Discharging state detection method, device and equipment and storage medium

Abstract

The invention discloses an unloading state detection method and device, equipment and a storage medium, and relates to the technical field of automatic driving. The unloading state detection method comprises the steps of obtaining first point cloud data of a region of interest of a first radar point cloud image collected by a laser radar installed at a vehicle target position under the condition of determining that a vehicle is executing an unloading task; according to the first point cloud data, determining ground plane parameters corresponding to the ground plane of the region of interest and ground plane point cloud data; determining mineral aggregate point cloud data in the first point cloud data according to the ground plane parameters under the condition that the ground plane parameters and the ground plane point cloud data meet preset ground plane conditions; and according to the mineral aggregate point cloud data and the ground plane point cloud data, a target unloading state of the vehicle is determined, and the target unloading state is used for indicating whether the vehicle completes an unloading task at the acquisition moment of the first radar point cloud image or not.

Description

Technical Field

[0001] The present application belongs to the field of autonomous driving technology, and in particular relates to a method, device, equipment and storage medium for detecting a discharge state. Background Art

[0002] With the popularization of 5G+ industrial Internet and artificial intelligence (AI) technology, autonomous driving has entered a stage of rapid development. The layout of many companies in the autonomous driving of mining trucks has achieved initial results, and can realize the loading and unloading of mineral materials according to the predetermined trajectory and destination. At the same time, the detection of the completion of mineral unloading is also of great significance to the autonomous driving of mining trucks.

[0003] In the existing method, a weight sensor is installed on the mining truck, and weight data collected by the weight sensor is used to detect whether the mining truck has been unloaded.

[0004] However, this method cannot accurately detect whether the ore has been completely unloaded when there is only a small amount of ore in the mine truck, resulting in poor detection accuracy. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and storage medium for detecting a discharge state, which can improve the accuracy of detection.

[0006] In one aspect of an embodiment of the present application, a method for detecting a discharge state is provided, comprising:

[0007] When it is determined that the vehicle is performing an unloading task, first point cloud data of an area of ​​interest of a first radar point cloud image collected by a laser radar installed at a target position of the vehicle is obtained, where the area of ​​interest is an area within a preset range behind the vehicle, the preset range is determined according to the length and width of the vehicle, and the target position of the vehicle is a preset position behind the chassis of the vehicle;

[0008] Determine ground plane parameters and ground plane point cloud data corresponding to a ground plane in the region of interest based on the first point cloud data;

[0009] When the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions, determine the mineral point cloud data in the first point cloud data according to the ground plane parameters;

[0010] The target unloading state of the vehicle is determined according to the mineral material point cloud data and the ground plane point cloud data. The target unloading state is used to indicate whether the vehicle has completed the unloading task at the time of acquisition of the first radar point cloud image.

[0011] In one aspect of an embodiment of the present application, a device for detecting a discharge state is provided, comprising:

[0012] A data acquisition module is used to acquire, when it is determined that the vehicle is performing an unloading task, first point cloud data of an area of ​​interest of a first radar point cloud image collected by a laser radar installed at a target position of the vehicle, wherein the area of ​​interest is an area within a preset range behind the vehicle, the preset range is determined according to the length and width of the vehicle, and the target position of the vehicle is a preset position behind the chassis of the vehicle;

[0013] A ground plane determination module, used to determine ground plane parameters and ground plane point cloud data corresponding to the ground plane of the region of interest based on the first point cloud data;

[0014] A point cloud determination module, for determining the mineral point cloud data in the first point cloud data according to the ground plane parameters when the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions;

[0015] The state determination module is used to determine the target unloading state of the vehicle based on the mineral point cloud data and the ground plane point cloud data. The target unloading state is used to indicate whether the vehicle has completed the unloading task at the time of acquisition of the first radar point cloud image.

[0016] In one aspect of an embodiment of the present application, an electronic device is provided, which includes: a memory and a program or instruction stored in the memory and executable on a processor, wherein when the program or instruction is executed by the processor, a method for detecting a discharge status as provided in any aspect of the above-mentioned embodiment of the present application is implemented.

[0017] In one aspect of an embodiment of the present application, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, a method for detecting a discharge status as provided in any aspect of the above-mentioned embodiment of the present application is implemented.

[0018] In one aspect of an embodiment of the present application, a computer program product is provided. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a method for detecting a discharge status as provided in any aspect of the above-mentioned embodiment of the present application.

[0019] In the detection method of the unloading state provided in the embodiment of the present application, an area of ​​interest is selected according to a preset range at the rear of the vehicle, and then the ground plane parameters corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data are determined based on the first point cloud data of the area of ​​interest to determine whether they meet the preset ground plane conditions. Then, if the preset ground plane conditions are met, the mineral point cloud data in the first point cloud data is further obtained, and according to the mineral point cloud data and the ground plane point cloud data, it is determined whether the target unloading vehicle has completed the unloading task. In this way, the embodiment of the present application selects an area of ​​interest in the unloading area of ​​the target unloading vehicle, without directly detecting the mineral situation in the vehicle cargo box, but indirectly by detecting the mineral situation on the ground plane, analyzing the mineral point cloud data corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data, so as to determine whether the mineral unloading is completed. Therefore, it is not limited by the mineral situation in the vehicle cargo box, and even if there are few remaining minerals in the vehicle cargo box, it can accurately determine whether the mineral unloading is completed, thereby improving the accuracy of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 It is a flow chart of a method for detecting a discharging state provided in an embodiment of the present application;

[0022] Figure 2 is a schematic diagram of a spoil dump provided in an embodiment of the present application;

[0023] Figure 3 It is a flow chart of another method for detecting a discharging state provided in an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of a detection device for a discharging state provided in an embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of a discharge status detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0027] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0028] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.

