A big data process monitoring system and method based on machine vision

Abstract

The invention discloses a big data process supervision system and method based on machine vision, and relates to the technical field of big data process supervision. The invention obtains road surface information on a construction material transportation route and construction material related information in a transportation vehicle through a data acquisition module; performs data analysis on the obtained road surface information and construction material related information through a data analysis module, and parses the obtained information in combination with machine vision technology; monitors the driving behavior of the transportation vehicle through a driving behavior data monitoring module, and monitors and obtains the current driving speed and driving direction of the vehicle; and judges the monitoring data of the driving behavior data monitoring module according to the analysis result of the data analysis module through an early warning feedback module, and issues an early warning if there is a risk of damage to the construction materials in the vehicle; so as to improve the credibility of the supervision of the construction transportation process, improve the safety guarantee for the transportation of construction materials, and effectively reduce the loss of construction materials during transportation.

Description

Technical Field

[0001] The present invention relates to the technical field of big data process supervision, and specifically to a big data process supervision system and method based on machine vision. Background Art

[0002] Machine vision uses computer science, digital signal processing, pattern recognition and other technologies to simulate human visual capabilities into computer systems, enabling computers to perceive and understand images or videos in the real world. Machine vision has a wide range of applications in many fields, and with the rapid development of deep learning and big data, it has made significant progress in practical applications.

[0003] Big data process supervision ensures the reliability of the process by real-time supervision and analysis of the process, and provides real-time feedback and decision support for relevant personnel. When transporting building materials, most of them are transported by whole vehicles, and building materials have the characteristics of being diverse, easy to lose, and easy to damage. For example, flat glass, building ceramics, insulation materials and other building materials are brittle materials. Once they are squeezed and impacted, they are extremely easy to be damaged, and in serious cases, they may even affect the safety of vehicles and personnel. At the same time, the roads leading to the construction site are unhardened, original dirt roads, sharp turns and steep slopes. In the process of transporting building materials, it is necessary to monitor the driving status of the vehicle in combination with the actual road conditions to avoid damage to the transported goods due to the driver's driving errors on the transportation route. In order to minimize the damage to building materials with the above characteristics, the transportation process of building materials needs to be strictly supervised when the transport vehicles are transporting building materials.

[0004] Therefore, in order to solve the above problems or part of the problems, the present invention provides a big data process supervision system and method based on machine vision. Summary of the invention

[0005] The purpose of the present invention is to provide a big data process monitoring system and method based on machine vision to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a big data process supervision method based on machine vision, comprising the following steps:

[0007] S1: Collect the road surface information of the transport route, including the slope, curvature and unevenness of the transport route; obtain the cargo loading information of the transport vehicle, including the location information and cargo placement status of the cargo in the vehicle;

[0008] S2: Analyze the collected road surface information and calculate the road surface flatness of the current driving route; analyze the acquired location and placement information of the cargo in the vehicle and calculate the bearing capacity threshold of the cargo in the vehicle;

[0009] S3: Monitor the driving condition of the current transport vehicle, monitor and obtain the current vehicle's driving speed and driving direction, and analyze the range of changes in the driving condition of the current transport vehicle;

[0010] S4: Based on the analysis result of S2, the driving condition monitored by S3 is judged to determine whether the next driving operation made by the driver meets the tolerable condition of the cargo in the vehicle when driving within the current driving route according to the current driving speed and driving direction.

[0011] Further, the S1 includes:

[0012] Step S1-1: Collect ground information of the current transport vehicle's driving route through machine vision technology; install a high-definition camera on the transport vehicle to collect ground images of the driving route in real time, wherein the camera can be located in front of, behind or to the side of the vehicle to obtain the best field of view;

[0013] Combined with the GPS positioning system, the coordinate location information of the transport vehicle is obtained. By obtaining the current location and driving trajectory of the vehicle, the driving route related data in the cloud is extracted. In the case of multiple vehicles transporting, the repeated collection of road information can be reduced;

[0014] Step S1-2: Process and analyze the collected images. Image processing algorithms can be used to detect road boundaries, obstacles, etc. Computer vision algorithms are used to perform target detection and feature extraction. The extracted feature data are preprocessed to obtain a road feature data set R, where R = {r1, r2, ..., r n}, where r1, r2, ..., r n Respectively represent the first, second, ..., nth groups of road feature data, including a boundary feature data set, a road slope feature data set, a road obstacle feature data set, and a road surface bump feature data set;

[0015] Step S1-3: Install a camera inside the transport vehicle, obtain the location information of the cargo by real-time monitoring the image inside the vehicle, establish a three-dimensional space about the cargo inside the vehicle, use a variety of sensors to monitor the weight and environmental conditions of the cargo loaded in the transport vehicle, and establish a three-dimensional model of the cargo inside the vehicle based on the sensor data. The sensor data can be converted into a visual three-dimensional model using a point cloud reconstruction algorithm or three-dimensional modeling software; the safety of the construction material transportation process is improved, and the efficiency of cargo transportation is optimized.

