Cargo patrol supervision method and system based on unmanned aerial vehicle

Abstract

The invention is suitable for the technical field of cargo management, and particularly relates to a cargo patrol supervision method and system based on an unmanned aerial vehicle, and the method comprises the steps: scanning a cargo, and constructing a cargo storage basic model; constructing an inspection virtual route, and controlling the unmanned aerial vehicle to move along the inspection virtual route; constructing a path control random function, controlling the flight height change of the unmanned aerial vehicle according to the path control random function, and scanning the goods to obtain real-time scanning data; and a simulation path is generated, simulation scanning data is generated according to the simulation path, and a cargo inspection result is generated through comparison. In the inspection process, the unmanned aerial vehicle randomly scans the goods along the random path, so that the scanning data corresponding to each goods model is obtained, whether abnormity exists or not is judged based on the scanning data, the labor intensity is greatly reduced, goods supervision on a large-area site can be realized, and the safety of the goods is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of cargo management, and in particular relates to a cargo inspection and supervision method and system based on drones. Background Art

[0002] Cargo inspection and supervision involves real-time monitoring and management of cargo during storage and transportation through a range of technical and management measures to ensure its safety, integrity, and compliance. This includes the use of technologies such as RFID, GPS, and IoT sensors to track cargo location, status, and environmental conditions, as well as regular manual inspections and audits to prevent and identify potential risks, ensuring smooth supply chain operations and cargo quality.

[0003] In the current cargo storage management process, due to the large area of the site, manual inspection is impossible and it is difficult to ensure the safety of the cargo. Summary of the Invention

[0004] The purpose of the present invention is to provide a cargo inspection and supervision method based on drones, aiming to solve the problem in the current cargo storage management process that due to the large site area, manual inspection is impossible and the safety of the cargo is difficult to ensure.

[0005] The present invention is implemented as follows: a cargo inspection and supervision method based on a drone, the method comprising:

[0006] Scan the cargo and build a cargo storage basic model, wherein the cargo storage basic model includes a site model and a cargo model;

[0007] Build a virtual inspection route based on the basic cargo storage model and control the drone to move along the virtual inspection route;

[0008] When the drone inspects the corresponding cargo model, a path control random function is constructed. According to the path control random function, the drone's flight altitude is controlled to scan the cargo and obtain real-time scanning data.

[0009] Based on the flight path of the drone, a corresponding simulation path is generated in the cargo storage basic model. Simulated scanning data is generated according to the simulation path, and the cargo inspection results are generated through comparison.

[0010] Preferably, the steps of constructing a virtual inspection route based on the cargo storage basic model and controlling the drone to move along the virtual inspection route specifically include:

[0011] Generate a cargo storage plan based on the cargo storage basic model, and divide the cargo storage plan into areas according to the location of the cargo model to obtain cargo areas and idle areas;

[0012] Count the number of pixels contained in each cargo area in the cargo storage plan, generate regional pixel coordinates, perform function fitting based on the regional pixel coordinates, and generate a random function for the inspection order. The horizontal coordinate of the regional pixel coordinate is the cargo area number, and the vertical coordinate is the number of pixels contained in the cargo area.

[0013] Import a preset natural number sequence, determine the inspection order based on the calculated value, generate a virtual inspection route, and control the drone to move along the virtual inspection route.

[0014] Preferably, when the drone inspects the corresponding cargo model, the steps of constructing a path control random function, controlling the flight altitude change of the drone according to the path control random function, scanning the cargo, and obtaining real-time scanning data specifically include:

[0015] When the UAV inspects the corresponding cargo model, it flies to randomly select a set of functions from the pre-equipment selection functions as the path control random function;

[0016] Use the current time value as a random variable, import it into the path control random function, obtain the variable calculation value, and intercept it into multiple types of strings according to the preset interception method;

[0017] A spiral line is generated according to the size of the cargo model, and the detection starting point and pitch are determined based on the character string to obtain a scanning spiral line. The drone scans along the scanning spiral line to obtain real-time scanning data.

[0018] Preferably, the steps of generating a corresponding simulated path in the cargo storage basic model based on the flight path of the drone, generating simulated scanning data according to the simulated path, and generating cargo inspection results by comparison specifically include:

[0019] Generate a corresponding simulation path in the cargo storage basic model based on the UAV's flight path, and obtain the ranging angle of the UAV at each position on the simulation path;

[0020] Calculate the distance between each point on the simulated path and the cargo model at the corresponding ranging angle to obtain simulated scanning data;

[0021] The simulated scan data is compared with the real-time scan data one by one, the model matching rate is calculated, and the cargo inspection results are generated based on the preset threshold range.