[0029] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0030] In the existing method, a weight sensor is installed on the mining truck, and the weight data collected by the weight sensor is used to detect whether the mining truck has been completely unloaded. However, this method cannot accurately detect whether the mining truck has been completely unloaded when there is only a small amount of mining material left in the mining truck, resulting in poor detection accuracy.

[0031] The purpose of the present application is to provide a method, device, equipment and storage medium for detecting the unloading state. In the unloading state detection method provided in the embodiment of the present application, an area of ​​interest is selected according to a preset range at the rear of the vehicle, and then the ground plane parameters corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data are determined according to the first point cloud data of the area of ​​interest. Whether they meet the preset ground plane conditions. Then, if the preset ground plane conditions are met, the mineral point cloud data in the first point cloud data is further obtained, and according to the mineral point cloud data and the ground plane point cloud data, it is determined whether the target unloading vehicle has completed the unloading task. In this way, the embodiment of the present application selects an area of ​​interest in the unloading area of ​​the target unloading vehicle, without directly detecting the mineral situation in the vehicle cargo box, but indirectly by detecting the mineral situation on the ground plane, the mineral point cloud data corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data are analyzed, so as to determine whether the mineral unloading is completed. Therefore, it is not limited by the mineral situation in the vehicle cargo box, and even if there are few remaining minerals in the vehicle cargo box, it can accurately determine whether the mineral unloading is completed, thereby improving the accuracy of detection.

[0032] The following describes specific embodiments of the method, device, equipment and storage medium for detecting the unloading state provided by the embodiments of the present application. First, the method for detecting the unloading state is introduced.

[0033] Figure 1 A flow chart of a method for detecting a discharge state is provided. The method for detecting a discharge state can be applied to a service end. The method for detecting a discharge state can include the following steps S101 to S104.

[0034] S101, when it is determined that the vehicle is performing an unloading task, obtain first point cloud data of an area of ​​interest of a first radar point cloud image collected by a laser radar installed at a target position of the vehicle, the area of ​​interest is an area within a preset range behind the vehicle, the preset range is determined based on the length and width of the vehicle, and the target position of the vehicle is a preset position behind the chassis of the vehicle.

[0035] In this embodiment, the region of interest is an area behind the vehicle determined according to the length and width of the vehicle. For example, a rectangle with the width of the vehicle body as the width and the length of the vehicle body plus the preset extension length as the length behind the vehicle can be constructed as the region of interest.

[0036] The lidar is installed at a preset position behind the vehicle chassis so that the first point cloud data in the area of ​​interest can be collected.

[0037] The first point cloud data is used to characterize the ground, ore piles and other possible obstacles in the area of ​​interest.

[0038] As an example, when the server determines that the vehicle is performing an unloading task, the server selects the first radar point cloud image at a specific time point as an analysis object.

[0039] Then, in the first radar point cloud image, a region of interest is defined with the width of the vehicle body as the width and the length of the vehicle body plus a preset extension length as the length, and first point cloud data is extracted from the region of interest.

[0040] S102: Determine ground plane parameters and ground plane point cloud data corresponding to a ground plane in an area of ​​interest based on the first point cloud data.

[0041] In this embodiment, the ground plane parameters may include at least one of a ground plane normal vector, a ground plane height, and a ground plane equation.

[0042] As an example, the server uses a ground extraction algorithm (such as the RANSAC algorithm) to process the first point cloud data in the area of ​​interest, identifies and fits the plane equation corresponding to the ground plane (such as Ax+By+Cz+D=0) as the ground plane parameter; at the same time, the point cloud data in the first point cloud data that matches the ground plane is filtered out as the ground plane point cloud data.

[0043] S103, when the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions, determine the mineral point cloud data in the first point cloud data according to the ground plane parameters.

[0044] In this embodiment, the preset ground plane condition is used to represent the threshold conditions preset for the ground plane parameters and the ground plane point cloud data respectively.

[0045] Mineral point cloud data is used to characterize the material unloaded by vehicles in the area of ​​interest.

[0046] As an example, the server determines whether the ground plane parameters and the ground plane point cloud data respectively meet the corresponding threshold conditions based on the ground plane parameters and the ground plane point cloud data. If both the ground plane parameters and the ground plane point cloud data meet the corresponding threshold conditions, it is confirmed that they meet the preset ground plane conditions; if at least one of the ground plane parameters and the ground plane point cloud data does not meet the corresponding threshold conditions, it is confirmed that they do not meet the preset ground plane conditions.

[0047] When the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions, the ground plane parameters are used as a reference to identify and separate the first point cloud data above the ground plane as the mineral material point cloud data.

[0048] S104, determining a target unloading state of the vehicle according to the mineral material point cloud data and the ground plane point cloud data, where the target unloading state is used to indicate whether the vehicle has completed the unloading task at the time of acquisition of the first radar point cloud image.

[0049] In this embodiment, a state judgment standard corresponding to the target unloading state is preset. For example, it can be set that when the proportion of mineral material point cloud data is less than a first preset proportion and when the proportion of ground plane point cloud data is greater than a second preset proportion, it is determined that the vehicle has completed the unloading task at the time of collecting the first radar point cloud image.

[0050] As an example, the server determines the respective proportions of the mineral point cloud data and the ground plane point cloud data, and then compares the proportion of the mineral point cloud data with the corresponding first preset proportion, and compares the proportion of the ground plane point cloud data with the corresponding second preset proportion, so as to determine whether the vehicle has completed the unloading task at the time of collecting the first radar point cloud image.