[0016] Step S1-4: Centrally store and manage the driving route data obtained in the above steps to establish a transportation route database; display the established three-dimensional model through a visualization tool to present the load and balance of the goods in an intuitive manner, and the user can check the cargo condition through the visualized three-dimensional model.

[0017] Further, the S2 includes:

[0018] Step S2-1: Extract characteristic parameters of n groups of road features in the road feature data set R, set weights for each characteristic parameter, and calculate the road surface flatness P of the current driving route according to the following formula:

[0019]

[0020] Among them, r i ′ represents the characteristic parameters of the i-th group of road features in the road feature dataset, i∈(1,2,...,n), ω i represents the weight coefficient of the i-th group of road characteristic parameters in the road surface characteristic data set, and λ represents the error factor;

[0021] Step S2-2: Determine the structural parameters of the current transport vehicle, including the overall size of the vehicle, the suspension system, the frame strength, etc., by accessing the database or by the driver's self-confirmation, and select the first safety range of the cargo center of gravity according to the structural parameters of the vehicle; decompose the vehicle and the cargo into multiple units by grid division according to the location information of the cargo, and select the second safety range of the cargo center of gravity in each unit according to the cargo parameters in each unit; analyze the acquired cargo information in the vehicle, construct a stiffness matrix for each unit, assemble the stiffness matrices of all units to form a global stiffness matrix, and add the stiffness matrix of each unit to the global stiffness matrix according to the degree of freedom of its nodes. ; define boundary conditions (displacement, force, constraint, etc.), and apply them to the global stiffness matrix and load vector, the load vector contains multiple components, each component represents a force magnitude and a force direction; solve the displacement vector, after solving, the displacement of each node can be obtained; use the obtained displacement vector, through the interpolation function of each unit itself, to establish a bearing capacity analysis model for the cargo in the vehicle, according to the established bearing capacity analysis model, analyze the current transport vehicle, when the displacement of the cargo in the vehicle makes the center of gravity of the cargo deviate from the first safety range, the displacement distance is considered to be the warning trigger value, and the force required to cause the displacement is considered to be the cargo bearing capacity threshold F of the current transport vehicle;

[0022] Alternatively, when the displacement of the center of gravity of the cargo in the K units divided in the vehicle causes the center of gravity of the cargo in each unit to deviate from the second safety range, the displacement distance is considered to be the warning trigger value, and the force required to cause the displacement is considered to be the cargo bearing capacity threshold F of the current transport vehicle;

[0023] The concentrated stacking and offset placement of goods may lead to uneven weight distribution in the transport vehicle, which may bring risks of imbalance and instability to the vehicle. By analyzing the placement and weight distribution of the goods in the vehicle, the impact of the state of the goods in the vehicle on the stability of the vehicle can be judged in time. The above two methods for determining the cargo bearing capacity threshold can be selected according to the size and characteristics of the goods.

[0024] Further, the S3 includes:

[0025] Step S3-1: Obtain the vehicle's location information through the positioning system, monitor the vehicle's driving related data through the vehicle-mounted sensor, and process the monitoring data to obtain the current driving speed V and driving direction Q of the transport vehicle;

[0026] Step S3-2: Data mining of the driving state of the transport vehicle and the bearing capacity of the cargo in the vehicle is performed through a computer simulation system:

[0027] X1: There is an acceleration α. ​​When the transport vehicle accelerates, a force Δf1 is generated on the cargo in the vehicle. The cargo bearing capacity of the transport vehicle exceeds the threshold range. The displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range, or the center of gravity of the cargo in the K units divided in the vehicle deviates from the second safety range. In this case, the acceleration α is considered to be the upper limit of the acceleration of the current transport vehicle.

[0028] X2: There is a driving direction deflection angle θ. When the transport vehicle deflects its driving direction, a force Δf2 is generated on the cargo in the vehicle. The cargo bearing capacity of the transport vehicle exceeds the threshold range. The displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range, or the center of gravity of the cargo in the K units divided in the vehicle deviates from the second safety range. In this case, the driving direction deflection angle θ is considered to be the upper limit of the driving direction deflection angle of the current transport vehicle.