[0022] Preferably, when the model matching rate is lower than a preset value, the corresponding cargo model is captured by a drone for image or video capture, which is entered into the cargo inspection results, and a warning message is issued.

[0023] Another object of the present invention is to provide a cargo inspection and supervision system based on a drone, the system comprising:

[0024] A model building module is used to scan the cargo and build a basic cargo storage model, wherein the basic cargo storage model includes a site model and a cargo model;

[0025] The inspection route generation module is used to build a virtual inspection route based on the basic cargo storage model and control the drone to move along the virtual inspection route;

[0026] The real-time scanning module is used to construct a path control random function when the drone inspects the corresponding cargo model, control the flight altitude of the drone according to the path control random function, scan the cargo, and obtain real-time scanning data;

[0027] The result analysis module is used to generate a corresponding simulation path in the cargo storage basic model based on the UAV's flight path, generate simulated scanning data according to the simulated path, and generate cargo inspection results through comparison.

[0028] Preferably, the inspection route generation module includes:

[0029] An area division unit is used to generate a cargo storage plan based on the cargo storage basic model, and divide the cargo storage plan into areas according to the positions of the cargo models to obtain cargo areas and idle areas;

[0030] A random function generation unit is used to count the number of pixels contained in each cargo area in the cargo storage plan, generate regional pixel coordinates, perform function fitting based on the regional pixel coordinates, and generate an inspection order random function, where the horizontal coordinate of the regional pixel coordinates is the cargo area number and the vertical coordinate is the number of pixels contained in the cargo area;

[0031] The path generation unit is used to import a preset natural number sequence, determine the inspection order according to the calculated value, generate a virtual inspection route, and control the drone to move along the virtual inspection route.

[0032] Preferably, the real-time scanning module includes:

[0033] The function selection unit is used to randomly select a set of functions from the pre-selected functions as the path control random function when the UAV inspects the corresponding cargo model;

[0034] A string interception unit is used to use the current time value as a random variable, import it into the path control random function, obtain the variable calculation value, and intercept it into multiple types of strings according to a preset interception method;

[0035] The real-time scanning unit is used to generate a spiral line according to the size of the cargo model, determine the detection starting point and pitch based on the character string, and obtain a scanning spiral line. The drone scans along the scanning spiral line to obtain real-time scanning data.

[0036] Preferably, the result analysis module includes:

[0037] A ranging information acquisition unit is used to generate a corresponding simulated path in the cargo storage basic model based on the flight path of the UAV and obtain the ranging angle of the UAV at each position on the simulated path;

[0038] A simulation scanning unit is used to calculate the distance between each point on the simulation path and the cargo model at the corresponding ranging angle to obtain simulation scanning data;

[0039] The inspection judgment unit is used to compare the simulated scan data with the real-time scan data one by one, calculate the model matching rate, and generate the cargo inspection results based on the preset threshold range.

[0040] Preferably, when the model matching rate is lower than a preset value, the corresponding cargo model is captured by a drone using images or videos, which are entered into the cargo inspection results, and a warning message is issued.

[0041] The present invention provides a cargo inspection and supervision method based on drones, which establishes a basic cargo storage model based on the cargo that needs to be supervised. In the subsequent inspection process, the drone randomly scans the cargo along a random path to obtain scanning data corresponding to each cargo model, and determines whether there are any abnormalities based on the scanning data, which greatly reduces labor intensity, enables cargo supervision over a large area, and ensures the safety of the cargo. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flowchart of a cargo inspection and supervision method based on drones provided in an embodiment of the present invention;

[0043] Figure 2 A flowchart of the steps of constructing a virtual inspection route based on a basic cargo storage model and controlling the movement of a drone along the virtual inspection route provided by an embodiment of the present invention;

[0044] Figure 3 A flowchart of the steps of constructing a path control random function, controlling the flight altitude of the drone according to the path control random function, scanning the cargo, and obtaining real-time scanning data when the drone inspects the corresponding cargo model, provided in an embodiment of the present invention;

[0045] Figure 4A flowchart of the steps of generating a corresponding simulated path in a cargo storage basic model based on the flight path of a drone provided in an embodiment of the present invention, generating simulated scanning data based on the simulated path, and generating cargo inspection results by comparing the simulated scan data;

[0046] Figure 5 An architecture diagram of a drone-based cargo inspection and supervision system provided in an embodiment of the present invention;

[0047] Figure 6 An architectural diagram of an inspection route generation module provided in an embodiment of the present invention;

[0048] Figure 7 An architectural diagram of a real-time scanning module provided by an embodiment of the present invention;

[0049] Figure 8 This is an architectural diagram of a result analysis module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0051] like Figure 1 FIG. 1 is a flow chart of a method for cargo inspection and supervision based on a drone according to an embodiment of the present invention, the method comprising:

[0052] S100 , scanning cargo and constructing a cargo storage basic model, wherein the cargo storage basic model includes a site model and a cargo model.

