Method and device for detecting empty-to-full loading of car hopper and medium

Abstract

The invention discloses a method and device for detecting empty-to-full loading of a car hopper and a medium, and relates to the technical field of loading detection, and the method comprises the steps: carrying out the numbering and recognition of vehicles for loading based on a computer vision model and a character recognition model, based on data collected by the magnetic sensor and the acceleration sensor, material stealing identification is carried out by using a material stealing identification method; acquiring position data of the charging vehicle in real time based on a road network system, and filtering abnormal alarms by using a driving filtering method when the charging vehicle runs; the method and the device are used for solving the problems that in the existing improvement in the aspect of car hopper loading detection, when loading and hidden danger of material stealing exist, whether the material stealing behavior exists or not cannot be effectively judged, so that the material stealing behavior cannot be effectively detected and early warned during loading, and then goods missing is caused.

Description

Technical Field

[0001] The present invention relates to the technical field of loading detection, and in particular to a method, equipment and medium for detecting the transition from empty to full loading of a truck compartment. Background Art

[0002] Truck bed loading inspection mainly refers to the inspection of the weight and center of gravity position of the vehicle after loading to ensure that the loading meets safety standards and regulations; this inspection is of great significance for ensuring road traffic safety, preventing cargo overloading, and protecting vehicles and cargo from damage; Truck bed loading inspection includes: Weight inspection: Check the total weight of the vehicle after loading to ensure that it does not exceed the vehicle's design carrying capacity and the maximum allowable weight specified by road traffic regulations; Center of gravity position inspection: Determine the distribution of the loaded cargo in the truck bed to ensure that the center of gravity position of the cargo is within the range allowed by the vehicle design; Cargo distribution inspection: Check whether the cargo is evenly distributed in the truck bed.

[0003] The existing method for detecting loading in the truck bed usually uses a camera to shoot the load in the truck bed, and uses edge recognition and other algorithms to process the captured image, so as to obtain the edge of the load and the edge of the loading space in the truck bed and compare them, so as to obtain the space where the load in the truck bed is located. Although this improved method can effectively obtain the position of the load in the truck bed during the detection of loading in the truck bed, when loading and there is a risk of stealing, it is impossible to effectively determine whether there is stealing behavior by only shooting in the truck bed, resulting in the inability to effectively detect and warn the stealing behavior during loading, which in turn causes problems such as missing goods. For example, in the patent application with publication number CN118202384A, Disclosed is a method for detecting a load, which determines the load space occupied by the load by comparing an identifiable edge of the load and its edge length with an edge of an unloaded load space and its edge length, or with an edge of a load space in a previously loaded state and its edge length. Other methods for detecting vehicle loading usually detect the loading of the vehicle while the vehicle is running, and are usually used to detect whether the loading is abnormal due to the cargo falling. However, this improved method still cannot effectively determine whether there is material theft when loading and there is a risk of material theft, resulting in an inability to effectively detect and warn of material theft during loading, which in turn causes problems such as cargo loss. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the prior art to a certain extent. By proposing a method, device and medium for detecting the change from empty to full loading of a truck bed, the present invention is used to solve the problem that the existing improvements for truck bed loading detection are unable to effectively determine whether there is material theft when loading and there is a risk of material theft, resulting in the inability to effectively detect and warn of material theft during loading, thereby causing problems such as missing goods.

[0005] To achieve the above objectives, in a first aspect, the present application provides a method for detecting whether a truck compartment is empty or fully loaded, comprising the following steps: The vehicles used for loading are numbered and identified based on the computer vision model and the text recognition model, and the numbers are ZL1 to ZL n , where n is the number of vehicles used for loading; A magnetic sensor is installed on the leaf spring of the vehicle, and an acceleration sensor is installed on the vehicle bucket. When the loading vehicle is loading, the stolen material identification method is used to identify the stolen material based on the data collected by the magnetic sensor and the acceleration sensor. When the stolen material is identified, the loading is stopped and an early warning report is issued based on the vehicle number. When the theft of materials is not identified, the loading detection method is used to perform loading detection on the vehicles that have completed loading, and the loading statistics are calculated based on the detection results; The location data of the loading vehicle is acquired in real time based on the road network system, and the driving filtering method is used to filter abnormal alarms when the loading vehicle is driving.