[0029] X3: When there are both acceleration α' and driving direction deflection angle θ', when the transport vehicle deflects the driving direction and accelerates, a force Δf3 is generated on the cargo in the vehicle, the cargo bearing capacity of the transport vehicle exceeds the threshold range, the displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range, or the center of gravity of the cargo in the K units divided in the vehicle deviates from the second safety range, then it is considered that either the driving direction deflection angle θ' or the acceleration α' is the upper limit of the combination when the other exists;

[0030] Step S3-3: Establish data association between the road surface flatness P, the driving state of the transport vehicle and the bearing capacity of the cargo in the vehicle. When the road surface flatness P>p0, the road surface has an impact factor on the cargo in the transport vehicle. Impact Factor It is positively correlated with the road surface flatness P. The bearing capacity of the cargo in the vehicle fluctuates, and the cargo bearing capacity threshold is updated. The cargo bearing capacity threshold F of the current transport vehicle is updated to F'. And synchronously update the upper limits of each parameter of the driving state in step S3-2;

[0031] Preferably, when the road surface flatness P>p0, there is an upper limit of the driving speed V max .

[0032] Further, S4 includes:

[0033] Step S4-1: Obtain the parameters related to the tolerable vehicle condition of the cargo in the vehicle through step S3; determine the driving condition of the current transport vehicle obtained through monitoring, and judge whether the cargo in the vehicle can withstand the current vehicle condition when the vehicle is traveling along the current driving route at the current driving speed and direction. At the same time, monitor the accelerator pedal and steering wheel of the vehicle; if the driving parameters of the current transport vehicle will exceed any upper limit of the parameters obtained by computer analysis under the next driving operation of the driver, it is considered that there is a risk of damage to the building materials in the vehicle, and an early warning is issued;

[0034] Step S4-2: In the current driving route of the transport vehicle, there is an arbitrary position. When m or more transport vehicles pass through the arbitrary position, the driving conditions need to be adjusted, and the arbitrary position is considered to be a risky position; the risky position in the current driving route is marked, and the marked risky position is uploaded to the transport route database for storage. The big data process supervision system prompts the transport vehicles on the route where the risky position is located according to the risk position information in the transport route database, and obtains the upper limit of the driving-related parameters of each risk point in combination with the actual parameters of each vehicle and the cargo-related data, supervises the driving behavior of each transport vehicle, and further automatically generates early warnings and controls for transport vehicles on routes with risky positions.

[0035] A big data process supervision system based on machine vision, the system comprising: a data acquisition module, a data analysis module, a driving behavior data monitoring module and a warning feedback module;

[0036] The data acquisition module is used to acquire road surface information on the construction material transportation route and relevant information of the construction materials in the transportation vehicle;

[0037] The data analysis module is used to perform data analysis on the acquired road surface information and building material related information, and analyze the acquired information in combination with machine vision technology;

[0038] The driving behavior data monitoring module is used to monitor the driving behavior of the transport vehicle and monitor and obtain the current driving speed and driving direction of the vehicle;

[0039] The early warning feedback module is used to judge the monitoring data of the driving behavior data monitoring module according to the analysis results of the data analysis module. If there is a risk of damage to the building materials in the vehicle according to the current driving situation of the transport vehicle, an early warning is issued; and the risk position in the current driving route is marked, and the marked risk position is uploaded to the transport route database for storage. The system prompts the transport vehicles on the route where the risk position is located based on the feedback risk position information, so as to improve the safety of the transportation of building materials and effectively reduce the loss of building materials during transportation. By connecting each vehicle to the cloud database for data reception and uploading, the efficiency of information sharing is improved and the repeated collection of data is reduced. At the same time, any time unit can be set to update the road conditions of the risk position, and the arbitrary time can be obtained by analyzing the road conditions and the vehicle traffic.

[0040] Furthermore, the data acquisition module includes a road data acquisition unit and an in-vehicle cargo data acquisition unit;

[0041] The road data acquisition unit is used to acquire the current position information of the vehicle through satellite navigation, acquire the data characteristics of the current road through a camera or radar, and upload the acquired road characteristic data and store it in a database;

[0042] The in-vehicle cargo data acquisition unit is used to acquire cargo-related data in the transport vehicle by using sensors and cameras, so as to obtain information such as the location, size and weight of the cargo, so as to monitor the loading status of the cargo in the vehicle, and transmit the acquired data to a subsequent processing module.

[0043] Furthermore, the data analysis module includes a road information analysis unit and an in-vehicle cargo information analysis unit;

[0044] The road information analysis unit is used to analyze the flatness of the road according to the acquired road-related data features;

[0045] The in-vehicle cargo information analysis unit is used to analyze and model the distribution of the in-vehicle cargo according to the acquired in-vehicle cargo related data, and to classify the cargo and conduct cargo status safety assessment.