[0053] In this step, the goods are scanned. When scanning, drones can be used for scanning, or manual scanning and modeling can be performed. Using drones for modeling is more efficient. Specifically, the drone is equipped with a high-precision camera, lidar, and GNSS positioning module. After determining the area to be scanned, the specific location of the goods is marked. Each pile of goods is scanned to construct a corresponding model in the three-dimensional model to obtain a basic model of goods storage. The modeling method can use lidar scanning modeling or a visual solution, such as multi-view geometry technology, to reconstruct the three-dimensional structure of the scene from multiple images taken from different angles, including feature detection and matching, camera calibration, and three-dimensional reconstruction steps, such as SfM (Structure from Motion) and MVS (Multi-View Stereo). The above modeling method is a commonly used technical means in this field, so it will not be repeated here.

[0054] S200 builds a virtual inspection route based on the basic cargo storage model and controls the drone to move along the virtual inspection route.

[0055] In this step, a virtual inspection route is constructed based on the basic model of cargo storage. During the inspection, the inspection effect is achieved by a drone. However, if a fixed path is used for inspection, it is easy for illegal elements to find the inspection pattern, causing them to evade the drone based on the inspection pattern. The present invention generates regional pixel coordinates based on the images corresponding to each cargo model in the basic model of cargo storage. Since the stacking method of different cargoes is random, the amount of pixels they occupy is also random, and the obtained regional pixel coordinates are also random. Function fitting is performed based on the obtained multiple groups of regional pixel coordinates to obtain a group of inspection order random functions. The order of inspecting each cargo model is determined based on the inspection order random function. Since the inspection order is not fixed, the time for inspecting each cargo model is also different, making it impossible for illegal elements to grasp the inspection time and making it impossible for them to evade. After generating the virtual inspection route, the drone is controlled to move along the virtual inspection route, and in the process, the cargo model is scanned.

[0056] S300, when the UAV inspects the corresponding cargo model, a path control random function is constructed, and the flight altitude of the UAV is controlled according to the path control random function to scan the cargo and obtain real-time scanning data.

[0057] In this step, when the UAV inspects the corresponding cargo model, a path control random function is constructed. When scanning, the UAV is used to carry a laser radar to scan, thereby measuring the distance between the UAV and the cargo model. During the scanning process, the path control random function is randomly selected and used to control the scanning path of the cargo model. When scanning, a spiral ascent is used to scan, and the path control random function is used to change the pitch of the spiral ascent. Since the pitch is randomly generated and the starting position is different, the path of each scan is random. While ensuring the sampling effect, the number of sampling points is greatly reduced, the power consumption of the UAV is reduced, and the endurance of the UAV is improved. The scanned data is saved to obtain real-time scanning data.

[0058] S400: Generate a corresponding simulated path in the cargo storage basic model based on the drone's flight path, generate simulated scanning data based on the simulated path, and generate cargo inspection results through comparison.

[0059] In this step, a corresponding simulation path is generated in the cargo storage basic model based on the flight path of the drone, the position of the drone is obtained in real time, and its corresponding position in the cargo storage basic model is determined according to the real-time position of the drone. The parameters of the drone during the scanning process, including the scanning angle, are obtained to simulate the corresponding scanning process in the cargo storage basic model, and the distance between the drone and the cargo model is calculated to obtain simulated scanning data. The simulated scanning data is compared with the real-time scanning data to determine whether there is any change in the current cargo. If there is a change, it is determined that there is an abnormality, and the drone is used to collect images or videos of the corresponding cargo model, which are entered into the cargo inspection results and a warning message is issued.

[0060] like Figure 2 As shown, as a preferred embodiment of the present invention, the steps of constructing a virtual inspection route based on the cargo storage basic model and controlling the drone to move along the virtual inspection route specifically include:

[0061] S201 , generating a cargo storage plan based on a cargo storage basic model, and dividing the cargo storage plan into regions according to the positions of the cargo models to obtain cargo areas and idle areas.

[0062] In this step, a cargo storage plan is generated based on the cargo storage basic model. The cargo storage plan is a top view and is divided according to the location of the cargo. Specifically, image recognition technology is used to identify the location of the cargo and divide it into cargo areas. The area excluding the cargo area is the idle area. During scanning, the drone can pass through the idle area.