[0051] In the detection method of the unloading state provided in the present embodiment, an area of ​​interest is selected according to a preset range at the rear of the vehicle, and then the ground plane parameters corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data are determined based on the first point cloud data of the area of ​​interest to determine whether they meet the preset ground plane conditions. Then, if the preset ground plane conditions are met, the mineral point cloud data in the first point cloud data is further obtained, and according to the mineral point cloud data and the ground plane point cloud data, it is determined whether the target unloading vehicle has completed the unloading task. In this way, the embodiment of the present application selects an area of ​​interest in the unloading area of ​​the target unloading vehicle, without directly detecting the mineral situation in the vehicle cargo box, but indirectly by detecting the mineral situation on the ground plane, analyzing the mineral point cloud data corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data, so as to determine whether the mineral unloading is completed. Therefore, it is not limited by the mineral situation in the vehicle cargo box, and even if there are few remaining minerals in the vehicle cargo box, it can accurately determine whether the mineral unloading is completed, thereby improving the accuracy of detection.

[0052] As an optional embodiment, S102 may specifically include:

[0053] Determine the height of the ground plane corresponding to the ground plane according to the target position of the vehicle;

[0054] According to the ground plane height, each first point cloud data is screened to obtain initial ground plane point cloud data, and the distance between the initial ground plane point cloud data and the ground plane height is less than or equal to a preset height deviation;

[0055] Extract the consistent plane by random sampling of each initial ground plane point cloud data to obtain the ground plane of the area of ​​interest;

[0056] According to the ground plane of the region of interest, ground plane parameters and ground plane point cloud data corresponding to the ground plane of the region of interest are determined.

[0057] In this embodiment, the vehicle target position is a preset position where the laser radar is installed behind the vehicle chassis.

[0058] The random sampling consensus plane is a plane extracted using the random sampling consensus (RANSAC) algorithm.

[0059] As an example, the server first estimates the ground plane height based on the known preset position of the laser radar installation. Then set a reasonable preset height deviation, such as 0.1 meters. Then traverse all the first point cloud data, and select the first point cloud data whose distance from the estimated ground plane height is less than or equal to the preset height deviation as the initial ground plane point cloud data.

[0060] Then, the RANSAC algorithm is applied to the initial ground plane point cloud data to obtain a best-fit plane as the ground plane of the region of interest. Finally, the ground plane normal vector and ground plane height corresponding to the ground plane of the region of interest are extracted, and the final ground plane point cloud data is obtained by screening the ground plane of the region of interest in the initial ground plane point cloud data.

[0061] Through this embodiment, the ground plane of the region of interest is fitted based on the first point cloud data of the region of interest, and finally the corresponding ground plane parameters and ground plane point cloud data are determined based on the ground plane of the region of interest. This helps to subsequently identify whether the vehicle has completed the unloading task based on the ground plane parameters and ground plane point cloud data, and can improve the accuracy of detecting whether the vehicle has completed the unloading task.

[0062] As an optional embodiment, before S103, the method for detecting the unloading state may further include:

[0063] According to the ground plane parameters, the ground plane deflection angle of the area of ​​interest is calculated;

[0064] Comparing the ground plane deflection angle with a preset deflection angle threshold to obtain a first comparison result;

[0065] Compare the point cloud quantity of the ground plane point cloud data with the first quantity threshold to obtain a second comparison result;

[0066] According to the first comparison result and the second comparison result, it is determined whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions.

[0067] In this embodiment, the ground plane deflection angle is used to characterize the angle between the normal vector of the ground plane in the region of interest and the Z axis.

[0068] As an example, the server obtains the normal vector of the ground plane from the ground plane fitted by the RANSAC algorithm, and then determines the ground plane deflection according to the angle between the normal vector of the ground plane and the Z axis. At the same time, the server pre-sets a preset deflection threshold, for example, the preset deflection threshold can be 5 degrees. Then, the calculated ground plane deflection is compared with the preset deflection threshold to obtain a first comparison result.

[0069] Then, the screened ground plane point cloud data is counted to obtain the point cloud quantity of the ground plane point cloud data. At the same time, the server pre-sets a first quantity threshold, for example, the first quantity threshold may be 100 points, and then compares the point cloud quantity of the ground plane point cloud data obtained by counting with the first quantity threshold to obtain a second comparison result.

[0070] Finally, based on the first comparison result (determining whether the ground plane deflection angle meets the conditions) and the second comparison result (determining whether the number of point clouds meets the conditions), a comprehensive judgment is made to determine whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions.

[0071] Through this embodiment, a comprehensive judgment is made from two aspects: the ground plane deflection angle and the number of point clouds, and whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions is determined according to the result of the comprehensive judgment. If the preset ground plane conditions are not met, it can be directly determined that the vehicle has not completed the unloading task at the time of collecting the first radar point cloud image, without the need for subsequent operations, thereby improving the efficiency of detecting whether the vehicle has completed the unloading task.

[0072] As an optional embodiment, judging whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions according to the first comparison result and the second comparison result may specifically include:

[0073] When the first comparison result indicates that the ground plane deflection angle is not greater than the preset deflection angle threshold, and the second comparison result indicates that the number of point clouds of the ground plane point cloud data is not less than the first number threshold, determining that the ground plane parameters and the ground plane point cloud data meet the preset ground plane condition;

[0074] When the first comparison result indicates that the ground plane deflection angle is greater than the preset deflection angle threshold, and / or the second comparison result indicates that the number of point clouds of the ground plane point cloud data is less than the first number threshold, it is determined that the ground plane parameters and the ground plane point cloud data do not meet the preset ground plane conditions.

[0075] In this embodiment, if Figure 2 As shown, a schematic diagram of a spoil dump is provided. The spoil dump includes three parts: the spoil dump ground, the spoil dump reverse slope and the retaining wall. The spoil dump ground is basically kept horizontal, and the spoil dump reverse slope is required to have a slope of 3%-5%.

[0076] Therefore, when the first comparison result indicates that the ground plane deflection angle is greater than the preset deflection angle threshold, it can be determined that the vehicle is still at the retaining wall of the spoil dump or on the reverse slope of the spoil dump. At this time, it can be directly determined that the vehicle has not completed the unloading task at the time of acquisition of the first radar point cloud image.

