load of each axle and an image acquisition unit for obtaining an image of the truck;

[0064] A classification module, connected to the perception module, is used to determine whether the truck is overloaded or over-limited based on the load of each axle and the truck image, and to classify the truck over-limited tendency category based on the truck type and the truck image;

[0065] A detection and analysis module, connected to each of the perception modules and the classification module, including a strategy selection unit and a signal sending unit;

[0066] The strategy selection unit is used to select a detection strategy according to the over-limit tendency category, including:

[0067] Calculate the load fluctuation value based on the load of each axle and calculate the warning characterization parameter in combination with the truck overrun difference value, wherein the truck overrun difference value includes the difference between the truck length and a preset truck length comparison threshold, the difference between the truck width and a preset truck width comparison threshold, and the difference between the truck height and a preset truck height comparison threshold, and determine whether to issue an overrun warning signal based on the warning characterization parameter;

[0068] Or, obtaining the change value of the over-limit parameters of the truck according to the truck image, wherein the over-limit parameters of the truck include the length, width and height of the truck, and determining whether to issue an over-limit warning signal;

[0069] The signal issuing unit is used to issue a warning signal.

[0070] Specifically, the present invention does not limit the specific structure of the perception module. The weighing detection unit may be a weighing sensor, and the image acquisition unit may be a camera arranged on the highway.

[0071] Specifically, the present invention does not limit the specific structure of the category classification module and the detection and analysis module, which can be composed of logical components or a combination of logical components. The logical components include a field programmable processor, a computer or a microprocessor in a computer. This is a prior art and will not be repeated here.

[0072] Specifically, the classification module determines whether the truck is overloaded or over-limited based on the load of each axle and the truck image.

[0073] Obtain the load of each axle and calculate the total weight of the truck based on the load of each axle;

[0074] Compare the gross weight of the truck with the preset truck overload comparison threshold,

[0075] If the total weight of the truck is greater than the preset truck overload comparison threshold, the truck is determined to be overloaded;

[0076] Get the truck image, extract the truck outline image, and get the length, width and height of the truck based on the truck outline image.

[0077] The length, width and height of the truck are compared with the preset truck length comparison threshold L0, the preset truck width comparison threshold W0, and the preset truck height comparison threshold H0 respectively.

[0078] If the first preset condition is met, it is determined that the truck is overloaded;

[0079] The first preset condition is that the length of the truck is greater than a preset truck length comparison threshold, or the width of the truck is greater than a preset truck width comparison threshold, or the height of the truck is greater than a preset truck height comparison threshold.

[0080] In this embodiment, the truck outer contour image is recognized based on the truck image by using image recognition software, and the length, width and height of the truck are extracted based on the truck outer contour image. The image recognition software may be matlab.

[0081] In this embodiment, the database stores various types of truck data and road information data. The preset truck overload comparison threshold is the sum of the maximum load capacity of the corresponding truck selected based on the truck image and the corresponding truck's own weight. The preset truck length comparison threshold, the preset truck width comparison threshold and the preset truck height comparison threshold are the truck length, truck width and truck height specified for the corresponding truck on the road selected based on the truck image.

[0082] See also Figure 3 Specifically, the classification module classifies trucks into overload tendency categories according to truck types and truck images.

[0083] According to the truck image, the truck type is divided into closed truck and non-closed truck.

[0084] The length, width and height of the truck are compared with the preset warning truck length comparison threshold, the preset warning truck width comparison threshold and the preset warning truck height comparison threshold respectively.

[0085] If the second preset condition is met, the truck overload tendency category is classified as a high warning overload category;

[0086] If the second preset condition is not met, the truck overload tendency category is classified as a low warning overload category;

[0087] The second preset condition is that the truck type is a non-enclosed truck and the length of the truck is greater than the preset warning truck length comparison threshold, or the truck type is a non-enclosed truck and the width of the truck is greater than the preset warning truck width comparison threshold, or the truck type is a non-enclosed truck and the height of the truck is greater than the preset warning truck height comparison threshold.

[0088] In this embodiment, trucks with fixed restrictions on the length, width and height of the vehicle are classified as closed trucks, such as vans. For vans, since their length, width and height are restricted, the cargo usually does not exceed the box body, so it is not easy to exceed the limit. Trucks with no fixed restrictions on the length, width or height of the vehicle are classified as non-closed trucks, such as panel trucks. The cargo may exceed the original height or length of the vehicle, and there may be a greater risk of overloading.