[0063] S202, counting the number of pixels contained in each cargo area in the cargo storage plan, generating regional pixel coordinates, performing function fitting based on the regional pixel coordinates, and generating an inspection order random function, where the horizontal coordinate of the regional pixel coordinates is the cargo area number, and the vertical coordinate is the number of pixels contained in the cargo area.

[0064] In this step, the number of pixels contained in each cargo area in the cargo storage plan is counted, and each cargo area is numbered. The number can be a natural number, such as 1, 2, 3, etc., and then the number of pixels contained in each cargo area is counted. For example, cargo area No. 1 contains 198723 pixels, and cargo area No. 2 contains 284374 pixels. Based on this, a regional pixel coordinate is constructed for each cargo area, such as (1, 1987). A preset number of regional pixel coordinates are selected, such as randomly selecting 5 regional pixel coordinates, (1, 1987), (3, 2612), (5, 2387), (4, 1885) and (7, 2081). Then, a function is fitted based on the above 5 regional pixel coordinates to obtain a random function of the inspection order.

[0065] S203, importing a preset natural number sequence, determining an inspection order according to the calculated value, generating an inspection virtual route, and controlling the UAV to move along the inspection virtual route.

[0066] In this step, a preset natural number sequence is imported and imported into the inspection order random function, thereby generating a calculated value through the inspection order random function, and the calculated value is continuously spliced to obtain a spliced string. The spliced string is searched in the spliced string according to the splicing order, and the order of appearance of the numbers corresponding to each cargo area is extracted. If the maximum number of the cargo area does not exceed two digits, the spliced string is split into multiple short strings consisting of two decimal characters to determine the order of appearance of each cargo area. The inspection order is determined according to the order of appearance of each cargo area. If the numbers of all cargo areas are found at the 1283rd character, the first 1283 characters are discarded, and all remaining characters in the spliced string are retained for use in determining the inspection order during the next inspection. After determining the order in which the drone inspects each cargo area, the corresponding inspection virtual route is generated, and the drone is controlled to move along the inspection virtual route.

[0067] like Figure 3 As shown, as a preferred embodiment of the present invention, when the drone inspects the corresponding cargo model, the steps of constructing a path control random function, controlling the flight altitude change of the drone according to the path control random function, scanning the cargo, and obtaining real-time scanning data specifically include:

[0068] S301, when the UAV inspects the corresponding cargo model, it flies to randomly select a set of functions from the pre-equipment selection functions as the path control random function.

[0069] In this step, when the drone inspects the corresponding cargo model, it queries the preset alternative function database, which stores multiple preset random functions. When called, one group of random functions is selected as the path control random function. The path control random function is used to determine the path for the drone to scan the cargo.

[0070] S302: Using the current time value as a random variable, importing it into the path control random function to obtain a variable calculation value, and intercepting it into multiple types of character strings according to a preset interception method.

[0071] In this step, the current time value is used as a random variable to import the path control random function, thereby calculating a calculated value, which is defined as the path control calculated value. It is cut and divided into three parts, namely the first value P1, the second value P2 and the third value P3, where the third value P3 is a two-digit number.

[0072] S303: Generate a spiral line according to the size of the cargo model, determine the detection starting point and pitch based on the character string, and obtain a scanning spiral line. The drone scans along the scanning spiral line to obtain real-time scanning data.

[0073] In this step, a spiral is generated according to the size of the cargo model. The spiral is a cylindrical spiral. Specifically, the starting point is determined, a minimum inscribed circle is constructed according to the currently inspected cargo area, and an equidistant circle is constructed based on the minimum inscribed circle. The radius difference between the equidistant circle and the minimum inscribed circle is R0. Taking the due north direction of the equidistant circle as the starting point, the starting point offset angle θ is calculated as (360*P1) / (P1+P2). Starting from the due north direction, the equidistant circle is offset clockwise by θ. The position where the equidistant circle is located at the starting point offset angle θ is the starting point of the spiral. The radius of the equidistant circle is the radius of the spiral. The pitch L is calculated as L0*P3 / 100, where L0 is the preset pitch. The radius of the generated spiral is equal to the radius of the equidistant circle. The pitch of the spiral is L, and a scanning spiral is obtained. The drone flies along the scanning spiral to determine the center of mass of the cargo area. When scanning, the drone uses laser ranging. The center of mass of the cargo area is always located on the laser beam, thereby generating multiple ranging results and obtaining real-time scanning data.