[0077] When the second comparison result indicates that the number of point clouds in the ground plane point cloud data is less than the first number threshold, it can be determined that there are more mineral materials in the area of ​​interest that block the acquisition of the ground plane point cloud data. At this time, it can also be directly determined that the vehicle has not completed the unloading task at the time of acquisition of the first radar point cloud image.

[0078] That is, only when the first comparison result indicates that the ground plane deflection angle is less than or equal to the preset deflection angle threshold, and the second comparison result indicates that the number of point clouds of the ground plane point cloud data is greater than or equal to the first number threshold, can it be determined that the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions; in other cases, it is determined that the ground plane parameters and the ground plane point cloud data do not meet the preset ground plane conditions. At this time, it can be directly determined that the vehicle has not completed the unloading task at the time of acquisition of the first radar point cloud image.

[0079] Through this embodiment, a comprehensive judgment is made from the first comparison result and the second comparison result, and whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions is determined according to the result of the comprehensive judgment. If the preset ground plane conditions are not met, it can be directly determined that the vehicle has not completed the unloading task at the time of collecting the first radar point cloud image, without the need for subsequent operations, thereby improving the efficiency of detecting whether the vehicle has completed the unloading task.

[0080] As an optional embodiment, the ground plane parameters include a ground plane normal vector and a ground plane height;

[0081] S103 may specifically include:

[0082] Determine a rotation matrix corresponding to the ground plane of the region of interest based on the horizontal plane normal vector and the ground plane normal vector;

[0083] According to the rotation matrix, each first point cloud data is converted into second point cloud data corresponding to the reference horizontal plane;

[0084] Determine the mineral material height threshold according to the ground level height and the preset mineral material height;

[0085] Each second point cloud data that is greater than or equal to the mineral material height threshold is determined as mineral material point cloud data.

[0086] In this embodiment, the horizontal plane normal vector points to the positive direction of the Z axis, that is, the horizontal plane normal vector is (0, 0, 1).

[0087] The rotation matrix is ​​used to transform the first point cloud data into second point cloud data corresponding to the reference horizontal plane.

[0088] The preset mineral material height is used to represent a preset default height of mineral materials. For example, it can be preset that the height of more than 30 cm belongs to the mineral material by default.

[0089] As an example, the server determines the rotation axis according to the horizontal plane normal vector and the ground plane normal vector using the following formula 1:

[0090] n = n1×nz Formula 1

[0091] Where n is the rotation axis, n1 is the ground plane normal vector, and nz is the horizontal plane normal vector.

[0092] Then, the server determines the rotation angle based on the horizontal plane normal vector and the ground plane normal vector using the following formula 2:

[0093]

[0094] Where θ is the rotation angle, arccos is the calculation of the inverse cosine function, n1 is the ground plane normal vector, and nz is the horizontal plane normal vector.

[0095] Then, a rotation matrix can be constructed according to the rotation axis and the rotation angle. Then, each first point cloud data is converted into second point cloud data corresponding to the reference horizontal plane according to the rotation matrix. At the same time, the server uses the sum of the ground plane height and the preset mineral material height as the mineral material height threshold, and extracts the second point cloud data with a height greater than or equal to the mineral material height threshold as the mineral material point cloud data.

[0096] Through this embodiment, a rotation matrix is ​​constructed according to the horizontal plane normal vector and the ground plane normal vector, so that each first point cloud data is converted into a second point cloud data corresponding to the reference horizontal plane through the rotation matrix. Then, according to the ground plane height and the preset mineral material height, a preset mineral material height threshold is set. Finally, the second point cloud data with a height greater than or equal to the mineral material height threshold can be confirmed as mineral material point cloud data. In this way, the embodiment of the present application can accurately filter out mineral material point cloud data, which is helpful for subsequent judgment of whether the mineral material has been unloaded according to the mineral material point cloud data, and can improve the accuracy of detection of whether the vehicle has completed the unloading task.

[0097] As an optional embodiment, after S104, the method for detecting the unloading state may further include:

[0098] Obtaining at least one reference detection result of whether the vehicle has completed the unloading task, wherein the at least one reference detection result is a detection result obtained by detecting at least one frame of second radar point cloud image collected by the laser radar, and the at least one frame of the second radar point cloud image is at least one frame of radar point cloud image continuous with the first radar point cloud image;

[0099] When both the target unloading state and the reference detection result indicate that the vehicle has completed the unloading task, it is determined that the vehicle has completed the unloading task.

[0100] In this embodiment, the second radar point cloud image is used to represent the radar point cloud image continuously collected by the laser radar and continuous with the first radar point cloud image.

[0101] The reference detection result is used to characterize the unloading state corresponding to the vehicle identified according to the second radar point cloud image.

[0102] As an example, when the server determines that the vehicle has completed the unloading task at the time of collecting the first radar point cloud image, it will further collect the second radar point cloud image and detect whether the vehicle has completed the unloading task at the time of collecting the second radar point cloud image. If the unloading task is detected to be completed at the time of collecting five consecutive frames of radar point cloud images, it is determined that the vehicle has completed the unloading task.

[0103] Through this embodiment, the unloading status of the vehicle is detected multiple times, and the vehicle is determined to have completed the unloading task only when the unloading task is detected at the time of collecting multiple consecutive frames of radar point cloud images. In this way, misjudgment caused by occasional frame anomalies can be prevented, and the accuracy of detecting whether the vehicle has completed the unloading task can be improved.