[0089] In this embodiment, the truck images are classified into closed trucks and non-closed trucks by image recognition software, and the image recognition software may be matlab.

[0090] In this embodiment, the preset warning truck length comparison threshold Ly0=a×L0, a is the length warning coefficient, 0.7<a<0.9, the preset warning truck width comparison threshold Wy0=b×W0, b is the width warning coefficient, 0.7<b<0.9, and the preset warning truck height comparison threshold Hy0=c×H0, c is the height warning coefficient, 0.7<c<0.9.

[0091] Specifically, the category classification module of the present invention classifies trucks into over-limit tendency categories according to the truck type and the truck image. In actual situations, there are fixed restrictions on the length, width and height of closed trucks, while there are no fixed restrictions on the length, width or height of non-closed trucks, which leads to the situation that the goods in non-closed trucks easily exceed the original length or height of the truck. The current situation of the truck can be obtained by identifying the length, width and height of the truck through the truck image. If the current length, width and height of the truck are already close to the over-limit value, it is more likely to over-limit. By classifying the truck over-limit tendency categories, different detection strategies can be adopted for trucks with different over-limit tendencies, thereby improving detection efficiency and reducing detection costs while ensuring detection reliability.

[0092] Specifically, the strategy selection unit is used to select a detection strategy according to the over-limit tendency category, wherein:

[0093] If the overload tendency category of the truck is a high warning overload category, the load fluctuation value is calculated according to the load of each axle and the warning characterization parameter is calculated in combination with the overload difference of the truck. The overload difference of the truck includes the difference between the length of the truck and the preset truck length comparison threshold, the difference between the width of the truck and the preset truck width comparison threshold, and the difference between the height of the truck and the preset truck height comparison threshold. It is determined whether to issue an overload warning signal according to the warning characterization parameter;

[0094] If the truck overload tendency category is a low warning overload category, the truck overload parameter change value is obtained based on the truck image, and the truck overload parameters include the truck length, truck width and truck height, to determine whether to issue an overload warning signal.

[0095] Specifically, the strategy selection unit calculates the load fluctuation value according to the load of each axle.

[0096] Obtain the load of each axle at a preset time interval;

[0097] Calculate the difference between the maximum and minimum loads on each axle;

[0098] Select the maximum difference as the load fluctuation value.

[0099] In this embodiment, the preset time is selected within the range of [5min, 10min].

[0100] It can be understood that the load of each axle is obtained at preset time intervals, the maximum value and the minimum value are obtained from the load data of the same axle obtained at different times, and the difference is calculated.

[0101] Specifically, the strategy selection unit calculates the warning characteristic parameter according to formula (1):

[0102]

[0103] In formula (1), D represents the warning characterization parameter, B represents the load fluctuation value, B0 represents the preset load fluctuation value threshold, Lc represents the truck length excess difference value, Lc0 represents the preset truck length excess difference value threshold, Hc represents the truck height excess difference value, Hc0 represents the preset truck height excess difference value threshold, Wc represents the truck width excess difference value, and Wc0 represents the preset truck width excess difference value threshold.

[0104] In this embodiment, the preset load fluctuation value threshold B0=d×F, d is the axle load coefficient, F is the axle load corresponding to the selected maximum difference, 0.05<d<0.15, Lc0=e×L0, e is the length excess difference coefficient, 0.05<e<0.15, Wc0=f×W0, f is the width excess difference coefficient, 0.05<f<0.15, Hc0=g×H0, g is the height excess difference coefficient, 0.05<g<0.15.

[0105] Specifically, the strategy selection unit of the present invention calculates the load fluctuation value based on the load of each axle and calculates the warning characterization parameter in combination with the over-limit difference of the truck. During the operation of the truck, the cargo loaded on the truck may shift or shake. When the cargo shifts or shakes, the loads of each axle obtained will also change to a certain extent. When the over-limit difference of the truck is small, the truck is more likely to exceed the limit. If the cargo loaded on the truck also shifts or shakes to a certain extent, the length or width of the truck may exceed the limit. By calculating the warning characterization parameters, trucks that are more prone to over-limit situations can be obtained. Warning signals can be issued by such trucks, thereby preventing over-limit situations and improving road safety.