[0006] Furthermore, the stolen material identification method includes: For any vehicle numbered ZL used for loading n1 The vehicle will be ZL n1 The point where the material is loaded is recorded as the loading point; n1 Before loading, ZL the vehicle n1 Drive to the loading point and use the speed at which the vehicle is loaded to ZL n1 The bucket is loaded with materials. When loading starts, the pressure data of the magnetic sensor is obtained in real time, and a corresponding curve is drawn in the plane rectangular coordinate system; when loading is finished, the obtained curve is recorded as the loading pressure curve; When loading is completed, the acceleration sensor is activated to obtain the acceleration of the bucket when it is withdrawn in real time, and the acceleration of the bucket is measured at the vehicle ZL n1 After leaving the loading point, the acquisition stops, and the acceleration data recorded by the acceleration sensor at this time is plotted into a corresponding curve in the plane rectangular coordinate system, which is recorded as the drawer acceleration curve.

[0007] Furthermore, the stolen material identification method also includes: In vehicle ZL n1When loading, a plane rectangular coordinate system is established, which is recorded as the excavator stealing material detection coordinate system. The unit of the X axis of the excavator stealing material detection coordinate system is time, and the unit of the Y axis is Newton. n1 When driving to the loading point and starting to load, the pressure data of the magnetic sensor is obtained in real time, and a corresponding curve is drawn in the excavator stealing material detection coordinate system based on the pressure data, which is recorded as the real-time loading curve; the loading pressure curve is placed in the excavator stealing material detection coordinate system, wherein the leftmost point of the real-time loading curve and the loading pressure curve are both in the Y axis; Use a straight line parallel to the Y axis to divide the charging pressure curve into k parts, which are recorded as pressure sub-curves YZ1 to YZ k , for any pressure sub-curve YZ k1 , the pressure sub-curve YZ k1 The value of the highest point's ordinate minus the lowest point's ordinate is recorded as the pressure span, the maximum value of the pressure span in all pressure sub-curves YZ is recorded as the pressure audit value, and the pressure sub-curve YZ whose pressure span is the pressure audit value is recorded as the audit sub-curve SZ.

[0008] Furthermore, the stolen material identification method also includes: The value obtained by dividing the abscissa of the rightmost point of the charging pressure curve by k is recorded as q; n1 During the charging process, the rightmost point of the real-time charging curve is obtained and recorded as the real-time charging point (x0, y0), the point with the horizontal coordinate x0 minus q in the real-time charging curve is recorded as the left point of the interval, and the real-time charging curve between the left point of the interval and the real-time charging point is recorded as the real-time sub-curve SQ; When the horizontal coordinate of the real-time loading point coincides with the horizontal coordinate of the rightmost point of any audit sub-curve SZ, the value of the vertical coordinate of the highest point in the real-time sub-curve SQ minus the vertical coordinate of the lowest point is recorded as the real-time pressure span. When the real-time pressure span is equal to the pressure audit value, continue loading; when the real-time pressure span is not equal to the pressure audit value, stop loading and send vehicle ZL n1 Excavator stealing material alarm; When the horizontal coordinate of the real-time loading point does not coincide with the horizontal coordinate of the rightmost point of any audit sub-curve SZ and the real-time pressure span is equal to the pressure audit value, the loading is stopped and the vehicle ZL is issued. n1 Excavator stealing material alarm.

[0009] Furthermore, the stolen material identification method also includes: When the horizontal coordinate of the real-time loading point coincides with the horizontal coordinate of the rightmost point of the loading pressure curve and no excavator stealing alarm is issued, it is recorded as vehicle ZL n1 Loading completed; in vehicle ZL n1 Loading is complete and vehicle ZL n1When the speed is greater than or equal to 0, the acceleration sensor is started to obtain the acceleration of the bucket when it is withdrawn in real time, and n1 Stop acquiring after leaving the loading point, draw a corresponding curve in the plane rectangular coordinate system for the acceleration data recorded by the acceleration sensor at this time, and record it as the real-time acceleration curve; put the drawer acceleration curve and the real-time acceleration curve into the same plane rectangular coordinate system and overlap the rightmost point of the drawer acceleration curve with the real-time acceleration curve. For any point (x1, y1) in the real-time acceleration curve, mark the vertical coordinate of the point with the horizontal coordinate x1 in the drawer acceleration coordinate system as y2. When y1 is less than y2, the vehicle ZL is issued. n1 Drawer theft alarm.

