A safety transportation monitoring method and system for a transportation vehicle

Abstract

The present invention relates to the technical field of vehicle safety transportation, and in particular to a method and system for monitoring the safe transportation of transportation vehicles. The method includes the steps of: starting the standby state of the camera after collecting the initial binary image of the carriage, and obtaining the speed value and tilt angle corresponding to each data point in the time series sequence of vehicle driving data; obtaining the warning level of the data point based on the speed difference and tilt angle difference between the data point and the preset-length neighboring sequence; constructing a target sequence of the data point in response to the ascending order of the Euclidean distances between the data point and other data points; calculating the alarm level of the data point; starting the camera to capture the warning binary image of the carriage corresponding to the data point in response to the alarm level of the data point being greater than a preset threshold; and realizing the safe transportation monitoring of the transportation vehicle through the exclusive OR result of the initial binary image of the carriage and the warning binary image, which can effectively improve the efficiency of the safe transportation monitoring of the transportation vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle safe transportation, and particularly to a method and a system for monitoring the safe transportation of a transport vehicle. Background Art

[0002] Goods such as electronic products, precision instruments, and fresh products are susceptible to factors such as sudden braking, severe jolting, or tilting during transportation, resulting in the goods shifting or even toppling, damaging the product quality, and even possibly causing traffic accidents and endangering road safety. Therefore, during the transportation of goods by a transport vehicle, it is necessary to monitor the goods in the carriage in real time so as to timely give an alarm for abnormal tilting during the goods transportation process and improve the transportation safety.

[0003] Conventional methods realize the monitoring and warning of goods by collecting the monitoring images of the cargo box in real time through a camera. However, a large amount of computing resources are required for processing the camera video stream, and during the normal driving process of the vehicle, most of the collected monitoring images are in a normal state, and the goods do not show tilting or shifting phenomena. Continuously collecting and uploading the monitoring video stream in real time will instead increase the burden on the vehicle-mounted power supply and the bandwidth cost, affecting the efficiency of vehicle transportation monitoring.

[0004] The tilting of goods is not only reflected in the tilting degree of the vehicle but also in the change of the vehicle speed. The change of the vehicle speed can reflect the possibility of the goods tilting or shifting. When monitoring the goods of the vehicle, the change of the vehicle speed and the tilting degree can be simultaneously concerned, so as to accurately identify potential abnormalities and achieve accurate warning.

[0005] Based on this, how to accurately achieve vehicle abnormal warning based on the change of vehicle speed and the tilting degree is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] In order to solve the technical problem of how to accurately achieve vehicle abnormal warning based on the change of vehicle speed and the tilting degree, the present invention provides a method and a system for monitoring the safe transportation of a transport vehicle.

[0007] In a first aspect, the present invention provides a method for monitoring the safe transportation of a transport vehicle, adopting the following technical solution:

[0008] A method for monitoring the safe transportation of a transport vehicle includes the steps:

[0009] After capturing an initial binary image of the vehicle cabin, the camera is activated and placed in standby mode. The speed and tilt angle corresponding to each data point in the vehicle driving data time series are obtained. The warning level of the data point is determined based on the speed and tilt angle differences between the data point and a neighboring sequence of a preset length. A target sequence for the data point is constructed based on the ascending order of the Euclidean distance between the data point and other data points. The warning level of the data point is calculated based on the difference in warning level and the difference in acquisition time between the data point and the data points in the target sequence:

[0010] ;

[0011] 、 、 are respectively the alarm level, warning level, and collection time of the i-th data point, is the mean value of the warning degree of the target sequence of the i-th data point, is the target sequence length, is the first data point in the target sequence The collection time of the data point, is an exponential function with base e, is an absolute value symbol; in response to the alarm level of a data point being greater than a preset threshold, the camera is started to capture the carriage alarm binary image corresponding to the data point; the safe transportation monitoring of the transport vehicle is realized through the XOR result of the initial binary image of the carriage and the alarm binary image.