[0046] Further, the driving behavior data monitoring module includes a vehicle sensor monitoring unit and a driving behavior analysis unit;

[0047] The vehicle sensor monitoring unit is used to monitor and record the driving state of the vehicle by adding sensors to the steering wheel, brake pedal, accelerator pedal and gear position, and transmit the monitoring data to the driving behavior analysis unit after processing;

[0048] The driving behavior analysis unit is used to analyze the received monitoring data and generate a driving behavior report to facilitate the evaluation of the driver's driving risk, promote the popularization of safe driving, and improve the driver's safety awareness and behavior standards.

[0049] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0050] The present invention collects road surface information of the transport route, obtains cargo loading information of the transport vehicle, and obtains the location information and cargo placement status of the cargo in the vehicle; by analyzing the placement position and weight distribution of the cargo in the vehicle, the influence of the cargo status in the vehicle on the stability of the vehicle can be timely determined; so as to improve the credibility of process supervision and transportation efficiency, reduce errors and risks in cargo transportation, and reduce the risk of imbalance and instability of the vehicle due to uneven weight distribution in the transport vehicle;

[0051] The collected road surface information is analyzed to calculate the road surface flatness of the current driving route; the location and placement information of the cargo in the vehicle is analyzed to calculate the bearing capacity threshold of the cargo in the vehicle; the safety of the construction material transportation process is improved, the driving conditions of the current transport vehicles are monitored, the current vehicle's driving speed and direction are monitored, and the range of changes in the driving conditions of the current transport vehicles is analyzed; the driving behavior of the transport vehicles is monitored to determine whether the next driving operation made by the driver meets the tolerable vehicle conditions of the cargo in the vehicle when driving at the current speed and direction within the current driving route; in order to improve the safety of construction material transportation, effectively reduce the loss of construction materials during transportation, and save economic costs; by connecting each vehicle to the cloud database for data reception and upload, the efficiency of information sharing is improved, the repeated collection of data is reduced, and the popularization of safe driving in transportation is promoted, effectively improving the safety awareness and behavior standards of drivers. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 It is a schematic diagram of the module structure of a big data process monitoring system based on machine vision of the present invention;

[0054] Figure 2 It is a flow chart of a big data process supervision method based on machine vision of the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] See also Figure 1 , Figure 2 The present invention is further described with reference to the accompanying drawings and specific embodiments.

[0057] Example 1: Figure 1 As shown, this embodiment provides a big data process supervision system based on machine vision, and the system includes:

[0058] A big data process supervision system based on machine vision, the system comprising: a data acquisition module, a data analysis module, a driving behavior data monitoring module and a warning feedback module;

[0059] A data acquisition module, used to acquire road surface information on the construction material transportation route and construction material related information in the transportation vehicle; the data acquisition module includes a road data acquisition unit and a vehicle cargo data acquisition unit;

[0060] The road data acquisition unit is used to obtain the current position information of the vehicle through satellite navigation, obtain the data characteristics of the current road through a camera or radar, and upload the obtained road characteristic data and store it in a database;

[0061] The in-vehicle cargo data acquisition unit is used to acquire cargo-related data in the transport vehicle by using sensors and cameras, so as to obtain information such as the location, size and weight of the cargo, so as to monitor the loading status of the cargo in the vehicle and transmit the acquired data to the subsequent processing module.

[0062] The data analysis module is used to analyze the acquired road surface information and building material related information, and analyze the acquired information in combination with machine vision technology; the data analysis module includes a road information analysis unit and an in-vehicle cargo information analysis unit;

[0063] The road information analysis unit is used to analyze the flatness of the road according to the acquired road-related data characteristics;

[0064] The in-vehicle cargo information analysis unit is used to analyze and model the distribution of the in-vehicle cargo based on the acquired in-vehicle cargo related data, and to classify the cargo and conduct cargo status safety assessment.

[0065] The driving behavior data monitoring module is used to monitor the driving behavior of the transport vehicle and monitor and obtain the current driving speed and driving direction of the vehicle; the driving behavior data monitoring module includes a vehicle sensor monitoring unit and a driving behavior analysis unit;

[0066] The vehicle sensor monitoring unit is used to monitor and record the driving status of the vehicle by adding sensors to the steering wheel, brake pedal, accelerator pedal and gear position, and transmit the monitoring data to the driving behavior analysis unit after processing;

[0067] The driving behavior analysis unit is used to analyze the received monitoring data and generate a driving behavior report to facilitate the assessment of the driver's driving risk, promote the popularization of safe driving, and improve the driver's safety awareness and behavior standards.