[0010] Furthermore, the loading detection method includes: The computer vision model is used to record the behavior of flattening the soil pile with a bucket and record it as the leveling behavior; a camera is installed on the bucket of the vehicle, and after the vehicle is loaded, the cargo in the bucket is obtained. When the cargo is flat, the camera is started to shoot the inside of the bucket and the computer vision model is used to identify the captured content. When the vehicle ZL n1 When flattening is detected before leaving the loading point, it is recorded as passing the loading inspection; when flattening is still not detected after vehicle ZLn1 leaves the loading point, a warning of not flattening is issued, where flattened cargo refers to cargo that needs to be flattened with a bucket; When the loading vehicle is recorded as having passed the loading inspection, the vehicle number is obtained and the vehicle numbers that have passed the loading inspection are counted in the database.

[0011] Furthermore, the location data of the loading vehicle is obtained in real time based on the road network system, and the driving filtering method is used to filter abnormal alarms when the loading vehicle is driving, including: When there is a vehicle that has passed the loading inspection in the database, the vehicle number recorded in the database is identified based on the road network system, and the identified vehicle is recorded as a loading vehicle; The location data of the loading vehicle is obtained in real time based on the road network system. When the loading vehicle is in the main driving area, the driving filtering method is used to filter out abnormal alarms when the vehicle is driving.

[0012] Further, the driving filtering method includes: when the loading driving vehicle is in the main driving area, using the magnetic sensor to obtain pressure data in real time, when the pressure in the pressure data continues to decrease, establishing a plane rectangular coordinate system, recorded as a pressure analysis coordinate system, wherein the unit of the X-axis of the pressure analysis coordinate system is time, and the unit of the Y-axis is Newton; Based on the pressure data when the pressure starts to decrease in the pressure data, a curve is drawn in the pressure analysis coordinate system, which is recorded as the material stealing analysis curve, wherein the leftmost point of the material stealing analysis curve coincides with the Y axis and the vertical coordinate of the leftmost point of the material stealing analysis curve is marked as P; Let the straight line Y=P be the pressure measurement line. When the abscissa of the rightmost point of the theft analysis curve is q and the intersection of the theft analysis curve with the pressure measurement line is equal to 1, an alarm for theft of cargo is issued. When the abscissa of the rightmost point of the theft analysis curve is q and the intersection of the theft analysis curve with the pressure measurement line is greater than 1, no alarm is issued.

[0013] In a second aspect, the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are performed.

[0014] In a third aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are performed.