[0012] The present invention collects surveillance images of cargo in carriages for abnormal monitoring, thereby enabling safe transportation monitoring and early warning of transport vehicles. In this process, the present invention takes into account that collecting and transmitting surveillance images at all times may result in a waste of resources, a large amount of data processing, and low efficiency. Based on this, the present invention starts the camera standby mode after collecting the initial image of the carriage, monitors the speed data and changes in the tilt angle of the vehicle body during driving, and determines the moment when the cargo may tilt or deflect. The surveillance image at that moment is collected and compared with the initial image. Through secondary confirmation, the results of the safe transportation monitoring and early warning of transport vehicles can be accurately obtained, thereby improving the efficiency of the safe transportation monitoring and early warning of transport vehicles.

[0013] According to a method for monitoring safe transportation of transport vehicles provided by the present invention, the method of obtaining the speed value and tilt angle corresponding to each data point in the vehicle driving data time series sequence also includes: treating the vehicle speed data and tilt angle data obtained at each acquisition moment as a data point, and obtaining the vehicle driving data time series sequence after preprocessing.

[0014] The present invention takes into account the possibility that the originally collected speed data and tilt angle data may be missing, and therefore improves the overall quality of the data through preprocessing to facilitate subsequent data processing.

[0015] A method for monitoring the safe transportation of a transport vehicle provided by the present invention, obtaining the warning level of a data point based on the speed difference and tilt angle difference between the data point and a preset-length adjacent sequence, includes: obtaining the absolute value mean of the speed difference between the speed value of the data point and the speeds in the adjacent sequence, normalizing the ratio of the absolute value mean of the speed difference to the speed standard deviation of the adjacent sequence of this data point, to obtain the speed mutability of this data point; obtaining the tilt angle mutability of this data point; recording the sum of the product of a preset speed weight and the speed mutability of the data point and the product of a preset tilt angle weight and the tilt angle mutability of this data point as the warning level of this data point.

[0016] The present invention takes into account that the inclination or deviation of goods is closely related to the speed of the transport vehicle and the tilt angle of the vehicle body. Therefore, a precise calculation method for the warning level of data points is provided. By analyzing the differences in speed data and tilt angle data between the current data point and adjacent data, the warning moment with prominent speed data and tilt angle data can be accurately obtained.

[0017] A method for monitoring the safe transportation of a transport vehicle provided by the present invention, constructing the target sequence of this data point in response to the ascending order of the Euclidean distances between the data point and other data points, includes: taking the other data points corresponding to a preset number of Euclidean distances with the minimum Euclidean distance between the data point and other data points in the ascending order as the starting point, as the target sequence of this data point.

[0018] A method for monitoring the safe transportation of a transport vehicle provided by the present invention, when the warning level of the data point is greater than a preset threshold, starting the camera to capture the warning binary image of the carriage corresponding to this data point, further includes: when the warning level of the data point is not greater than the preset threshold, continuing to keep the camera in the standby state.

[0019] A method for monitoring the safe transportation of a transport vehicle provided by the present invention, the method for obtaining the initial binary image and warning binary image of the carriage, includes: processing the initial monitoring image and warning monitoring image collected by the camera through an edge detection algorithm to obtain the initial binary image and warning binary image.

[0020] A method for monitoring the safe transportation of a transport vehicle provided by the present invention, the exclusive OR result of the initial binary image and warning binary image of the carriage, includes: if the gray values of the pixel points in the initial binary image of the carriage and the corresponding pixel points in the warning binary image are different, then this pixel point is an abnormal pixel point; otherwise, this pixel point is a normal pixel point.

[0021] A method for monitoring the safe transportation of a transportation vehicle provided by the present invention realizes the monitoring of the safe transportation of the transportation vehicle through the exclusive OR result of the initial binary image of the carriage and the warning binary image, including: if the proportion of the number of abnormal pixel points in the exclusive OR result of the initial binary image of the carriage and the warning binary image is greater than a preset abnormal threshold, obtaining that the monitoring result of the safe transportation of the transportation vehicle is abnormal; otherwise, the monitoring result of the safe transportation of the transportation vehicle is normal; in response to the monitoring result of the safe transportation of the transportation vehicle being abnormal, an abnormal voice warning is issued outward.