[0104] As an optional embodiment, S104 may specifically include:

[0105] Dividing the number of point clouds of the mineral material point cloud data by the number of point clouds of the first point cloud data to obtain a first ratio;

[0106] The number of point clouds of the ground plane point cloud data is divided by the number of point clouds of the initial ground plane point cloud data to obtain a second ratio;

[0107] Determine whether the first ratio is less than a preset unloading ratio threshold value, and obtain a first determination result;

[0108] Determine whether the second ratio is greater than a preset ground area ratio threshold value, and obtain a second determination result;

[0109] The target unloading state of the vehicle is determined according to the first judgment result and the second judgment result.

[0110] In this embodiment, the server divides the number of point clouds of the mineral point cloud data by the number of point clouds of the first point cloud data to obtain a first ratio; and then divides the number of point clouds of the ground plane point cloud data by the number of point clouds of the initial ground plane point cloud data to obtain a second ratio.

[0111] Then the first ratio and the second ratio are compared with the corresponding preset proportion thresholds respectively to obtain the first judgment result and the second judgment result. And according to the final first judgment result and the second judgment result, the target unloading state corresponding to the vehicle is determined.

[0112] Through this embodiment, it is determined whether the target unloading vehicle has completed the unloading task based on the mineral point cloud data and the ground plane point cloud data. It is not necessary to directly detect the mineral situation in the vehicle cargo box, but indirectly detect the mineral situation on the ground plane, analyze the mineral point cloud data corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data, so as to determine whether the mineral unloading is completed, which can improve the accuracy of detection.

[0113] As an optional embodiment, determining the target unloading state of the vehicle according to the first judgment result and the second judgment result may specifically include:

[0114] When the first judgment result indicates that the first ratio is less than the preset unloading ratio threshold, and the second judgment result indicates that the second ratio is greater than the preset ground ratio threshold, it is determined that the vehicle completes the unloading task at the time of acquisition of the first radar point cloud image;

[0115] When the first judgment result indicates that the first ratio is not less than the preset unloading proportion threshold, and / or the second judgment result indicates that the second ratio is not greater than the preset ground proportion threshold, it is determined that the vehicle has not completed the unloading task at the time of acquisition of the first radar point cloud image.

[0116] In this embodiment, the first ratio is used to characterize the proportion of mineral materials in the area of ​​interest. When the proportion of mineral materials is greater than or equal to the preset unloading proportion threshold, it indicates that the amount of mineral materials in the area of ​​interest is large. At this time, it can be directly determined that the vehicle has not completed the unloading task at the time of acquisition of the first radar point cloud image.

[0117] The second ratio is used to characterize the ratio of the real ground point cloud data to the initial ground point cloud data in the area of ​​interest. When it is less than or equal to the preset ground point cloud data threshold, it indicates that the real ground point cloud data in the area of ​​interest accounts for a small proportion. At this time, it can be directly determined that the vehicle has not completed the unloading task at the time of acquisition of the first radar point cloud image.

[0118] Therefore, only when the first judgment result indicates that the first ratio is less than the preset unloading proportion threshold and the second judgment result indicates that the second ratio is greater than the preset ground proportion threshold, is it determined that the vehicle has completed the unloading task at the time of acquisition of the first radar point cloud image; in other cases, it is determined that the vehicle has not completed the unloading task at the time of acquisition of the first radar point cloud image.

[0119] Through this embodiment, according to the first judgment result and the second judgment result, it is determined whether the target unloading vehicle has completed the unloading task. It is not necessary to directly detect the mineral material situation in the vehicle cargo box, but indirectly detect the mineral material situation on the ground plane, analyze the mineral material point cloud data corresponding to the ground plane of the area of ​​interest and the ground plane point cloud data, so as to determine whether the mineral material has been unloaded, which can improve the accuracy of detection.

[0120] As an optional embodiment, before S101, the method for detecting the unloading state may further include:

[0121] Get the vehicle's current mission and lift sensor status;

[0122] When the current task is an unloading task and the lifting sensor state is a lifting state, it is determined that the vehicle is performing the unloading task.

[0123] In this embodiment, the server will first read the current task of the vehicle and detect the lifting sensor status of the vehicle. If the current task of the vehicle is the unloading task and the lifting sensor status of the vehicle is in the lifting state, it is considered that the vehicle is performing the unloading task, and the unloading state of the vehicle is detected at this time; if at least one of the current task of the vehicle and the lifting sensor status does not meet the conditions, it is considered that the vehicle is not performing the unloading task, and there is no need to detect the unloading state of the vehicle.

[0124] Through this embodiment, the service end first identifies the current task of the vehicle and the lifting sensor status, thereby determining whether the vehicle is performing an unloading task. If the vehicle is not performing an unloading task, there is no need to detect the unloading status of the vehicle, thereby improving the detection efficiency of the vehicle.

[0125] As an optional embodiment, after S101, the method for detecting the unloading state may further include:

[0126] Compare the point cloud quantity of the first point cloud data with a second quantity threshold to obtain a quantity comparison result;

[0127] When the quantity comparison result indicates that the point cloud quantity of the first point cloud data is less than the second quantity threshold, it is determined that the vehicle has not completed the unloading task.

[0128] In this embodiment, after acquiring the first point cloud data of the area of ​​interest, the server further compares the number of point clouds of the first point cloud data with the second number threshold. If the number of point clouds of the first point cloud data is less than the second number threshold, it is considered that the laser radar is blocked by the mineral material, resulting in missing point clouds, and thus it can be directly determined that the vehicle has not completed the unloading task at the time of collecting the first radar point cloud image.

[0129] Through this embodiment, after acquiring the first point cloud data of the area of ​​interest, the server further compares the point cloud quantity of the first point cloud data with the second quantity threshold. When the point cloud quantity is less than the second quantity threshold, it can be directly determined that the vehicle has not completed the unloading task at the time of collecting the first radar point cloud image, without the need for subsequent operations, thereby improving the efficiency of detecting whether the vehicle has completed the unloading task.