[0015] Beneficial effects of the present invention: the present invention firstly numbers and identifies vehicles used for loading based on a computer vision model and a text recognition model; then installs a magnetic sensor on a leaf spring of the vehicle, and installs an acceleration sensor on a vehicle bucket; when the loading vehicle is loading, a material theft identification method is used based on data collected by the magnetic sensor and the acceleration sensor to identify theft; the advantage of this is that by using the material theft identification method based on data collected by the magnetic sensor and the acceleration sensor to identify theft, the pressure data caused by the bucket during loading and the acceleration data when the bucket is moved out can be effectively obtained, thereby analyzing the real-time pressure data and acceleration data, and then effectively judging whether there is material theft during loading, and preventing the problem of missing goods due to material theft during loading; The present invention also obtains the position data of the loading vehicle in real time based on the road network system, and uses a driving filtering method to filter abnormal alarms when the loading vehicle is driving. The advantage of this is that by filtering abnormal alarms through the road network system, it is possible to prevent the alarm system from being triggered due to vehicle shaking and the like when the vehicle is driving normally, thereby preventing the abnormal alarm from hindering the normal driving of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the steps of the method of the present invention; Figure 2 It is a schematic diagram of obtaining the real-time sub-curve SQ of the present invention; Figure 3 It is a schematic diagram of the material stealing analysis curve of the present invention; Figure 4It is a schematic structural diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0018] Example 1, please refer to Figure 1 As shown, the present application provides a method for detecting whether a truck compartment is empty or fully loaded, characterized in that it comprises the following steps: Step S1: numbering and identifying vehicles used for loading based on computer vision model and text recognition model, and the numbering is ZL1 to ZL n , where n is the number of vehicles used for loading; In the specific implementation process, PaddleOCR can be selected as the text recognition model, and the YOLO model is used as the computer vision model. After the vehicles are numbered, the YOLO model is used to obtain the number to be recognized during identification, and then PaddleOCR is used for text recognition to achieve accurate identification of the vehicle. Step S2, installing a magnetic sensor on the leaf spring of the vehicle and an acceleration sensor on the bucket of the vehicle. When the loading vehicle is loading, the stolen material is identified using the stolen material identification method based on the data collected by the magnetic sensor and the acceleration sensor. When the stolen material is identified, the loading is stopped and an early warning is reported based on the vehicle number. The method for identifying stolen materials includes: step S201, for any vehicle numbered ZL in the vehicle used for loading materials n1 The vehicle will be ZL n1 The point where the material is loaded is recorded as the loading point; n1 Before loading, ZL the vehicle n1 Drive to the loading point and use the speed at which the vehicle is loaded to ZL n1 The cargo box of the vehicle is loaded with materials. When loading begins, the pressure data of the magnetic sensor is obtained in real time, and a corresponding curve is drawn in the plane rectangular coordinate system; when loading is finished, the obtained curve is recorded as the loading pressure curve; in the specific implementation process, the cargo loaded into the cargo box of the vehicle can be sand, gravel, plate materials, steel and other cargoes that can be transported by the cargo box; When loading is completed, the acceleration sensor is activated to obtain the acceleration of the bucket when it is withdrawn in real time, and the acceleration of the bucket is measured at the vehicle ZL. n1After leaving the loading point, stop acquiring, and draw a corresponding curve in the plane rectangular coordinate system with the acceleration data recorded by the acceleration sensor at this time, which is recorded as the bucket acceleration curve; in the specific implementation process, by acquiring the loading pressure curve and the bucket acceleration curve, the pressure change in the bucket when the vehicle ZL is loading and the acceleration change of the bucket when it is withdrawn can be obtained, which is helpful for accurate judgment in the subsequent theft detection; Step S202, in vehicle ZL n1 When loading, a plane rectangular coordinate system is established, which is recorded as the excavator stealing material detection coordinate system. The unit of the X axis of the excavator stealing material detection coordinate system is time, and the unit of the Y axis is Newton. n1 When driving to the loading point and starting to load, the pressure data of the magnetic sensor is obtained in real time, and a corresponding curve is drawn in the excavator stealing material detection coordinate system based on the pressure data, which is recorded as the real-time loading curve; the loading pressure curve is placed in the excavator stealing material detection coordinate system, wherein the leftmost point of the real-time loading curve and the loading pressure curve are both in the Y axis; Step S203: Use a straight line parallel to the Y axis to evenly divide the charging pressure curve into k parts, which are recorded as pressure sub-curves YZ1 to YZ2. k , for any pressure sub-curve YZ k1 , the pressure sub-curve YZ k1 The value of the highest point's ordinate minus the lowest point's ordinate is recorded as the pressure span, the maximum value of the pressure span in all pressure sub-curves YZ is recorded as the pressure audit value, and the pressure sub-curve YZ whose pressure span is the pressure audit value is recorded as the audit sub-curve SZ; In the specific implementation process, by obtaining the pressure audit value, the maximum pressure change that can be generated during the loading process can be obtained. When the actual pressure change exceeds the pressure audit value, it indicates that there may be a situation where the pressure change of the bucket is abnormal due to theft of materials, thereby issuing a theft alarm. In this embodiment, k is set to 10. In the specific implementation, k can be set according to the actual loading situation. For example, if a bucket is used for loading in the specific