[0022] The present invention takes into account that during the driving process of the transportation vehicle, the staff may not be able to view the monitoring result in time. Therefore, after obtaining that the monitoring result of the safe transportation of the transportation vehicle is abnormal, the present invention promptly issues an abnormal voice warning outward to prompt the staff to process it as soon as possible, thereby reducing the risk of cargo damage and improving the transportation quality.

[0023] A method for monitoring the safe transportation of a transportation vehicle provided by the present invention, after realizing the monitoring of the safe transportation of the transportation vehicle, further includes: associatively storing the data points where the monitoring result of the safe transportation of the transportation vehicle is abnormal and the corresponding warning binary images to a database.

[0024] The present invention takes into account that the deviation of the cargo in the carriage may damage the quality of the cargo. Therefore, the time of deviation and the warning image are associatively stored to facilitate the subsequent analysis of the work effect of the staff and standardize the operation behavior of the staff.

[0025] In a second aspect, the present invention provides a system for monitoring the safe transportation of a transportation vehicle, adopting the following technical solution:

[0026] A system for monitoring the safe transportation of a transportation vehicle includes: a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned method for monitoring the safe transportation of a transportation vehicle is realized.

[0027] By adopting the above technical solution, the above-mentioned method for monitoring the safe transportation of a transportation vehicle is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0028] The present invention has the following technical effects:

[0029] Based on the above technical solution, a method and system for monitoring the safe transportation of a transport vehicle provided by the present invention can achieve the monitoring and early warning of the safe transportation of the transport vehicle by collecting monitoring images of the goods in the carriage for abnormal monitoring. In this process, the present invention considers that collecting and transmitting monitoring images at all times may cause waste of resources, large data processing volume and low efficiency; based on this, after the initial image of the carriage is collected, the camera is put into the standby state, and by monitoring the speed data and the change of the body tilt angle during the vehicle driving process, the moment when the goods may tilt or shift is obtained, and the monitoring image at this moment is collected and compared with the initial image. Through secondary confirmation, the monitoring and early warning result of the safe transportation of the transport vehicle can be accurately obtained, and the efficiency of the monitoring and early warning of the safe transportation of the transport vehicle is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic flow chart of a method for monitoring the safe transportation of a transport vehicle provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments.

[0032] In order to achieve the monitoring and early warning of the safe transportation of a transport vehicle, an embodiment of the present invention discloses a method for monitoring the safe transportation of a transport vehicle. After collecting the initial monitoring image of the carriage by a camera, the camera is kept in the standby state, and the vehicle driving data is analyzed to accurately obtain the possibility that the goods in the carriage are tilted or shifted. When it is obtained from the vehicle driving data that the goods may be tilted or shifted, the camera is started again to collect the real-time warning monitoring image of the carriage, and the abnormal monitoring result of the vehicle operation can be accurately obtained, effectively improving the efficiency of the monitoring and early warning of the safe transportation of the transport vehicle.

[0033] Specifically, please refer to Figure 1 as shown in Figure 1 It is a schematic flow chart of a method for monitoring the safe transportation of a transport vehicle provided by an embodiment of the present invention, and the method specifically includes the following steps.

[0034] S1: After collecting the initial binary image of the carriage, start the standby state of the camera.

[0035] Exemplarily, in the embodiment of the present invention, the method for obtaining the initial binary image of the carriage includes: processing the initial monitoring image collected by the camera through an edge detection algorithm to obtain the initial binary image.

[0036] The edge detection algorithm may be a Canny edge detection algorithm, a Sober edge detection algorithm, etc., and may be set according to actual needs.

[0037] Specifically, after the transport vehicle completes loading, an initial monitoring image is captured by a high-definition camera.

[0038] For example, before collecting the initial binary image of the carriage, the initial monitoring image may be subjected to denoising preprocessing, image enhancement, etc., which may be specifically configured according to actual needs and are not excessively limited in the embodiment of the present invention.

[0039] It should be noted that when the monitoring images of the cargo box are collected in real time by the camera, the status of the cargo in most monitoring images may remain unchanged. If all monitoring images are monitored and transmitted, it may cause a waste of resources.

[0040] Based on this, the embodiment of the present invention controls the camera to be in a standby state after collecting the initial monitoring image of the vehicle compartment, thereby reducing resource consumption.