[0074] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of generating a corresponding simulated path in the cargo storage basic model based on the flight path of the drone, generating simulated scanning data according to the simulated path, and generating cargo inspection results by comparison specifically include:

[0075] S401: Generate a corresponding simulation path in the cargo storage basic model based on the flight path of the drone, and obtain the ranging angle of the drone at each position on the simulation path.

[0076] S402 , calculating the distance between each point on the simulated path and the cargo model at the corresponding ranging angle to obtain simulated scanning data.

[0077] In this step, a corresponding simulation path is generated in the cargo storage basic model based on the UAV's flight path. That is, the simulation path is the same as the scanning spiral. A simulated measurement ray is generated in the cargo storage basic model. The starting point of the simulated measurement ray is the position of the UAV on the simulation path. The simulated measurement ray will pass through the center of mass of the cargo area. The distance value between the simulated measurement ray from the UAV to the cargo model is counted and used as the simulated scanning data.

[0078] S403 , comparing the simulated scan data with the real-time scan data one by one, calculating the model matching rate, and generating the cargo inspection results based on the preset threshold range.

[0079] In this step, the simulated scanning data is compared with the real-time scanning data one by one to determine the scanning point position corresponding to the real-time scanning data, and the data matching it is selected in the simulated scanning data to compare whether the distance values contained in the two are the same. The difference between the two is calculated. If the difference is greater than the preset value, it is determined that there is a scanning error in the scanning point, and the model matching rate is calculated. The model matching rate is the ratio between the number of scanning points with scanning errors and the total number of scanning points. The cargo inspection results are generated based on the preset threshold interval. If the model matching rate exceeds the preset threshold interval, it is determined that there is an abnormality. At this time, the drone is controlled to collect images or videos of the corresponding cargo.

[0080] like Figure 5 As shown in FIG, a cargo inspection and supervision system based on a drone is provided in an embodiment of the present invention, and the system includes:

[0081] The model building module 100 is used to scan the cargo and build a cargo storage basic model, which includes a site model and a cargo model.

[0082] In this system, the model building module 100 scans the goods. When scanning, drones can be used for scanning, or manual scanning and modeling can be performed. Using drones for modeling is more efficient. Specifically, the drone is equipped with a high-precision camera, a lidar, and a GNSS positioning module. After determining the area to be scanned, the specific location of the goods is marked. Each pile of goods is scanned to build a corresponding model in the three-dimensional model to obtain a basic model of goods storage. The modeling method can use lidar scanning modeling or a visual solution, such as multi-view geometry technology, to reconstruct the three-dimensional structure of the scene from multiple images taken from different angles, including feature detection and matching, camera calibration, and three-dimensional reconstruction steps, such as SfM (Structure from Motion) and MVS (Multi-View Stereo). The above modeling method is a commonly used technical means in this field, so it will not be repeated here.

[0083] The inspection route generation module 200 is used to construct an inspection virtual route based on the cargo storage basic model and control the UAV to move along the inspection virtual route.

[0084] In this system, the inspection route generation module 200 constructs an inspection virtual route based on the cargo storage basic model. During the inspection, the inspection effect is achieved by a drone. However, if a fixed path is used for inspection, it is easy for illegal elements to find the inspection pattern, causing them to evade the drone based on the inspection pattern. The present invention generates regional pixel coordinates based on the image corresponding to each cargo model in the cargo storage basic model. Since the stacking method of different cargoes is random, the number of pixels they occupy is also random, and the obtained regional pixel coordinates are also random. Function fitting is performed based on the obtained multiple groups of regional pixel coordinates to obtain a group of inspection sequence random functions. The order of inspecting each cargo model is determined based on the inspection sequence random function. Since the inspection order is not fixed, the time for inspecting each cargo model is also different, making it impossible for illegal elements to grasp the inspection time and making it impossible for them to evade. After the inspection virtual route is generated, the drone is controlled to move along the inspection virtual route and scan the cargo model in the process.

[0085] The real-time scanning module 300 is used to construct a path control random function when the drone inspects the corresponding cargo model, control the flight altitude change of the drone according to the path control random function, scan the cargo, and obtain real-time scanning data.

[0086] In this system, the real-time scanning module 300 constructs a path control random function when the drone inspects the corresponding cargo model. When scanning, the drone carries a laser radar to scan, thereby measuring the distance value between the drone and the cargo model. During the scanning process, the path control random function is randomly selected and used to control the scanning path of the cargo model. When scanning, a spiral ascent method is used. The path control random function is used to change the pitch of the spiral ascent. Since the pitch is randomly generated and the starting position is different, the path of each scan is random. While ensuring the sampling effect, the number of sampling points is greatly reduced, the power consumption of the drone is reduced, and the endurance of the drone is improved. The scanned data is saved to obtain real-time scanning data.