[0068] The early warning feedback module is used to judge the monitoring data of the driving behavior data monitoring module according to the analysis results of the data analysis module. If there is a risk of damage to the building materials in the vehicle according to the current driving situation of the transport vehicle, an early warning will be issued; and the risk position in the current driving route will be marked, and the marked risk position will be uploaded to the transport route database for storage. The system will prompt the transport vehicles on the route where the risk position is located based on the feedback risk position information, so as to improve the safety of the transportation of building materials and effectively reduce the loss of building materials during transportation. By connecting each vehicle to the cloud database for data reception and uploading, the efficiency of information sharing is improved and the repeated collection of data is reduced. At the same time, any time unit can be set to update the road conditions at the risk position, and the arbitrary time can be obtained by analyzing the road conditions and the vehicle traffic.

[0069] Example 2: Figure 2 As shown, this embodiment provides a big data process supervision method based on machine vision, which is implemented based on a big data process supervision system based on machine vision in the embodiment, and specifically includes the following steps:

[0070] S1: Collect the road surface information of the transport route, including the slope, curvature and unevenness of the transport route; obtain the cargo loading information of the transport vehicle, including the location information and cargo placement status of the cargo in the vehicle;

[0071] Step S1-1: Collect ground information of the current transport vehicle's driving route through machine vision technology; install a high-definition camera on the transport vehicle to collect real-time ground images of the driving route, wherein the camera can be located in front of, behind or to the side of the vehicle to obtain the best field of view; or scan the ground through laser to obtain road surface information such as the ground geometry, and digitally model the road surface through laser scanning data;

[0072] Combined with the GPS positioning system, the coordinate location information of the transport vehicle is obtained. By obtaining the current location and driving trajectory of the vehicle, the driving route related data in the cloud is extracted. In the case of multiple vehicles transporting, the repeated collection of road information can be reduced;

[0073] Step S1-2: Process and analyze the collected images. Image processing algorithms can be used to detect road boundaries, obstacles, etc. Computer vision algorithms are used to perform target detection and feature extraction. The extracted feature data are preprocessed to obtain a road feature data set R, where R = {r1, r2, ..., r n}, where r1, r2, ..., r n Respectively represent the first, second, ..., nth groups of road feature data, including a boundary feature data set, a road slope feature data set, a road obstacle feature data set, and a road surface bump feature data set;

[0074] Step S1-3: Install a camera inside the transport vehicle, obtain the location information of the cargo by real-time monitoring the image inside the vehicle, establish a three-dimensional space about the cargo inside the vehicle, monitor the weight and environmental conditions of the cargo loaded in the transport vehicle by using a variety of sensors, and establish a three-dimensional model of the cargo inside the vehicle based on the sensor data. The sensor data can be converted into a visual three-dimensional model using a point cloud reconstruction algorithm or a three-dimensional modeling software;

[0075] For example, the weight and distribution of goods can be detected by weight sensors, and the tilt degree of goods can be detected by tilt sensors; the position, placement status and possible abnormalities of goods can be monitored in real time, thus improving the safety of the construction material transportation process and optimizing the efficiency of goods transportation.

[0076] Step S1-4: Centrally store and manage the driving route data obtained in the above steps to establish a transportation route database; display the established three-dimensional model through visualization tools, such as Blender, Maya, 3ds Max and other three-dimensional modeling and rendering software, so as to present the load and balance of the goods in an intuitive way, and the user can check the cargo condition through the visualized three-dimensional model.

[0077] S2: Analyze the collected road surface information and calculate the road surface flatness of the current driving route; analyze the acquired location and placement information of the cargo in the vehicle and calculate the bearing capacity threshold of the cargo in the vehicle;

[0078] Step S2-1: Extract characteristic parameters of n groups of road features in the road feature data set R, set weights for each characteristic parameter, and calculate the road surface flatness P of the current driving route according to the following formula:

[0079]

[0080] Among them, r i ′ represents the characteristic parameters of the i-th group of road features in the road feature dataset, i∈(1,2,...,n), ω i represents the weight coefficient of the i-th group of road characteristic parameters in the road surface characteristic data set, and λ represents the error factor;

[0081] For example, for the boundary feature data set, feature parameters such as the average offset of the boundary line, the curvature change, and the distance between the edge line and the lane center line can be extracted; for the road slope feature data set, feature parameters such as the average value, maximum value, minimum value, and degree of change of the longitudinal or lateral slope of the road can be extracted; for the road obstacle feature data set, feature parameters such as the number of obstacles, obstacle volume, and the proportion of obstacles in the road surface can be extracted; for the road bump feature data set, feature parameters such as the number and height of bumps can be extracted.