[0041] It can be understood that the camera standby state refers to the low-power mode in which the camera is in when it is not performing operations such as shooting or recording. In the standby state, the camera usually turns off or reduces the power consumption of the image sensor, etc., while maintaining the state of receiving instructions or signals.

[0042] It should be further explained that after the control camera is in standby mode, it needs to continue to monitor and warn the cargo in the carriage. The tilt or deviation of the cargo in the carriage is directly related to the speed and tilt angle of the vehicle.

[0043] Based on this, the embodiment of the present invention obtains the possibility of tilt or offset of the cargo in the carriage by analyzing the changes in the speed data and tilt angle data of the transport vehicle during transportation, thereby accurately realizing vehicle safety transportation monitoring and early warning, that is, executing the following steps.

[0044] S2: Obtain the speed value and tilt angle corresponding to each data point in the vehicle driving data time series; based on the speed difference and tilt angle difference between the data point and the adjacent sequence of preset length, obtain the warning level of the data point.

[0045] The preset length of the adjacent sequence may be set to 20, which may be specifically set according to actual needs, and the embodiment of the present invention does not impose any excessive restrictions on this.

[0046] It is understandable that the neighboring sequence of the current data point does not include the current data point itself; the preset length of the neighboring sequence is the number of data points included in the neighboring sequence.

[0047] For example, when obtaining the adjacent sequence of the current data point, the adjacent data point to the left of the current data point can be used as the starting point to obtain data points, construct the neighboring sequence of the current data point, the length of the neighboring sequence is .

[0048] It's important to note that the tilt angle of a transport vehicle's body can directly indicate the possibility of tilt or shifting of cargo within the vehicle. The greater the tilt angle, the greater the likelihood of tilt or shifting. However, if a significant change in the vehicle's tilt angle is detected, the cargo within the vehicle may have already tilted significantly or even collapsed. The tilt of the vehicle's body can also be reflected by the vehicle's speed. Large speed fluctuations or high instantaneous speeds can cause the cargo's inertia to cause the vehicle to tilt, potentially causing the cargo within the vehicle to tilt or shift.

[0049] Based on this, the embodiment of the present invention obtains the change of speed data and tilt angle data of the transport vehicle to obtain the possibility of tilt or offset of the cargo in the carriage, so as to identify potential abnormalities in a timely and accurate manner and improve the accuracy of early warning.

[0050] For example, in an embodiment of the present invention, the speed value and tilt angle corresponding to each data point in the vehicle driving data time series sequence are obtained, which also includes: taking the speed data and tilt angle data of the vehicle obtained at each acquisition moment as a data point, and obtaining the vehicle driving data time series sequence after preprocessing.

[0051] The preprocessing may be data normalization, missing data interpolation, etc., which may be specifically configured according to actual needs, and the embodiment of the present invention does not impose excessive restrictions thereon.

[0052] Specifically, when collecting vehicle speed data and tilt angle data, the collection frequency can be preset, the vehicle speed data can be obtained through the positioning system, and the tilt sensor can be placed on the frame or center of the vehicle chassis of the transport vehicle to collect the tilt angle data of the transport vehicle.

[0053] The acquisition frequency may be set to 10 Hz, and may be set according to actual needs. The embodiment of the present invention does not impose any restrictions on this.

[0054] For example, in an embodiment of the present invention, the warning level of a data point is obtained based on the speed difference and tilt angle difference between the data point and an adjacent sequence of a preset length, including: obtaining the absolute mean of the speed value of the data point and the speed difference in the adjacent sequence, normalizing the ratio of the absolute mean of the speed difference to the standard deviation of the speed of the adjacent sequence of the data point to obtain the speed mutation of the data point; obtaining the tilt angle mutation of the data point; and recording the sum of the product of the preset speed weight and the speed mutation of the data point and the product of the preset tilt angle weight and the tilt angle mutation of the data point as the warning level of the data point.

[0055] Among them, the preset speed weight can be set to 0.3, the preset tilt angle weight can be set to 0.7, and the sum of the preset speed weight and the preset tilt angle weight is 1; specifically, it can be set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0056] It can be understood that the body tilt angle data directly reflects the tilt state of the body and is closely related to the stability of the goods. If the body tilt angle is relatively large, the goods are more likely to shift or tip over due to the action of gravity, while the driving speed data has a relatively small impact on the stability of the goods. Therefore, in the embodiments of the present invention when setting the corresponding weights, the weight of the body tilt angle data can be made greater than the weight of the driving speed data.