[0130] As an optional embodiment, before comparing the point cloud quantity of the first point cloud data with the second quantity threshold and obtaining the quantity comparison result, the method for detecting the unloading state may further include:

[0131] Performing discrete point filtering on the first point cloud data to obtain first filtered point cloud data;

[0132] Performing voxel filtering on the first filtered point cloud data to obtain second filtered point cloud data;

[0133] Counting the number of point clouds of the second filtered point cloud data;

[0134] Comparing the point cloud quantity of the first point cloud data with the second quantity threshold to obtain a quantity comparison result, specifically including:

[0135] The point cloud quantity of the second filtered point cloud data is compared with a second quantity threshold to obtain a quantity comparison result.

[0136] In this embodiment, after acquiring the first point cloud data, the server performs SOR discrete point filtering on the first point cloud data to filter out dust and discrete noise points in the first point cloud data; then performs downsampling voxel filtering on the first filtered point cloud data obtained after filtering, thereby homogenizing the point cloud distribution of the area of ​​interest to obtain the second filtered point cloud data. Finally, the point cloud quantity of the second filtered point cloud data is compared with the second quantity threshold to obtain a quantity comparison result.

[0137] Through this embodiment, the server can remove interference of dust and discrete noise on the first point cloud data by pre-processing the first point cloud data through discrete point filtering and voxel filtering, thereby improving the accuracy of detecting whether the vehicle has completed the unloading task.

[0138] As an optional scenario implementation example, Figure 3 As shown, a flow chart of another method for detecting the unloading state is provided.

[0139] First, the server detects whether the vehicle is performing an unloading task through S301. If the vehicle is not performing an unloading task, the unloading status detection process is directly terminated.

[0140] When the vehicle is performing an unloading task, S302 is used to detect whether the number of point clouds in the first point cloud data is greater than or equal to the second number threshold. When the number of point clouds in the first point cloud data is less than the second number threshold, S307 is used to directly determine that the vehicle has not completed the unloading task.

[0141] When the number of point clouds in the first point cloud data is greater than or equal to the second number threshold, S303 is used to further detect whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions. If the preset ground plane conditions are not met, S307 is used to directly determine that the vehicle has not completed the unloading task.

[0142] When the preset ground plane condition is met, S304 is further used to detect whether the unloading task is completed at the collection time of the current frame. When the unloading task is not completed at the collection time of the current frame, S307 is directly used to determine that the vehicle has not completed the unloading task.

[0143] If the unloading task is completed at the collection time of the current frame, then S305 is further used to detect whether the unloading task is completed at the collection time of the consecutive preset number of frames. If the unloading task is completed at the collection time of the consecutive preset number of frames, then S306 is used to determine that the vehicle has completed the unloading task; if the unloading task is not completed at any time during the collection time of the consecutive preset number of frames, then S307 is used to determine that the vehicle has not completed the unloading task.

[0144] Detection method based on unloading state. Accordingly, the present application also provides a specific embodiment of a detection device for unloading state.

[0145] like Figure 4 As shown, the unloading status detection device 400 provided in the embodiment of the present application includes a data acquisition module 410 , a ground plane determination module 420 , a point cloud determination module 430 and a status determination module 440 .

[0146] The data acquisition module 410 is used to obtain the first point cloud data of the area of ​​interest of the first radar point cloud image collected by the laser radar installed at the target position of the vehicle when it is determined that the vehicle is performing an unloading task. The area of ​​interest is an area within a preset range behind the vehicle. The preset range is determined based on the length and width of the vehicle. The target position of the vehicle is a preset position behind the chassis of the vehicle.

[0147] The ground plane determination module 420 is used to determine ground plane parameters and ground plane point cloud data corresponding to the ground plane of the region of interest according to the first point cloud data.

[0148] The point cloud determination module 430 is used to determine the mineral point cloud data in the first point cloud data according to the ground plane parameters when the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions.

[0149] The state determination module 440 is used to determine the target unloading state of the vehicle based on the mineral point cloud data and the ground plane point cloud data. The target unloading state is used to indicate whether the vehicle has completed the unloading task at the time of collecting the first radar point cloud image.

[0150] As an optional embodiment, the ground plane determination module 420 specifically includes the following units:

[0151] a height determination unit, for determining a ground plane height corresponding to a ground plane according to a target position of the vehicle;

[0152] A point cloud screening unit, used for screening each first point cloud data according to the ground plane height to obtain initial ground plane point cloud data, wherein the distance between the initial ground plane point cloud data and the ground plane height is less than or equal to a preset height deviation;

[0153] A ground plane extraction unit is used to extract a consistent plane by random sampling of each initial ground plane point cloud data to obtain a ground plane of an area of ​​interest;

[0154] The parameter determination unit is used to determine the ground plane parameters and ground plane point cloud data corresponding to the ground plane of the area of ​​interest according to the ground plane of the area of ​​interest.

[0155] As an optional embodiment, when the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions, before determining the mineral material point cloud data in the first point cloud data according to the ground plane parameters, the unloading state detection device 400 further includes the following modules:

[0156] A deflection angle calculation module is used to calculate the ground plane deflection angle of the area of ​​interest according to the ground plane parameters;

[0157] A deflection angle comparison module, used to compare the ground plane deflection angle with a preset deflection angle threshold to obtain a first comparison result;

[0158] A quantity comparison module, used for comparing the point cloud quantity of the ground plane point cloud data with a first quantity threshold value to obtain a second comparison result;

[0159] The condition judgment module is used to judge whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions according to the first comparison result and the second comparison result.