[0082] Step S2-2: Determine the structural parameters of the current transport vehicle, including the overall size of the vehicle, the suspension system, the frame strength, etc., by accessing the database or by the driver's self-confirmation, and select the first safety range of the cargo center of gravity according to the structural parameters of the vehicle; decompose the vehicle and the cargo into multiple units by grid division according to the location information of the cargo, and select the second safety range of the cargo center of gravity in each unit according to the cargo parameters in each unit; analyze the acquired cargo information in the vehicle, construct a stiffness matrix for each unit, and assemble the stiffness matrices of all units to form a global stiffness matrix, which can be achieved by adding the stiffness matrix of each unit to the global stiffness matrix according to the degrees of freedom of its nodes; define boundary conditions (displacement, force, approx. beam, etc.), and apply it to the global stiffness matrix and load vector, the load vector contains multiple components, each component represents a force magnitude and a force direction; methods such as Gaussian elimination method, LU decomposition method or conjugate gradient method can be used to solve the linear equations to solve the displacement vector, and after solving, the displacement of each node can be obtained; using the obtained displacement vector, through the interpolation function of each unit itself, a bearing capacity analysis model of the cargo in the vehicle is established, and according to the established bearing capacity analysis model, the current transport vehicle is analyzed. When the displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range, the displacement distance is considered to be the warning trigger value, and the force required to cause the displacement is considered to be the cargo bearing capacity threshold F of the current transport vehicle;

[0083] Combined with the cargo weight information, when the cargo displacement in any unit reaches the preset trigger value G, the bearing capacity to achieve the displacement is considered to be the upper limit of the cargo bearing capacity in the transport vehicle;

[0084] S3: Monitor the driving condition of the current transport vehicle, monitor and obtain the current vehicle's driving speed and driving direction, and analyze the range of changes in the driving condition of the current transport vehicle;

[0085] Step S3-1: Obtain the vehicle's location information through the positioning system, monitor the vehicle's driving related data through the vehicle-mounted sensor, and process the monitoring data to obtain the current driving speed V and driving direction Q of the transport vehicle;

[0086] Step S3-2: Data mining of the driving state of the transport vehicle and the bearing capacity of the cargo in the vehicle is performed through a computer simulation system:

[0087] X1: There is an acceleration α. ​​When the transport vehicle accelerates, a force Δf1 is generated on the cargo in the vehicle. The cargo bearing capacity of the transport vehicle exceeds the threshold range. The displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range. In this case, the acceleration α is considered to be the upper limit of the acceleration of the current transport vehicle.

[0088] X2: There is a driving direction deflection angle θ. When the transport vehicle deflects its driving direction, a force Δf2 is generated on the cargo in the vehicle. The cargo bearing capacity of the transport vehicle exceeds the threshold range. The displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range. In this case, the driving direction deflection angle θ is considered to be the upper limit of the driving direction deflection angle of the current transport vehicle.

[0089] X3: When there are both acceleration α' and driving direction deflection angle θ', when the transport vehicle deflects the driving direction and accelerates, a force Δf3 is generated on the cargo in the vehicle, the cargo bearing capacity of the transport vehicle exceeds the threshold range, and the displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range, it is considered that either the driving direction deflection angle θ' or the acceleration α' is the upper limit of the combination when the other exists;

[0090] Step S3-3: Establish data association between the road surface flatness P, the driving state of the transport vehicle and the bearing capacity of the cargo in the vehicle. When the road surface flatness P>p0, the road surface has an impact factor on the cargo in the transport vehicle. Impact Factor It is positively correlated with the road surface flatness P. The bearing capacity of the cargo in the vehicle fluctuates, and the cargo bearing capacity threshold is updated. The cargo bearing capacity threshold F of the current transport vehicle is updated to F'. And synchronously update the upper limits of each parameter of the driving state in step S3-2;

[0091] S4: according to the analysis result of S2, the driving condition monitored by S3 is judged to determine whether the next driving operation made by the driver meets the tolerable condition of the cargo in the vehicle when driving within the current driving route according to the current driving speed and driving direction;

[0092] Step S4-1: Obtain the parameters related to the tolerable vehicle condition of the cargo in the vehicle through step S3; determine the driving condition of the current transport vehicle obtained through monitoring, and judge whether the cargo in the vehicle can withstand the current vehicle condition when the vehicle is traveling along the current driving route at the current driving speed and direction. At the same time, monitor the accelerator pedal and steering wheel of the vehicle; if the driving parameters of the current transport vehicle will exceed any upper limit of the parameters obtained by computer analysis under the next driving operation of the driver, it is considered that there is a risk of damage to the building materials in the vehicle, and an early warning is issued;

[0093] Step S4-2: In the current driving route of the transport vehicle, there is an arbitrary position. When m or more transport vehicles pass through the arbitrary position, the driving conditions need to be adjusted, and the arbitrary position is considered to be a risky position; the risky position in the current driving route is marked, and the marked risky position is uploaded to the transport route database for storage. The big data process supervision system prompts the transport vehicles on the route where the risky position is located according to the risk position information in the transport route database, and obtains the upper limit of the driving-related parameters of each risk point in combination with the actual parameters of each vehicle and the cargo-related data, supervises the driving behavior of each transport vehicle, and further automatically generates early warnings and controls for transport vehicles on routes with risky positions.