[0087] The result analysis module 400 is used to generate a corresponding simulated path in the cargo storage basic model based on the flight path of the drone, generate simulated scanning data according to the simulated path, and generate cargo inspection results by comparing.

[0088] In this system, the result analysis module 400 generates a corresponding simulation path in the cargo storage basic model based on the flight path of the drone, obtains the position of the drone in real time, determines its corresponding position in the cargo storage basic model according to the real-time position of the drone, obtains the parameters of the drone during the scanning process, including the scanning angle, thereby simulating the corresponding scanning process in the cargo storage basic model, calculates the distance between the drone and the cargo model to obtain simulated scanning data, compares the simulated scanning data with the real-time scanning data to determine whether there is any change in the current cargo. If there is a change, it is determined that there is an abnormality, and the drone is used to collect images or videos of the corresponding cargo model, which are entered into the cargo inspection results and a warning message is issued.

[0089] like Figure 6 As shown, as a preferred embodiment of the present invention, the inspection route generation module 200 includes:

[0090] The area division unit 201 is used to generate a cargo storage plan based on the cargo storage basic model, and divide the cargo storage plan into areas according to the positions of the cargo models to obtain cargo areas and idle areas.

[0091] In this module, the area division unit 201 generates a cargo storage plan based on the cargo storage basic model. The cargo storage plan is a top view and is divided according to the location of the cargo. Specifically, image recognition technology is used to identify the location of the cargo and divide it into cargo areas. The area excluding the cargo area is an idle area. During scanning, the drone can pass through the idle area.

[0092] The random function generating unit 202 is configured to count the number of pixels contained in each cargo area in the cargo storage plan, generate the area pixel coordinates, perform function fitting based on the area pixel coordinates, and generate a random function for the inspection order, where the abscissa of the area pixel coordinates is the cargo area number, and the ordinate is the number of pixels contained in the cargo area.

[0093] In this module, the random function generating unit 202 counts the number of pixels contained in each cargo area in the cargo storage plan, and numbers each cargo area. The number can be a natural number, such as 1, 2, 3, etc., and then counts the number of pixels contained in each cargo area. For example, cargo area No. 1 contains 198723 pixels, and cargo area No. 2 contains 284374 pixels. Based on this, a regional pixel coordinate is constructed for each cargo area, such as (1, 1987). A preset number of regional pixel coordinates are selected, such as randomly selecting 5 regional pixel coordinates, (1, 1987), (3, 2612), (5, 2387), (4, 1885), and (7, 2081). Then, a function is fitted based on the above 5 regional pixel coordinates to obtain a random function of the inspection order.

[0094] The path generation unit 203 is used to import a preset natural number sequence, determine the inspection order according to the calculated value, generate an inspection virtual route, and control the UAV to move along the inspection virtual route.

[0095] In this module, the path generation unit 203 imports a preset natural number sequence, imports the natural number sequence into the inspection order random function, thereby generating a calculated value through the inspection order random function, continuously splicing the calculated value to obtain a spliced string, searching in the spliced string according to the splicing order, and extracting the order of appearance of the numbers corresponding to each cargo area. If the maximum number of the cargo area does not exceed two digits, the spliced string is split into multiple short strings consisting of two decimal characters to determine the order of appearance of each cargo area. The inspection order is determined according to the order of appearance of each cargo area. If the numbers of all cargo areas are found at the 1283rd character, the first 1283 characters are discarded, and all remaining characters in the spliced string are retained for use in determining the inspection order during the next inspection. After determining the order in which the drone inspects each cargo area, a corresponding inspection virtual route is generated, and the drone is controlled to move along the inspection virtual route.

[0096] like Figure 7 As shown, as a preferred embodiment of the present invention, the real-time scanning module 300 includes:

[0097] The function selection unit 301 is used to randomly select a group of functions from the pre-selected functions as the path control random function when the UAV inspects the corresponding cargo model.

[0098] In this module, the function selection unit 301 queries the preset alternative function database when the drone inspects the corresponding cargo model. Multiple preset random functions are stored in the alternative function database. When called, one group of random functions is selected as the path control random function. The path control random function is used to determine the path for the drone to scan the cargo.

[0099] The character string interception unit 302 is used to use the current time value as a random variable, import it into the path control random function, obtain the variable calculation value, and intercept it into multiple types of character strings according to a preset interception method.

[0100] In this module, the string interception unit 302 uses the current time value as a random variable to import the path control random function, thereby calculating a calculated value, which is defined as the path control calculated value, and is intercepted and divided into three parts, namely the first value P1, the second value P2 and the third value P3, where the third value P3 is a two-digit number.