[0057] For the convenience of understanding, hereinafter, the embodiments of the present invention will take the calculation of the speed mutation of data points as an example for illustration, but it does not mean that the embodiments of the present invention are only limited thereto.

[0058] Exemplarily, in the embodiments of the present invention, to calculate the speed mutation of data points, the following relational expression can be specifically referred to:

[0059] ;

[0060] is the speed mutation of the i-th data point, is the length of the adjacent sequence of data points, is the speed value of the i-th data point, is the -th data point speed value in the adjacent sequence of the i-th data point, is the speed standard deviation of the adjacent sequence of the i-th data point, is the absolute value symbol, is the standard normalization function.

[0061] In the above formula, the speed mutation of the i-th data point is used to characterize the degree of speed mutation during the driving of the transport vehicle, represents the speed difference between the i-th data point and the adjacent sequence. The greater the difference, the greater the change difference between the speed data of the transport vehicle at the acquisition moment corresponding to the i-th data point and the recent speed data, and the greater the possibility of offset or tilt of the cargo in the carriage at the current moment.

[0062] It can be understood that the driving conditions of the transport vehicle are different on different road sections. For example, the vehicle speed will be continuously high on the highway section, and the vehicle speed changes greatly but the speed value is small in the traffic jam section. Therefore, through comparing the speed data points that change at different time periods with a unified standard, it is convenient for data processing.

[0063] Similarly, the tilt angle mutation of each data point can be obtained.

[0064] For example, in an embodiment of the present invention, obtaining the sudden change in the tilt angle of the data point includes: obtaining the absolute mean of the difference between the tilt angle value of the data point and the tilt angle in the adjacent sequence, normalizing the ratio of the absolute mean of the tilt angle difference to the standard deviation of the tilt angle of the adjacent sequence of the data point, and obtaining the sudden change in the tilt angle of the data point.

[0065] After obtaining the speed mutation and tilt angle mutation of the data point based on the above steps, the warning level of the data point can be obtained based on the speed mutation and tilt angle mutation of the data point, and then continue to perform the following steps.

[0066] S3: In response to the ascending order of the Euclidean distances between the data point and other data points, a target sequence for the data point is constructed, and the alarm level of the data point is calculated.

[0067] It should be noted that the above steps can obtain the warning level of the data point by analyzing the speed difference and tilt angle difference between the data point and the adjacent sequence. The higher the warning level, the higher the possibility that the cargo is tilted or offset at the collection moment corresponding to the current data point.

[0068] However, during the driving process of a truck, the process of cargo deviation or tilting is usually time-series. The above steps only determine whether an early warning is needed based on the warning level obtained at a single collection moment, which is easily affected by instantaneous noise data and may lead to false warnings.

[0069] Based on this, an embodiment of the present invention can obtain some data points with a close Euclidean distance to the data point as the target sequence of the data point. The smaller the Euclidean distance between the data points, the higher the similarity between the data points. By analyzing the difference in warning degree and collection time between the data point and the data points in the target sequence, the possibility that the current data point is noise data can be accurately obtained, thereby accurately obtaining the possibility that the goods are offset or tilted.

[0070] For example, in an embodiment of the present invention, in response to the ascending arrangement of the Euclidean distance between a data point and other data points, a target sequence of the data point is constructed, including: taking the minimum value of the Euclidean distance between the data point and other data points in the ascending arrangement as a starting point to obtain a preset number of other data points corresponding to the Euclidean distance as the target sequence of the data point.

[0071] Among them, the preset number can be set to 10, and can be set specifically according to actual needs. The embodiment of the present invention does not impose too many restrictions on this.

[0072] It can be understood that the data points in the target sequence of the current data point are several data points that are ranked high in ascending order, that is, several data points that are close to the current data point in Euclidean distance.