[0160] As an optional embodiment, the ground plane parameters include a ground plane normal vector and a ground plane height;

[0161] The point cloud determination module 430 specifically includes the following units:

[0162] A matrix determination unit, used to determine a rotation matrix corresponding to the ground plane of the region of interest according to a horizontal plane normal vector and a ground plane normal vector;

[0163] A point cloud conversion unit, used for converting each first point cloud data into second point cloud data corresponding to a reference horizontal plane according to a rotation matrix;

[0164] A threshold determination unit, used to determine a mineral material height threshold according to a ground plane height and a preset mineral material height;

[0165] The point cloud determination unit is used to determine each second point cloud data that is greater than or equal to the mineral material height threshold as mineral material point cloud data.

[0166] As an optional embodiment, after determining the target unloading state of the vehicle according to the mineral material point cloud data and the ground plane point cloud data, the unloading state detection device 400 further includes the following modules:

[0167] A result acquisition module is used to obtain at least one reference detection result of whether the vehicle has completed the unloading task, wherein the at least one reference detection result is a detection result obtained by detecting at least one frame of a second radar point cloud image collected by the laser radar, and the at least one frame of the second radar point cloud image is at least one frame of radar point cloud image continuous with the first radar point cloud image;

[0168] The result determination module is used to determine that the vehicle has completed the unloading task when both the target unloading state and the reference detection result indicate that the vehicle has completed the unloading task.

[0169] As an optional embodiment, the state determination module 440 specifically includes the following units:

[0170] A ratio determination unit, configured to divide the number of point clouds of the mineral material point cloud data by the number of point clouds of the first point cloud data to obtain a first ratio;

[0171] The ratio determination unit is further used to divide the number of point clouds of the ground plane point cloud data by the number of point clouds of the initial ground plane point cloud data to obtain a second ratio;

[0172] A result judgment unit, used to judge whether the first ratio is less than a preset discharge ratio threshold value, and obtain a first judgment result;

[0173] The result judgment unit is further used to judge whether the second ratio is greater than a preset ground area ratio threshold value to obtain a second judgment result;

[0174] The state determination unit is used to determine the target unloading state of the vehicle according to the first judgment result and the second judgment result.

[0175] As an optional embodiment, when it is determined that the vehicle is performing an unloading task, before acquiring the first point cloud data of the area of ​​interest of the first radar point cloud image collected by the laser radar installed at the target position of the vehicle, the unloading state detection device 400 further includes the following modules:

[0176] The task acquisition module is used to obtain the current task of the vehicle and the lifting sensor status;

[0177] The state determination module is used to determine that the vehicle is performing an unloading task when the current task is an unloading task and the lifting sensor state is a lifting state.

[0178] As an optional embodiment, when it is determined that the vehicle is performing an unloading task, after obtaining the first point cloud data of the area of ​​interest of the first radar point cloud image collected by the laser radar installed at the target position of the vehicle, the unloading state detection device 400 further includes the following modules:

[0179] The quantity comparison module is further used to compare the point cloud quantity of the first point cloud data with the second quantity threshold to obtain a quantity comparison result;

[0180] The state determination module is also used to determine that the vehicle has not completed the unloading task when the quantity comparison result indicates that the point cloud quantity of the first point cloud data is less than the second quantity threshold.

[0181] As an optional embodiment, before comparing the point cloud quantity of the first point cloud data with the second quantity threshold to obtain the quantity comparison result, the unloading state detection device 400 further includes the following modules:

[0182] A point cloud filtering module, used for performing discrete point filtering on the first point cloud data to obtain first filtered point cloud data;

[0183] The point cloud filtering module is further used to perform voxel filtering on the first filtered point cloud data to obtain second filtered point cloud data;

[0184] A quantity statistics module, used for counting the number of point clouds of the second filtered point cloud data;

[0185] The quantity comparison module is specifically used for:

[0186] The point cloud quantity of the second filtered point cloud data is compared with a second quantity threshold to obtain a quantity comparison result.

[0187] Detection method based on unloading state. Accordingly, the present application also provides a specific embodiment of the detection device of unloading state.

[0188] Figure 5 A schematic diagram of the hardware structure of a discharge status detection device provided in an embodiment of the present application is shown.

[0189] The device for detecting the unloading state may include a processor 501 and a memory 502 storing computer program instructions.

[0190] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0191] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0192] The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the methods for detecting the unloading state in the above embodiments.

[0193] In one example, the unloading state detection device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0194] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0195] Bus 510 includes hardware, software or both, and the parts of the detection equipment of the discharge state are coupled to each other.For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In suitable cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0196] In addition, in combination with the detection method of the unloading state in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the detection methods of the unloading state in the above embodiment is implemented.

[0197] In addition, in combination with the method for detecting the unloading status in the above-mentioned embodiment, the embodiment of the present application may provide a computer program product for implementation. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device executes the method for detecting the unloading status provided in any aspect of the above-mentioned embodiment of the present application.

[0198] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0199] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0200] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0201] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0202] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for detecting a discharging state, characterized in that: include: When it is determined that the vehicle is performing an unloading task, first point cloud data of an area of ​​interest of a first radar point cloud image collected by a laser radar installed at a target position of the vehicle is obtained, wherein the area of ​​interest is an area within a preset range behind the vehicle, the preset range is determined according to the length and width of the vehicle, and the target position of the vehicle is a preset position behind the chassis of the vehicle; Determine, according to the first point cloud data, ground plane parameters and ground plane point cloud data corresponding to the ground plane of the region of interest; In a case where the ground plane parameters and the ground plane point cloud data meet a preset ground plane condition, determining the mineral point cloud data in the first point cloud data according to the ground plane parameters; The target unloading state of the vehicle is determined based on the mineral point cloud data and the ground plane point cloud data, and the target unloading state is used to indicate whether the vehicle has completed the unloading task at the time of acquisition of the first radar point cloud image.