[0094] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0095] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A big data process supervision method based on machine vision, characterized by: The following steps are involved: S1: Collect the road surface information of the transport route, obtain the cargo loading information of the transport vehicle, and obtain the location information and cargo placement status of the cargo in the vehicle; S2: Analyze the collected road surface information and calculate the road surface flatness of the current driving route; analyze the acquired location and placement information of the cargo in the vehicle and calculate the bearing capacity threshold of the cargo in the vehicle; S3: Monitor the driving condition of the current transport vehicle, monitor and obtain the current vehicle's driving speed and driving direction, and analyze the variable range of the current transport vehicle's driving condition; S4: according to the analysis result of S2, the driving condition monitored by S3 is judged to determine whether the next driving operation made by the driver meets the tolerable condition of the cargo in the vehicle when driving within the current driving route according to the current driving speed and driving direction; The S1 includes: Step S1-1: Collect ground information of the current transport vehicle's driving route through machine vision technology; install a high-definition camera on the transport vehicle to collect ground images of the driving route in real time; Step S1-2: Process and analyze the collected images, perform target detection and feature extraction through computer vision algorithms, preprocess the extracted feature data, and obtain a road feature data set R, where R = {r1, r2, ..., r n }, where r1, r2, ..., r n Respectively represent the 1st, 2nd, ..., nth groups of road feature data; Step S1-3: Install a camera inside the transport vehicle, obtain the location information of the cargo by real-time monitoring the image inside the vehicle, establish a three-dimensional space about the cargo inside the vehicle, monitor the weight and environmental conditions of the cargo loaded in the transport vehicle by using multiple sensors, and establish a three-dimensional model of the cargo inside the vehicle based on the sensor data; Step S1-4: Centrally store and manage the driving route data obtained in the above steps to establish a transportation route database; and display the established three-dimensional model through a visualization tool.

2. The method for monitoring a big data process based on machine vision according to claim 1, characterized in that: The S2 includes: Step S2-1: Extract characteristic parameters of n groups of road features in the road feature data set R, set weights for each characteristic parameter, and calculate the road surface flatness P of the current driving route according to the following formula: Among them, r i ′ represents the characteristic parameters of the i-th group of road features in the road feature dataset, i∈(1,2,...,n), ω i represents the weight coefficient of the i-th group of road characteristic parameters in the road surface characteristic data set, and λ represents the error factor; Step S2-2: Determine the structural parameters of the current transport vehicle by accessing a database or by the driver's self-confirmation, and select a first safety range of the cargo center of gravity according to the structural parameters of the vehicle; decompose the vehicle and the cargo into multiple units by grid division according to the cargo location information, and select a second safety range of the cargo center of gravity in each unit according to the cargo parameters in each unit; analyze the acquired cargo information in the vehicle, establish a bearing capacity analysis model for the cargo in the vehicle, and analyze the current transport vehicle according to the established bearing capacity analysis model. When the displacement of the cargo in the vehicle causes the cargo center of gravity to deviate from the first safety range, the displacement distance is considered to be a warning trigger value, and the force required to cause the displacement is considered to be the cargo bearing capacity threshold F of the current transport vehicle; Alternatively, when the displacement of the center of gravity of the cargo within the K units divided in the vehicle causes the center of gravity of the cargo in each unit to deviate from the second safety range, the displacement distance is considered to be the warning trigger value, and the force required to cause the displacement is considered to be the cargo bearing capacity threshold F of the current transport vehicle.