implementation, the value of k can be controlled so that the lateral span of the pressure sub-curve YZ is the time for the bucket to load once, thereby performing more accurate and effective detection. Step S204, the value obtained by dividing the abscissa of the rightmost point of the charging pressure curve by k is recorded as q; when the vehicle ZL n1 During the charging process, the rightmost point of the real-time charging curve is obtained and recorded as the real-time charging point (x0, y0), the point with the horizontal coordinate x0 minus q in the real-time charging curve is recorded as the left point of the interval, and the real-time charging curve between the left point of the interval and the real-time charging point is recorded as the real-time sub-curve SQ; In the specific implementation process, for example, the charging pressure curve and real-time charging curve obtained during an analysis can be found in Figure 2 As shown, curve EE1 is the charging pressure curve, curve EE2 is the real-time charging curve, and through analysis, the abscissa of the rightmost point XX1 of the charging pressure curve is 40min, the value of k is 10, and the value of q is 4min. When the real-time charging point obtained during the charging process is point DD1, through analysis, point DD2 is the left point of the interval, and the curve SQ between point DD1 and point DD2 is the real-time sub-curve SQ; Step S205, when the horizontal coordinate of the real-time loading point coincides with the horizontal coordinate of the rightmost point of any audit sub-curve SZ, the value of the vertical coordinate of the highest point in the real-time sub-curve SQ minus the vertical coordinate of the lowest point is recorded as the real-time pressure span. When the real-time pressure span is equal to the pressure audit value, continue loading; when the real-time pressure span is not equal to the pressure audit value, stop loading and send a vehicle ZL n1 Excavator stealing alarm; in the specific implementation process, when the real-time pressure span is equal to the pressure audit value, it means that the loading is normal at this time, and when the real-time pressure span is not equal to the pressure audit value, no matter the real-time pressure span is greater than or less than the pressure audit value, it means that there are other factors involved in the loading process at this time. In order to prevent the occurrence of stealing behavior, the stealing alarm should be issued in time; When the horizontal coordinate of the real-time loading point does not coincide with the horizontal coordinate of the rightmost point of any audit sub-curve SZ and the real-time pressure span is equal to the pressure audit value, the loading is stopped and the vehicle ZL is issued. n1 Excavator stealing alarm; in the specific implementation process, when the horizontal coordinate of the real-time loading point does not coincide with the horizontal coordinate of the rightmost point of any audit sub-curve SZ and the real-time pressure span is equal to the pressure audit value, it means that there are other factors that cause the additional real-time pressure span to be equal to the pressure audit value during the loading process. Therefore, in order to avoid stealing caused by other factors, the stealing alarm should be issued in time. If the loading is carried out strictly according to the loading process, there will be no additional real-time pressure span equal to the pressure audit value. Step S206: When the horizontal coordinate of the real-time loading point coincides with the horizontal coordinate of the rightmost point of the loading pressure curve and no excavator stealing alarm is issued, it is recorded as vehicle ZL n1 Loading completed; in vehicle ZL n1 Loading is complete and vehicle ZL n1 When the speed is greater than or equal to 0, the acceleration sensor is started to obtain the acceleration of the bucket when it is withdrawn in real time, and n1Stop acquiring after leaving the loading point, draw a corresponding curve in the plane rectangular coordinate system for the acceleration data recorded by the acceleration sensor at this time, and record it as the real-time acceleration curve; put the drawer acceleration curve and the real-time acceleration curve into the same plane rectangular coordinate system and overlap the rightmost point of the drawer acceleration curve with the real-time acceleration curve. For any point (x1, y1) in the real-time acceleration curve, mark the vertical coordinate of the point with the horizontal coordinate x1 in the drawer acceleration coordinate system as y2. When y1 is less than y2, the vehicle ZL is issued. n1 Drawer stealing alarm; In the specific implementation process, for example, during a data processing, the point in the real-time acceleration curve is obtained as (2min, 3m / s²). At this time, the vertical coordinate of the point with the horizontal coordinate of 2min in the drawer acceleration coordinate system is 5m / s², which means that the departure speed of vehicle ZL is slower than the normal departure speed. Therefore, in order to prevent theft caused by slowing down the speed of the vehicle, the drawer stealing alarm should be issued; Step S208, when no material theft is identified, a loading detection method is used to perform a loading detection on the vehicle that has completed loading, and loading statistics are performed based on the detection results; The loading detection method includes: step S2081, using a computer vision model to record the behavior of flattening a soil pile with a bucket and record it as a flattening behavior; installing a camera on the bucket of the vehicle, and after the vehicle is loaded, obtaining the cargo in the bucket at this time, when the cargo is flat, starting the camera to shoot the inside of the bucket and using the computer vision model to identify the shot content, when the vehicle ZL n1 When flattening is detected before leaving the loading point, it is recorded as passing the loading inspection; when flattening is still not detected after vehicle ZLn1 leaves the loading point, a warning of not flattening is issued, where flattened cargo refers to cargo that needs to be flattened with a bucket; In the specific implementation process, in the actual cargo transportation process, the leveled cargo can be soil or sand and gravel that need to be flattened with a bucket after loading. At the same time, when recording the leveling behavior, cargo other than soil piles can be used for recording, so that the leveling behavior can meet actual needs; Step S2082, when the loading vehicle is recorded as having passed the loading inspection, the vehicle number is obtained and the vehicle numbers that have passed the loading inspection are counted in the database.