[0101] The real-time scanning unit 303 is used to generate a spiral line according to the size of the cargo model, determine the detection starting point and pitch based on the character string, and obtain a scanning spiral line. The drone scans along the scanning spiral line to obtain real-time scanning data.

[0102] In this module, the real-time scanning unit 303 generates a spiral line according to the size of the cargo model. The spiral line is a cylindrical spiral line. Specifically, the starting point position is determined, and a minimum inscribed circle is constructed according to the cargo area currently being inspected. The equidistant circle is constructed based on the minimum inscribed circle. The radius difference between the equidistant circle and the minimum inscribed circle is R0. The north direction of the equidistant circle is used as the starting point, and the starting point offset angle θ=(360*P1) / (P1+P2) is calculated. Starting from the north direction, the equidistant circle is offset clockwise by θ, and the equidistant circle is located at the starting point offset angle. The position at angle θ is the starting point of the spiral, and the radius of the equidistant circle is the radius of the spiral. The pitch L is calculated as L0*P3 / 100, where L0 is the preset pitch. The radius of the generated spiral is equal to the radius of the equidistant circle. The pitch of the spiral is L, and a scanning spiral is obtained. The drone flies along the scanning spiral to determine the center of mass of the cargo area. When scanning, the drone uses laser ranging. The center of mass of the cargo area is always located on the laser beam, thereby generating multiple ranging results and obtaining real-time scanning data.

[0103] like Figure 8 As shown, as a preferred embodiment of the present invention, the result analysis module 400 includes:

[0104] The ranging information acquisition unit 401 is used to generate a corresponding simulated path in the cargo storage basic model based on the flight path of the drone, and obtain the ranging angle of the drone at each position on the simulated path.

[0105] The simulation scanning unit 402 is used to calculate the distance between each point on the simulation path and the cargo model at the corresponding ranging angle to obtain simulation scanning data.

[0106] In this module, the ranging information acquisition unit 401 generates a corresponding simulation path in the cargo storage basic model based on the flight path of the UAV. That is, the simulation path is the same as the scanning spiral line. A simulated measurement ray is generated in the cargo storage basic model. The starting point of the simulated measurement ray is the position of the UAV on the simulation path. The simulated measurement ray will pass through the center of mass of the cargo area. The distance value between the simulated measurement ray from the UAV to the cargo model is counted and used as the simulated scanning data.

[0107] The inspection determination unit 403 is used to compare the simulated scan data with the real-time scan data one by one, calculate the model matching rate, and generate the cargo inspection result based on the preset threshold range.

[0108] In this module, the inspection judgment unit 403 compares the simulated scanning data with the real-time scanning data one by one, determines the scanning point position corresponding to the real-time scanning data, selects the data that matches it in the simulated scanning data, compares whether the distance values contained in the two are the same, and calculates the difference between the two. If the difference is greater than the preset value, it is determined that there is a scanning error in the scanning point, and the model matching rate is calculated. The model matching rate is the ratio between the number of scanning points with scanning errors and the total number of scanning points. The cargo inspection results are generated based on the preset threshold interval. If the model matching rate exceeds the preset threshold interval, it is determined that there is an abnormality. At this time, the drone is controlled to perform image or video acquisition on the corresponding cargo.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A cargo inspection and supervision method based on drones, characterized in that: The method comprises: Scan the cargo and build a cargo storage basic model, wherein the cargo storage basic model includes a site model and a cargo model; Build a virtual inspection route based on the basic cargo storage model and control the drone to move along the virtual inspection route; When the drone inspects the corresponding cargo model, a path control random function is constructed. According to the path control random function, the drone's flight altitude is controlled to scan the cargo and obtain real-time scanning data. Based on the flight path of the drone, a corresponding simulation path is generated in the cargo storage basic model. Simulated scanning data is generated according to the simulation path, and the cargo inspection results are generated through comparison.

2. The cargo inspection and supervision method based on drone according to claim 1 is characterized in that: The steps of constructing a virtual inspection route based on the cargo storage basic model and controlling the drone to move along the virtual inspection route specifically include: Generate a cargo storage plan based on the cargo storage basic model, and divide the cargo storage plan into areas according to the location of the cargo model to obtain cargo areas and idle areas; Count the number of pixels contained in each cargo area in the cargo storage plan, generate regional pixel coordinates, perform function fitting based on the regional pixel coordinates, and generate a random function for the inspection order. The horizontal coordinate of the regional pixel coordinate is the cargo area number, and the vertical coordinate is the number of pixels contained in the cargo area. Import a preset natural number sequence, determine the inspection order based on the calculated value, generate a virtual inspection route, and control the drone to move along the virtual inspection route.