3. The big data process monitoring method based on machine vision according to claim 1 is characterized in that: The S3 includes: Step S3-1: Obtain the vehicle's location information through the positioning system, monitor the vehicle's driving related data through the vehicle-mounted sensor, and process the monitoring data to obtain the current driving speed V and driving direction Q of the transport vehicle; Step S3-2: Data mining of the driving state of the transport vehicle and the bearing capacity of the cargo in the vehicle is performed through a computer simulation system: X1: There is an acceleration α. ​​When the transport vehicle accelerates, the cargo bearing capacity of the transport vehicle exceeds the threshold range, the displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range, or the center of gravity of the cargo in the K units divided in the vehicle deviates from the second safety range. In this case, the acceleration α is considered to be the upper limit of the acceleration of the current transport vehicle. X2: There is a driving direction deflection angle θ. When the transport vehicle deflects its driving direction, the cargo bearing capacity of the transport vehicle exceeds the threshold range, and the displacement of the cargo in the vehicle causes the center of gravity of the cargo to deviate from the first safety range, or the center of gravity of the cargo in the K units divided in the vehicle deviates from the second safety range. In this case, the driving direction deflection angle θ is considered to be the upper limit of the driving direction deflection angle of the current transport vehicle. X3: When there are both acceleration α' and driving direction deflection angle θ', and when the transport vehicle deflects in the driving direction and accelerates, the cargo bearing capacity of the transport vehicle exceeds the threshold range, and the displacement of the cargo in the vehicle causes the cargo center of gravity to deviate from the first safety range, or the cargo center of gravity in the K units divided in the vehicle deviates from the second safety range, then it is considered that either the driving direction deflection angle θ' or the acceleration α' is the upper limit of the combination when the other exists; Step S3-3: Establish data association between the road surface flatness P, the driving state of the transport vehicle and the bearing capacity of the cargo in the vehicle. When the road surface flatness P>p0, the road surface has an impact factor on the cargo in the transport vehicle. Impact Factor It is positively correlated with the road surface flatness P. The bearing capacity of the cargo in the vehicle fluctuates, and the cargo bearing capacity threshold is updated. The cargo bearing capacity threshold F of the current transport vehicle is updated to F'. The upper limits of the parameters of the driving state in step S3-2 are also updated synchronously.

4. The big data process monitoring method based on machine vision according to claim 1 is characterized in that: The S4 comprises: Step S4-1: Determine the driving condition of the current transport vehicle obtained by monitoring, by monitoring the accelerator pedal and steering wheel of the vehicle; if the driving parameters of the current transport vehicle will exceed any upper limit of the parameters obtained by computer analysis under the next driving operation of the driver, then issue a warning; Step S4-2: In the current driving route of the transport vehicle, there is an arbitrary position. When m or more transport vehicles pass through this arbitrary position, the driving conditions need to be adjusted, and this arbitrary position is considered to be a risky position; the risky position in the current driving route is marked, and the marked risky position is uploaded to the transport route database for storage. The big data process supervision system prompts the transport vehicles on the route where the risky position is located according to the risk position information in the transport route database.

5. A big data process monitoring system based on machine vision, characterized by: The system includes: a data acquisition module, a data analysis module, a driving behavior data monitoring module and a warning feedback module; The data acquisition module is used to acquire road surface information on the construction material transportation route and relevant information of the construction materials in the transportation vehicle; The data analysis module is used to perform data analysis on the acquired road surface information and building material related information, and analyze the acquired information in combination with machine vision technology; The driving behavior data monitoring module is used to monitor the driving behavior of the transport vehicle and monitor and obtain the current driving speed and driving direction of the vehicle; The warning feedback module is used to judge the monitoring data of the driving behavior data monitoring module according to the analysis results of the data analysis module. If there is a risk of damage to the building materials in the vehicle according to the current driving situation of the transport vehicle, a warning is issued; and the risk position in the current driving route is marked, and the marked risk position is uploaded to the transport route database for storage. The system prompts the transport vehicle on the route where the risk position is located according to the feedback risk position information; The data acquisition module includes a road data acquisition unit and an in-vehicle cargo data acquisition unit; The road data acquisition unit is used to acquire the current position information of the vehicle through satellite navigation, acquire the data characteristics of the current road through a camera or radar, and upload the acquired road characteristic data and store it in a database; The in-vehicle cargo data acquisition unit is used to acquire cargo-related data in the transport vehicle by using sensors and cameras.

6. The big data process monitoring system based on machine vision according to claim 5 is characterized by: The data analysis module includes a road information analysis unit and an in-vehicle cargo information analysis unit; The road information analysis unit is used to analyze the flatness of the road according to the acquired road-related data features; The in-vehicle cargo information analysis unit is used to analyze and model the distribution of the in-vehicle cargo according to the acquired in-vehicle cargo related data, and to classify the cargo and conduct cargo status safety assessment.

7. The big data process monitoring system based on machine vision according to claim 5 is characterized by: The driving behavior data monitoring module includes a vehicle sensor monitoring unit and a driving behavior analysis unit; The vehicle sensor monitoring unit is used to monitor and record the driving state of the vehicle by adding sensors to the steering wheel, brake pedal, accelerator pedal and gear position, and transmit the monitoring data to the driving behavior analysis unit after processing; The driving behavior analysis unit is used to analyze the received monitoring data and generate a driving behavior report.

Images