[0073] For example, in an embodiment of the present invention, the alarm level of a data point is calculated, and specific reference may be made to the following relationship:

[0074] ;

[0075] is the warning level of the i-th data point, is the warning level of the i-th data point, is the mean value of the warning degree of the target sequence of the i-th data point, is the target sequence length, is the collection time of the i-th data point, is the first data point in the target sequence The collection time of the data point, is an exponential function with e as the base, where e is a natural constant. is the absolute value symbol.

[0076] In the above formula, It represents the difference between the warning level of the i-th data point and the mean warning level of the target sequence of the i-th data point. The larger the value, the greater the possibility that the i-th data point is noise data. In order to reduce the interference of noise data, the warning level of the data point needs to be lowered. Therefore, the corresponding warning level of the i-th data point is lower.

[0077] It represents the difference between the collection time of the i-th data point and the collection time of each data point in the target sequence of the i-th data point. The smaller the value, the closer the i-th data point is to its target sequence. The closer the collection times of the data points are, the higher the credibility of the alarm level of the obtained data points.

[0078] After the alarm level of each data point is obtained based on the above steps, it can be determined whether there is a possibility that the cargo in the carriage is tilted or offset based on the comparison result of the alarm level of the data point with the preset threshold.

[0079] S4: In response to the alarm level of the data point being greater than a preset threshold, the camera is started to capture the carriage alarm binary image corresponding to the data point.

[0080] The preset threshold value may be set to 0.7. The preset threshold value may be set according to actual needs, and the embodiment of the present invention does not impose any excessive restrictions on this.

[0081] It should be noted that the binary image of the carriage warning corresponding to the data point captured by the camera startup is the carriage monitoring image corresponding to the data point where the current goods may be tilted or offset. When it is detected that the goods may be tilted or offset, the camera is started to capture the current monitoring image, and based on the difference between the current monitoring image and the initial monitoring image, the warning of the data point is reconfirmed, and the warning result of the current data point can be accurately obtained, reducing the possibility of false warnings.

[0082] Exemplarily, in the embodiment of the present invention, the method for obtaining the binary image of the carriage warning includes: processing the warning monitoring image collected by the camera through an edge detection algorithm to obtain the warning binary image.

[0083] Exemplarily, when the initial binary image and the warning binary image are obtained by processing the initial monitoring image and the warning monitoring image collected by the camera through an edge detection algorithm, the edge detection algorithm obtains the edge detection results in the initial monitoring image and the warning monitoring image to obtain the initial binary image and the warning binary image.

[0084] Among them, the specific steps of the edge detection algorithm for obtaining the edge detection results in the initial monitoring image and the warning monitoring image to obtain the initial binary image and the warning binary image can be implemented by the prior art, and the embodiments of the present invention will not be elaborated herein.

[0085] It can be understood that if the warning level of the current data point is not greater than the preset threshold, it means that there is no abnormality or the abnormality is small in the transportation process of the transport vehicle at the acquisition moment corresponding to the current data point, and the possibility of the goods in the carriage being offset or tilted is small. In this case, the standby state of the camera can be continued.

[0086] Exemplarily, in the embodiment of the present invention, in response to the warning level of the data point being greater than the preset threshold, starting the camera to capture the binary image of the carriage warning corresponding to the data point further includes: in response to the warning level of the data point not being greater than the preset threshold, continuing to maintain the standby state of the camera.

[0087] After obtaining the binary image of the carriage warning based on the above steps, the following steps are continued.

[0088] S5: Implement the safety transportation monitoring of the transport vehicle through the exclusive OR result of the initial binary image of the carriage and the warning binary image.

[0089] It should be noted that each pixel on the binary image has only two possible gray values. By comparing the gray values of the pixel points at the same position in the two binary images, the exclusive OR result of each pixel point can be obtained.

[0090] For example, by comparing the grayscale values of the pixels at the same position in the initial binary image of the carriage and the binary image of the alarm, when the XOR results of each pixel are obtained, if the grayscale values of the pixels at the same position are the same, the output is 0; if the grayscale values of the pixels at the same position are different, the output is 1.