[0106] Please follow Figure 4 Specifically, the strategy selection unit determines whether to issue an over-limit warning signal according to the warning characteristic parameter.

[0107] Compare the warning characteristic parameter with the preset warning characteristic parameter comparison threshold,

[0108] If the warning characteristic parameter is greater than the preset warning characteristic parameter comparison threshold, it is determined that an over-limit warning signal is issued.

[0109] In this embodiment, the preset warning characterization parameter comparison threshold is selected within the range of [1.82, 1.90].

[0110] Specifically, the strategy selection unit obtains the truck overload parameter change value according to the truck image.

[0111] Extract two adjacent truck images;

[0112] The difference in the length of the truck in the truck outer contour image is the truck length change value, the difference in the width of the truck in the truck outer contour image is the truck width change value, and the difference in the height of the truck in the truck outer contour image is the truck height change value.

[0113] In this embodiment, two adjacent truck images are truck images obtained by adjacent image acquisition units during the driving process of the truck.

[0114] Specifically, the strategy selection unit obtains the change value of the truck overload parameter according to the truck image to determine whether to issue an overload warning signal.

[0115] The truck length change value is compared with the preset truck length change value comparison threshold, the truck height change value is compared with the preset truck height change value comparison threshold, and the truck width change value is compared with the preset truck width change value comparison threshold.

[0116] If the third preset condition is met, it is determined that an over-limit warning signal is issued;

[0117] The third preset condition is that the change in truck length is greater than the preset truck length change comparison threshold Lb0, or the change in truck width is greater than the preset truck width change comparison threshold Wb0, or the change in truck height is greater than the preset truck height change comparison threshold Hb0.

[0118] In this embodiment, Lb0=h×L0, h is the length change coefficient, 0.05<h<0.1, Wb0=j×W0, j is the width change coefficient, 0.05<j<0.1, Hb0=g×H0, g is the height change coefficient, 0.05<g<0.1.

[0119] Specifically, the strategy selection unit of the present invention obtains the change value of the truck's over-limit parameter based on the truck image to determine whether to issue an over-limit warning signal. For trucks in the low-warning over-limit category, it is less likely to over-limit. By obtaining the change value of the truck's over-limit parameter, the change in the truck's state during the truck's driving process can be obtained. When the change value of the truck's over-limit parameter is large, the truck's state has changed significantly during the truck's driving process. Even if the truck is less likely to over-limit, a warning signal should be issued for the truck, thereby preventing over-limit situations and improving road safety.

[0120] Specifically, the signal issuing unit obtains the determination results of the category classification module and the strategy selection unit, and issues an overload signal, an over-limit signal, or an early warning signal.

[0121] 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.

[0122] 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 automatic detection system for high-speed freight overload and over-limit based on intelligent perception, characterized in that: include: A perception module, comprising a weighing detection unit arranged on each axle of the truck for obtaining the load of each axle and an image acquisition unit for obtaining an image of the truck; A classification module, connected to the perception module, is used to determine whether the truck is overloaded or over-limited based on the load of each axle and the truck image, and to classify the truck over-limited tendency category based on the truck type and the truck image; A detection and analysis module, connected to each of the perception modules and the classification module, including a strategy selection unit and a signal sending unit; The strategy selection unit is used to select a detection strategy according to the over-limit tendency category, including: Calculate the load fluctuation value based on the load of each axle and calculate the warning characterization parameter in combination with the truck overrun difference value, wherein the truck overrun difference value includes the difference between the truck length and a preset truck length comparison threshold, the difference between the truck width and a preset truck width comparison threshold, and the difference between the truck height and a preset truck height comparison threshold, and determine whether to issue an overrun warning signal based on the warning characterization parameter; Or, obtaining the change value of the over-limit parameters of the truck according to the truck image, wherein the over-limit parameters of the truck include the length, width and height of the truck, and determining whether to issue an over-limit warning signal; The signal issuing unit is used to issue a warning signal.

2. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 1 is characterized in that: The classification module determines whether the truck is overloaded or over-limited based on the load of each axle and the truck image. Obtain the load of each axle and calculate the total weight of the truck based on the load of each axle; Compare the gross weight of the truck with the preset truck overload comparison threshold, If the total weight of the truck is greater than the preset truck overload comparison threshold, the truck is determined to be overloaded; Get the truck image, extract the truck outline image, and get the length, width and height of the truck based on the truck outline image. The length, width and height of the truck are compared with the preset truck length comparison threshold, the preset truck width comparison threshold and the preset truck height comparison threshold respectively. If the first preset condition is met, it is determined that the truck is overloaded; The first preset condition is that the length of the truck is greater than a preset truck length comparison threshold, or the width of the truck is greater than a preset truck width comparison threshold, or the height of the truck is greater than a preset truck height comparison threshold.

3. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 1 is characterized in that: The classification module classifies trucks into overload tendency categories according to the truck type and the truck image. According to the truck image, the truck type is divided into closed truck and non-closed truck. The length, width and height of the truck are compared with the preset warning truck length comparison threshold, the preset warning truck width comparison threshold and the preset warning truck height comparison threshold respectively. If the second preset condition is met, the truck overload tendency category is classified as a high warning overload category; If the second preset condition is not met, the truck overload tendency category is classified as a low warning overload category; The second preset condition is that the truck type is a non-enclosed truck and the length of the truck is greater than the preset warning truck length comparison threshold, or the truck type is a non-enclosed truck and the width of the truck is greater than the preset warning truck width comparison threshold, or the truck type is a non-enclosed truck and the height of the truck is greater than the preset warning truck height comparison threshold.

4. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 3 is characterized in that: The strategy selection unit is used to select a detection strategy according to the over-limit tendency category, wherein: If the overload tendency category of the truck is a high warning overload category, the load fluctuation value is calculated according to the load of each axle and the warning characterization parameter is calculated in combination with the overload difference of the truck. The overload difference of the truck includes the difference between the length of the truck and the preset truck length comparison threshold, the difference between the width of the truck and the preset truck width comparison threshold, and the difference between the height of the truck and the preset truck height comparison threshold. It is determined whether to issue an overload warning signal according to the warning characterization parameter; If the truck overload tendency category is a low warning overload category, the truck overload parameter change value is obtained based on the truck image, and the truck overload parameters include the truck length, truck width and truck height, to determine whether to issue an overload warning signal.

5. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 1 is characterized in that: The strategy selection unit calculates the load fluctuation value according to the load of each axle. Obtain the load of each axle at a preset time interval; Calculate the difference between the maximum and minimum loads on each axle; Select the maximum difference as the load fluctuation value.

6. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 5 is characterized in that: The strategy selection unit calculates the warning characteristic parameter according to formula (1): In formula (1), D represents the warning characterization parameter, B represents the load fluctuation value, B0 represents the preset load fluctuation value threshold, Lc represents the truck length excess difference value, Lc0 represents the preset truck length excess difference value threshold, Hc represents the truck height excess difference value, Hc0 represents the preset truck height excess difference value threshold, Wc represents the truck width excess difference value, and Wc0 represents the preset truck width excess difference value threshold.

7. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 6 is characterized in that: The strategy selection unit determines whether to issue an over-limit warning signal according to the warning characteristic parameter. Compare the warning characteristic parameter with the preset warning characteristic parameter comparison threshold, If the warning characteristic parameter is greater than the preset warning characteristic parameter comparison threshold, it is determined that an over-limit warning signal is issued.

8. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 1 is characterized in that: The strategy selection unit obtains the truck overrun parameter change value according to the truck image, Extract two adjacent truck images; The difference in the length of the truck in the truck outer contour image is the truck length change value, the difference in the width of the truck in the truck outer contour image is the truck width change value, and the difference in the height of the truck in the truck outer contour image is the truck height change value.

9. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 8 is characterized in that: The strategy selection unit obtains the change value of the truck overload parameter according to the truck image and determines whether to issue an overload warning signal. The truck length change value is compared with the preset truck length change value comparison threshold, the truck height change value is compared with the preset truck height change value comparison threshold, and the truck width change value is compared with the preset truck width change value comparison threshold. If the third preset condition is met, it is determined that an over-limit warning signal is issued; The third preset condition is that the change value of the truck length is greater than the preset truck length change value comparison threshold, or the change value of the truck width is greater than the preset truck width change value comparison threshold, or the change value of the truck height is greater than the preset truck height change value comparison threshold.

10. The high-speed freight overload and over-limit automatic detection system based on intelligent perception according to claim 1 is characterized in that: The signal issuing unit obtains the judgment results of the category classification module and the strategy selection unit, and issues an overload signal, an over-limit signal, or an early warning signal.

Images