3. The cargo inspection and supervision method based on drone according to claim 1 is characterized in that: When the drone inspects the corresponding cargo model, the steps of constructing a path control random function, controlling the flight altitude of the drone according to the path control random function, scanning the cargo, and obtaining real-time scanning data specifically include: When the UAV inspects the corresponding cargo model, it flies to randomly select a set of functions from the pre-equipment selection functions as the path control random function; Use the current time value as a random variable, import it into the path control random function, obtain the variable calculation value, and intercept it into multiple types of strings according to the preset interception method; A spiral line is generated according to the size of the cargo model, and the detection starting point and pitch are determined based on the character string to obtain a scanning spiral line. The drone scans along the scanning spiral line to obtain real-time scanning data.

4. The cargo inspection and supervision method based on drone according to claim 1 is characterized in that: The steps of generating a corresponding simulated path in the cargo storage basic model based on the flight path of the drone, generating simulated scanning data according to the simulated path, and generating cargo inspection results by comparison specifically include: Generate a corresponding simulation path in the cargo storage basic model based on the UAV's flight path, and obtain the ranging angle of the UAV at each position on the simulation path; Calculate the distance between each point on the simulated path and the cargo model at the corresponding ranging angle to obtain simulated scanning data; The simulated scan data is compared with the real-time scan data one by one, the model matching rate is calculated, and the cargo inspection results are generated based on the preset threshold range.

5. The cargo inspection and supervision method based on drone according to claim 4 is characterized in that: When the model matching rate is lower than the preset value, the drone will collect images or videos of the corresponding cargo model, enter them into the cargo inspection results, and issue a warning message.

6. A cargo inspection and supervision system based on drones, characterized in that: The system comprises: A model building module is used to scan the cargo and build a basic cargo storage model, wherein the basic cargo storage model includes a site model and a cargo model; The inspection route generation module is used to build a virtual inspection route based on the basic cargo storage model and control the drone to move along the virtual inspection route; The real-time scanning module is used to construct a path control random function when the drone inspects the corresponding cargo model, control the flight altitude of the drone according to the path control random function, scan the cargo, and obtain real-time scanning data; The result analysis module is used to generate a corresponding simulation path in the cargo storage basic model based on the UAV's flight path, generate simulated scanning data according to the simulated path, and generate cargo inspection results through comparison.

7. The cargo inspection and supervision system based on drones according to claim 6 is characterized in that: The inspection route generation module includes: An area division unit is used to generate a cargo storage plan based on the cargo storage basic model, and divide the cargo storage plan into areas according to the positions of the cargo models to obtain cargo areas and idle areas; A random function generation unit is used to count the number of pixels contained in each cargo area in the cargo storage plan, generate regional pixel coordinates, perform function fitting based on the regional pixel coordinates, and generate an inspection order random function, where the horizontal coordinate of the regional pixel coordinates is the cargo area number and the vertical coordinate is the number of pixels contained in the cargo area; The path generation unit is used to import a preset natural number sequence, determine the inspection order according to the calculated value, generate a virtual inspection route, and control the drone to move along the virtual inspection route.

8. The cargo inspection and supervision system based on drones according to claim 6 is characterized in that: The real-time scanning module includes: The function selection unit is used to randomly select a set of functions from the pre-selected functions as the path control random function when the UAV inspects the corresponding cargo model; A string interception unit is used to use the current time value as a random variable, import it into the path control random function, obtain the variable calculation value, and intercept it into multiple types of strings according to a preset interception method; The real-time scanning unit is used to generate a spiral line according to the size of the cargo model, determine the detection starting point and pitch based on the character string, and obtain a scanning spiral line. The drone scans along the scanning spiral line to obtain real-time scanning data.

9. The cargo inspection and supervision system based on drones according to claim 6 is characterized in that: The result analysis module includes: A ranging information acquisition unit is used to generate a corresponding simulated path in the cargo storage basic model based on the flight path of the UAV and obtain the ranging angle of the UAV at each position on the simulated path; A simulation scanning unit is used to calculate the distance between each point on the simulation path and the cargo model at the corresponding ranging angle to obtain simulation scanning data; The inspection judgment unit is used to compare the simulated scan data with the real-time scan data one by one, calculate the model matching rate, and generate the cargo inspection results based on the preset threshold range.

10. The cargo inspection and supervision system based on drones according to claim 9 is characterized in that: When the model matching rate is lower than the preset value, the drone will collect images or videos of the corresponding cargo model, enter them into the cargo inspection results, and issue a warning message.

Images