[0091] It's understandable that the camera's position remains unchanged, so each pixel in the captured initial binary image of the carriage and the alarm binary image corresponds one-to-one. If the pixel output is 0, it indicates that the pixel has not changed between the initial binary image and the alarm binary image, and is therefore a normal pixel. Conversely, if the pixel output is 1, it indicates that the pixel has changed between the initial binary image and the alarm binary image, and is therefore an abnormal pixel.

[0092] For example, in an embodiment of the present invention, the XOR result of the initial binary image of the car and the alarm binary image includes: if the grayscale value of a pixel point in the initial binary image of the car and the corresponding pixel point in the alarm binary image are different, then the pixel point is an abnormal pixel point; otherwise, the pixel point is a normal pixel point.

[0093] After obtaining the XOR result of each pixel in the initial binary image of the carriage and the alarm binary image based on the above steps, the monitoring result of whether the cargo is tilted or offset can be obtained based on the XOR result of the pixel points.

[0094] For example, in an embodiment of the present invention, the safe transportation monitoring of the transport vehicle is realized by the XOR result of the initial binary image of the carriage and the alarm binary image, including: if the proportion of the number of abnormal pixels in the XOR result of the initial binary image of the carriage and the alarm binary image is greater than a preset abnormal threshold, the safe transportation monitoring result of the transport vehicle is abnormal; otherwise, the safe transportation monitoring result of the transport vehicle is normal; in response to the safe transportation monitoring result of the transport vehicle being abnormal, an abnormal voice warning is issued to the outside.

[0095] The preset abnormality threshold may be set to 0.3; the preset abnormality threshold may be set according to actual needs, and the embodiment of the present invention does not impose any excessive restrictions on this.

[0096] It can be understood that the proportion of abnormal pixel points is the ratio of the number of abnormal pixel points to the total number of pixels in the initial binary image of the carriage or the alarm binary image. The higher the ratio, the greater the proportion.

[0097] For example, in an embodiment of the present invention, safe transportation monitoring of transport vehicles is implemented, and then the method further includes: associating and storing data points with abnormal results of safe transportation monitoring of transport vehicles and alarm binary images corresponding to the data points in a database.

[0098] In this way, in the embodiment of the present invention, by associatively storing the abnormal monitoring results of the safe transportation of the transport vehicle and the corresponding images, subsequent accurate abnormal analysis can be performed based on this, thereby standardizing the behaviors of the staff.

[0099] It can be seen that in the embodiment of the present invention, when implementing the safe transportation monitoring of the transport vehicle, after collecting the initial binary image of the carriage, the camera standby state can be started, and the speed value and tilt angle corresponding to each data point in the time series sequence of the vehicle driving data can be obtained; based on the speed difference and tilt angle difference between the data point and the preset-length adjacent sequence, the warning level of the data point can be obtained; in response to the ascending order of the Euclidean distances between the data point and other data points, the target sequence of the data point can be constructed;

[0100] ;

[0101] 、 、 are respectively the warning level, the early warning level, and the acquisition time of the i-th data point, is the average value of the early warning levels of the target sequence of the i-th data point, is the length of the target sequence, is the acquisition time of the -th data point in the target sequence of the i-th data point, is the exponential function with e as the base, is the absolute value symbol; in response to the warning level of the data point being greater than the preset threshold, the camera is started to capture the warning binary image of the carriage corresponding to the data point; through the exclusive OR result of the initial binary image of the carriage and the warning binary image, the safe transportation monitoring of the transport vehicle can be realized, and the efficiency of the safe transportation monitoring of the transport vehicle can be effectively improved.

[0102] The embodiment of the present invention also discloses a safe transportation monitoring system for a transport vehicle, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a safe transportation monitoring method provided by the present invention is implemented.

[0103] The above system further includes other components well known to those skilled in the art such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be elaborated here.

[0104] In the present invention, the foregoing memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.