2. The method according to claim 1, characterized in that The step of determining, based on the first point cloud data, ground plane parameters and ground plane point cloud data corresponding to the ground plane of the region of interest includes: Determining a ground plane height corresponding to the ground plane according to the target position of the vehicle; According to the ground plane height, each of the first point cloud data is screened to obtain initial ground plane point cloud data, wherein the distance between the initial ground plane point cloud data and the ground plane height is less than or equal to a preset height deviation; Extracting a consistent plane by randomly sampling each of the initial ground plane point cloud data to obtain a ground plane of the region of interest; According to the ground plane of the region of interest, ground plane parameters and ground plane point cloud data corresponding to the ground plane of the region of interest are determined.

3. The method according to claim 1, characterized in that When the ground plane parameters and the ground plane point cloud data meet the preset ground plane conditions, before determining the mineral point cloud data in the first point cloud data according to the ground plane parameters, the method further includes: Calculating the ground plane deflection angle of the region of interest according to the ground plane parameters; Comparing the ground plane deflection angle with a preset deflection angle threshold to obtain a first comparison result; Comparing the point cloud quantity of the ground plane point cloud data with a first quantity threshold to obtain a second comparison result; According to the first comparison result and the second comparison result, it is determined whether the ground plane parameters and the ground plane point cloud data meet the preset ground plane condition.

4. The method according to claim 1, characterized in that: The ground plane parameters include a ground plane normal vector and a ground plane height; When the ground plane parameters and the ground plane point cloud data meet a preset ground plane condition, determining the mineral point cloud data in the first point cloud data according to the ground plane parameters includes: Determine a rotation matrix corresponding to the ground plane of the region of interest according to the horizontal plane normal vector and the ground plane normal vector; According to the rotation matrix, convert each of the first point cloud data into second point cloud data corresponding to a reference horizontal plane; Determining a mineral material height threshold according to the ground plane height and a preset mineral material height; Each of the second point cloud data that is greater than or equal to the mineral material height threshold is determined as the mineral material point cloud data.

5. The method according to claim 1, characterized in that After determining the target unloading state of the vehicle according to the mineral material point cloud data and the ground plane point cloud data, the method further includes: Acquire at least one reference detection result of whether the vehicle completes the unloading task, wherein the at least one reference detection result is a detection result obtained by detecting at least one frame of second radar point cloud image collected by the laser radar, and the at least one frame of second radar point cloud image is at least one frame of radar point cloud image continuous with the first radar point cloud image; When both the target unloading state and the reference detection result indicate that the vehicle has completed the unloading task, it is determined that the vehicle has completed the unloading task.

6. The method according to claim 2, characterized in that The step of determining a target unloading state of the vehicle according to the mineral material point cloud data and the ground plane point cloud data includes: Dividing the number of point clouds of the mineral material point cloud data by the number of point clouds of the first point cloud data to obtain a first ratio; Dividing the number of point clouds of the ground plane point cloud data by the number of point clouds of the initial ground plane point cloud data to obtain a second ratio; Determine whether the first ratio is less than a preset unloading ratio threshold value, and obtain a first determination result; Determine whether the second ratio is greater than a preset ground area ratio threshold, and obtain a second determination result; A target unloading state of the vehicle is determined according to the first judgment result and the second judgment result.

7. The method according to any one of claims 1 to 6, characterized in that: Before obtaining first point cloud data of an area of ​​interest of a first radar point cloud image collected by a laser radar installed at a target position of the vehicle when it is determined that the vehicle is performing a unloading task, the method further includes: Obtaining the current mission and lift sensor status of the vehicle; When the current task is the unloading task and the lifting sensor state is the lifting state, it is determined that the vehicle is performing the unloading task.

8. The method according to any one of claims 1 to 6, characterized in that: In the case where it is determined that the vehicle is performing an unloading task, after obtaining first point cloud data of an area of ​​interest of a first radar point cloud image collected by a laser radar installed at a target position of the vehicle, the method further includes: Compare the point cloud quantity of the first point cloud data with a second quantity threshold to obtain a quantity comparison result; When the quantity comparison result indicates that the point cloud quantity of the first point cloud data is less than the second quantity threshold, it is determined that the vehicle has not completed the unloading task.

9. The method according to claim 8, characterized in that Before comparing the point cloud quantity of the first point cloud data with a second quantity threshold to obtain a quantity comparison result, the method further includes: Performing discrete point filtering on the first point cloud data to obtain first filtered point cloud data; Performing voxel filtering on the first filtered point cloud data to obtain second filtered point cloud data; Counting the number of point clouds of the second filtered point cloud data; The step of comparing the point cloud quantity of the first point cloud data with a second quantity threshold to obtain a quantity comparison result includes: The point cloud quantity of the second filtered point cloud data is compared with a second quantity threshold to obtain a quantity comparison result.

10. A device for detecting a discharge state, characterized in that: include: A data acquisition module, for acquiring, when it is determined that the vehicle is performing an unloading task, first point cloud data of an area of ​​interest of a first radar point cloud image collected by a laser radar installed at a target position of the vehicle, wherein the area of ​​interest is an area within a preset range behind the vehicle, the preset range is determined according to the length and width of the vehicle, and the target position of the vehicle is a preset position behind the chassis of the vehicle; A ground plane determination module, configured to determine ground plane parameters and ground plane point cloud data corresponding to the ground plane of the region of interest based on the first point cloud data; A point cloud determination module, configured to determine the mineral point cloud data in the first point cloud data according to the ground plane parameters when the ground plane parameters and the ground plane point cloud data meet a preset ground plane condition; A state determination module is used to determine the target unloading state of the vehicle based on the mineral point cloud data and the ground plane point cloud data, and the target unloading state is used to indicate whether the vehicle has completed the unloading task at the time of acquisition of the first radar point cloud image.

11. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for detecting the unloading status as described in any one of claims 1-9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for detecting the unloading state according to any one of claims 1 to 9 is implemented.

Images