[0019] Step S3, acquiring the position data of the loading vehicle in real time based on the road network system, and using a driving filtering method to filter abnormal alarms when the loading vehicle is driving.

[0020] Step S3 includes: Step S301, when there is a vehicle that has passed the loading inspection in the database, the vehicle number recorded in the database is identified based on the road network system, and the identified vehicle is recorded as a loading vehicle; Step S302, based on the road network system, real-time acquisition of location data of the loading vehicle is performed. When the loading vehicle is in a main driving area, a driving filtering method is used to filter abnormal alarms when the vehicle is driving. The main driving area is an area where many vehicles are driving at the same time, such as a highway or a main road. The driving filtering method includes: when the loading vehicle is in the main driving area, using a magnetic sensor to obtain pressure data in real time, when the pressure in the pressure data continues to decrease, establishing a plane rectangular coordinate system, recorded as a pressure analysis coordinate system, wherein the unit of the X-axis of the pressure analysis coordinate system is time, and the unit of the Y-axis is Newton; based on the pressure data when the pressure in the pressure data begins to decrease, a curve is drawn in the pressure analysis coordinate system, recorded as a theft analysis curve, wherein the leftmost point of the theft analysis curve coincides with the Y-axis and the vertical coordinate of the leftmost point of the theft analysis curve is marked as P; the straight line Y=P is recorded as a pressure measurement line, when the horizontal coordinate of the rightmost point of the theft analysis curve is q and the intersection of the theft analysis curve and the pressure measurement line is equal to 1, a cargo theft alarm is issued; when the horizontal coordinate of the rightmost point of the theft analysis curve is q and the intersection of the theft analysis curve and the pressure measurement line is greater than 1, no alarm is issued; In the specific implementation process, when the pressure in the pressure data continues to decrease, it means that the cargo in the vehicle's cargo box is continuously decreasing. In order to eliminate the error caused by vehicle bumps and other reasons, further analysis should be carried out. For example, in a data processing process, the stolen material analysis curve obtained is as follows: Figure 3 As shown, curve WC is the material theft analysis curve, straight line P is the pressure measurement curve, and the value of q is 10min. Through analysis, it can be obtained that when the horizontal coordinate of the rightmost point of the material theft analysis curve is q, the intersection of the material theft analysis curve and the pressure measurement line is greater than 1, so no alarm is issued.

[0021] Example 2, please refer to Figure 4 As shown, Figure 4The structural schematic diagram of an electronic device is illustrated, and the electronic device may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a method for detecting the change from empty to full loading of a vehicle bucket are executed to achieve the following functions: first, the vehicle used for loading is numbered and identified based on a computer vision model and a text recognition model; then, a magnetic sensor is installed on the leaf spring of the vehicle, and an acceleration sensor is installed on the vehicle bucket. When the loading vehicle is loading, the stolen material identification method is used to identify the stolen material based on the data collected by the magnetic sensor and the acceleration sensor. Finally, the location data of the loading vehicle is obtained in real time based on the road network system, and the driving filtering method is used to filter abnormal alarms when the loading vehicle is driving.

[0022] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0023] Embodiment 3, the present application also provides a computer program product, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by the computer, the computer can execute a method for detecting the change from empty to full loading of a vehicle bed provided by the above methods, the method including: first, numbering and identifying vehicles used for loading based on a computer vision model and a text recognition model; then installing a magnetic sensor on the leaf spring of the vehicle, and installing an acceleration sensor on the vehicle bed; when the loading vehicle is loading, a theft identification method is used to identify theft based on data collected by the magnetic sensor and the acceleration sensor; finally, the location data of the loading vehicle is acquired in real time based on the road network system, and a driving filtering method is used to filter abnormal alarms when the loading vehicle is driving.