[0105] The above are all the preferred embodiments of the present invention. The protection scope of the present invention is not limited by this. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A safety transportation monitoring method for a transportation vehicle, characterized in that include: After collecting the initial binary image of the vehicle compartment, the camera is started in standby mode to obtain the speed value and tilt angle corresponding to each data point in the vehicle driving data time series; Based on the speed difference and tilt angle difference between the data point and the adjacent sequence of preset length, the warning level of the data point is obtained; In response to the ascending order of the Euclidean distance between a data point and other data points, a target sequence for the data point is constructed; based on the difference in warning levels and the difference in collection time between the data point and the data points in the target sequence, the alarm level of the data point is calculated: ； , , are respectively the alarm level, early warning level, and acquisition time of the i-th data point, is the average early warning level of the target sequence of the i-th data point, is the length of the target sequence, is the acquisition time of the -th data point in the target sequence of the i-th data point, is the exponential function with base e, is the absolute value symbol; In response to the alarm level of a data point being greater than a preset threshold, the camera is activated to capture the carriage alarm binary image corresponding to the data point; the safe transportation monitoring of the transport vehicle is achieved through the XOR result of the initial carriage binary image and the alarm binary image.

2. The safety transportation monitoring method for a transportation vehicle according to claim 1, wherein, The method of obtaining the speed value and tilt angle corresponding to each data point in the vehicle driving data time series sequence also includes: The speed data and tilt angle data of the vehicle obtained at each acquisition moment are taken as a data point, and the vehicle driving data time series is obtained after preprocessing.

3. The safety transportation monitoring method for a transportation vehicle according to claim 1, characterized in that The method of obtaining the warning level of a data point based on the speed difference and tilt angle difference between the data point and an adjacent sequence of a preset length includes: Obtain the absolute mean of the speed difference between the speed value of the data point and the speed values in the adjacent sequence, normalize the ratio of the absolute mean of the speed difference to the standard deviation of the speed of the adjacent sequence of the data point to obtain the speed mutation of the data point; obtain the inclination angle mutation of the data point; The sum of the product of the preset speed weight and the speed mutation of the data point and the product of the preset tilt angle weight and the tilt angle mutation of the data point is recorded as the warning level of the data point.

4. A safety transportation monitoring method for a transportation vehicle according to claim 1, characterized in that, The step of constructing a target sequence of the data point in response to the ascending order of the Euclidean distances between the data point and other data points comprises: The minimum Euclidean distance between a data point and other data points in ascending order is used as a starting point to obtain a preset number of other data points corresponding to the Euclidean distance as the target sequence of the data point.

5. A safety transportation monitoring method for a transportation vehicle according to claim 1, characterized in that, In response to the alarm level of the data point being greater than a preset threshold, starting the camera to capture the carriage alarm binary image corresponding to the data point further includes: In response to the alarm level of the data point being no greater than a preset threshold, the camera continues to be in a standby state.

6. The safety transportation monitoring method for a transportation vehicle according to claim 1, wherein The method for obtaining the carriage initial binary image and the warning binary image includes: The initial monitoring image and the alarm monitoring image collected by the camera are processed by an edge detection algorithm to obtain an initial binary image and an alarm binary image.

7. A safety transportation monitoring method for a transportation vehicle according to claim 1, characterized in that, The XOR result of the initial binary image of the carriage and the binary image of the warning includes: If the grayscale value of a pixel in the initial binary image of the carriage is different from the grayscale value of the corresponding pixel in the alarm binary image, the pixel is an abnormal pixel; otherwise, the pixel is a normal pixel.

8. The safety transportation monitoring method for a transportation vehicle according to claim 7, characterized in that, The method realizes safe transportation monitoring of transport vehicles by performing an exclusive OR operation of the initial binary image of the carriage and the binary image of the warning, including: If the proportion of abnormal pixel points in the XOR result of the initial binary image of the carriage and the alarm binary image is greater than the preset abnormal threshold, the transport safety monitoring result of the transport vehicle is abnormal; otherwise, the transport safety monitoring result of the transport vehicle is normal; In response to the abnormal result of the safe transportation monitoring of the transport vehicle, an abnormal voice warning is issued outward.

9. A safety transportation monitoring method for a transportation vehicle according to claim 1, characterized in that, After implementing the safe transportation monitoring of the transport vehicle, it further includes: Associatively storing the data points with abnormal results of the safe transportation monitoring of the transport vehicle and the corresponding warning binary images of the data points in a database.

10. A safety transportation monitoring system for a transportation vehicle, characterized in that, It includes: A processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for safe transportation monitoring of a transport vehicle according to any one of claims 1-9 is implemented.

Images