[0024] Embodiment 4, the present application also provides a computer-readable storage medium, the present application provides a storage medium, on which a computer program is stored, and when the computer program is executed by the processor, the steps in the above method for detecting the change from empty to full loading of a vehicle bed are executed to achieve the following functions: first, the vehicle used for loading is numbered and identified based on a computer vision model and a text recognition model; then, a magnetic sensor is installed on the leaf spring of the vehicle, and an acceleration sensor is installed on the vehicle bed; when the loading vehicle is loading, a theft identification method is used to identify theft based on the data collected by the magnetic sensor and the acceleration sensor; finally, the location data of the loading vehicle is acquired in real time based on the road network system, and a driving filtering method is used to filter abnormal alarms when the loading vehicle is driving.

[0025] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0026] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0027] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting whether a truck bucket is empty or fully loaded, characterized in that: The steps include: The vehicles used for loading are numbered and identified based on the computer vision model and the text recognition model, and the numbers are ZL1 to ZL n , where n is the number of vehicles used for loading; A magnetic sensor is installed on the leaf spring of the vehicle, and an acceleration sensor is installed on the vehicle bucket. When the loading vehicle is loading, the stolen material identification method is used to identify the stolen material based on the data collected by the magnetic sensor and the acceleration sensor. When the stolen material is identified, the loading is stopped and an early warning report is issued based on the vehicle number. When the theft of materials is not identified, the loading detection method is used to perform loading detection on the vehicles that have completed loading, and the loading statistics are calculated based on the detection results; The location data of the loading vehicle is acquired in real time based on the road network system, and the driving filtering method is used to filter abnormal alarms when the loading vehicle is driving.

2. A method for detecting a truck load from empty to full according to claim 1, characterized in that: Methods for identifying stolen materials include: For any vehicle numbered ZL used for loading n1 The vehicle will be ZL n1 The point where the material is loaded is recorded as the loading point; n1 Before loading, ZL the vehicle n1 Drive to the loading point and use the speed at which the vehicle is loaded to ZL n1 The bucket is loaded with materials. When loading starts, the pressure data of the magnetic sensor is obtained in real time, and a corresponding curve is drawn in the plane rectangular coordinate system; when loading is finished, the obtained curve is recorded as the loading pressure curve; When loading is completed, the acceleration sensor is activated to obtain the acceleration of the bucket when it is withdrawn in real time, and the acceleration of the bucket is measured at the vehicle ZL. n1 After leaving the loading point, the acquisition stops, and the acceleration data recorded by the acceleration sensor at this time is plotted into a corresponding curve in the plane rectangular coordinate system, which is recorded as the drawer acceleration curve.

3. A method for detecting a truck load from empty to full according to claim 2, characterized in that: The method of identifying stolen materials also includes: In vehicle ZL n1 When loading, a plane rectangular coordinate system is established, which is recorded as the excavator stealing material detection coordinate system. The unit of the X axis of the excavator stealing material detection coordinate system is time, and the unit of the Y axis is Newton. n1 When driving to the loading point and starting to load, the pressure data of the magnetic sensor is obtained in real time, and a corresponding curve is drawn in the excavator stealing material detection coordinate system based on the pressure data, which is recorded as the real-time loading curve; the loading pressure curve is placed in the excavator stealing material detection coordinate system, wherein the leftmost point of the real-time loading curve and the loading pressure curve are both in the Y axis; Use a straight line parallel to the Y axis to divide the charging pressure curve into k parts, which are recorded as pressure sub-curves YZ1 to YZ k , for any pressure sub-curve YZ k1 , the pressure sub-curve YZ k1 The value of the highest point's ordinate minus the lowest point's ordinate is recorded as the pressure span, the maximum value of the pressure span in all pressure sub-curves YZ is recorded as the pressure audit value, and the pressure sub-curve YZ whose pressure span is the pressure audit value is recorded as the audit sub-curve SZ.

4. A method for detecting a truck load from empty to full according to claim 3, characterized in that: The method of identifying stolen materials also includes: The value obtained by dividing the abscissa of the rightmost point of the charging pressure curve by k is recorded as q; n1 During the charging process, the rightmost point of the real-time charging curve is obtained and recorded as the real-time charging point (x0, y0), the point with the horizontal coordinate x0 minus q in the real-time charging curve is recorded as the left point of the interval, and the real-time charging curve between the left point of the interval and the real-time charging point is recorded as the real-time sub-curve SQ; When the horizontal coordinate of the real-time loading point coincides with the horizontal coordinate of the rightmost point of any audit sub-curve SZ, the value of the vertical coordinate of the highest point in the real-time sub-curve SQ minus the vertical coordinate of the lowest point is recorded as the real-time pressure span. When the real-time pressure span is equal to the pressure audit value, continue loading; when the real-time pressure span is not equal to the pressure audit value, stop loading and send vehicle ZL n1 Excavator stealing material alarm; When the horizontal coordinate of the real-time loading point does not coincide with the horizontal coordinate of the rightmost point of any audit sub-curve SZ and the real-time pressure span is equal to the pressure audit value, the loading is stopped and the vehicle ZL is issued. n1 Excavator stealing material alarm.

5. A method for detecting a truck load from empty to full according to claim 4, characterized in that: The method of identifying stolen materials also includes: When the horizontal coordinate of the real-time loading point coincides with the horizontal coordinate of the rightmost point of the loading pressure curve and no excavator stealing alarm is issued, it is recorded as vehicle ZL n1 Loading completed; in vehicle ZL n1 Loading is complete and vehicle ZL n1 When the speed is greater than or equal to 0, the acceleration sensor is started to obtain the acceleration of the bucket when it is withdrawn in real time, and n1 Stop acquiring after leaving the loading point, draw a corresponding curve in the plane rectangular coordinate system for the acceleration data recorded by the acceleration sensor at this time, and record it as the real-time acceleration curve; put the drawer acceleration curve and the real-time acceleration curve into the same plane rectangular coordinate system and overlap the rightmost point of the drawer acceleration curve with the real-time acceleration curve. For any point (x1, y1) in the real-time acceleration curve, mark the vertical coordinate of the point with the horizontal coordinate x1 in the drawer acceleration coordinate system as y2. When y1 is less than y2, the vehicle ZL is issued. n1 Drawer theft alarm.

6. A method for detecting a truck load from empty to full according to claim 5, characterized in that: The loading inspection methods include: The computer vision model is used to record the behavior of flattening the soil pile with a bucket and record it as the leveling behavior; a camera is installed on the bucket of the vehicle, and after the vehicle is loaded, the cargo in the bucket is obtained. When the cargo is flat, the camera is started to shoot the inside of the bucket and the computer vision model is used to identify the captured content. When the vehicle ZL n1 When flattening is detected before leaving the loading point, it is recorded as passing the loading inspection; when flattening is still not detected after vehicle ZLn1 leaves the loading point, a warning of not flattening is issued, where flattened cargo refers to cargo that needs to be flattened with a bucket; When the loading vehicle is recorded as having passed the loading inspection, the vehicle number is obtained and the vehicle numbers that have passed the loading inspection are counted in the database.

7. A method for detecting a truck load from empty to full according to claim 6, characterized in that: Based on the road network system, the location data of the loading vehicle is obtained in real time, and the driving filtering method is used to filter abnormal alarms when the loading vehicle is driving, including: When there is a vehicle that has passed the loading inspection in the database, the vehicle number recorded in the database is identified based on the road network system, and the identified vehicle is recorded as a loading vehicle; The location data of the loading vehicle is obtained in real time based on the road network system. When the loading vehicle is in the main driving area, the driving filtering method is used to filter out abnormal alarms when the vehicle is driving.

8. A method for detecting a truck load from empty to full according to claim 7, characterized in that: The driving filtering method includes: when the loading driving vehicle is in the main driving area, using a magnetic sensor to obtain pressure data in real time, when the pressure in the pressure data continues to decrease, establishing a plane rectangular coordinate system, recorded as a pressure analysis coordinate system, wherein the unit of the X-axis of the pressure analysis coordinate system is time, and the unit of the Y-axis is Newton; Based on the pressure data when the pressure starts to decrease in the pressure data, a curve is drawn in the pressure analysis coordinate system, which is recorded as the material stealing analysis curve, wherein the leftmost point of the material stealing analysis curve coincides with the Y axis and the vertical coordinate of the leftmost point of the material stealing analysis curve is marked as P; Let the straight line Y=P be the pressure measurement line. When the abscissa of the rightmost point of the theft analysis curve is q and the intersection of the theft analysis curve with the pressure measurement line is equal to 1, an alarm for theft of cargo is issued. When the abscissa of the rightmost point of the theft analysis curve is q and the intersection of the theft analysis curve with the pressure measurement line is greater than 1, no alarm is issued.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 8 are executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are executed.

Images