Railway freight car coal load detection method, device and storage medium

Abstract

The application discloses a railway freight car coal load detection method, device and storage medium, and relates to the load detection technical field. The method comprises the following steps: acquiring laser point cloud data of a to-be-detected freight car and multiple sampling images on a conveying belt; extracting a three-dimensional contour model based on the laser point cloud data; determining the volume of loaded coal based on the size of the to-be-detected freight car and the three-dimensional contour model; performing contour recognition to obtain the coal contour in each sampling image in the multiple sampling images; counting the particle size of all the coal in the multiple sampling images based on the coal contour; obtaining the coal distribution proportion of each particle size interval based on the particle size of all the coal; and estimating the coal load in the to-be-detected freight car based on the volume of the loaded coal in the to-be-detected freight car and the coal distribution proportion of each particle size interval, so as to obtain the coal load of the to-be-detected freight car. The method, device and storage medium disclosed by the application can avoid the overloading of the coal load of the freight car.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of load detection, and particularly relates to a railway freight car coal load weight detection method, device and storage medium. BACKGROUND

[0002] Before coal is shipped, the coal to be transported needs to be loaded into the freight car compartment of the railway freight car at the collection and transportation station. Generally, the load weight of each freight car compartment is limited, and the weight of the loaded coal cannot exceed the set limit.

[0003] At present, for the coal load weight of the freight car compartment, the loading personnel generally estimates the coal load weight of the freight car compartment according to the observed loading volume. However, due to the difference between the observed loading volume and the actual loading volume, and the difference in the weight of the unit volume of coal of different sizes, the manually estimated coal load weight may be greatly different from the actual coal load weight of the freight car compartment, thereby causing the coal load weight of the freight car compartment to exceed the set limit, and causing the risk of the railway freight car due to overloading.

[0004] Therefore, how to provide an effective scheme to more accurately detect the coal load weight of the freight car compartment of the railway freight car and avoid the risk of the railway freight car due to overloading has become a problem to be solved in the prior art. SUMMARY

[0005] The purpose of the present application is to provide a railway freight car coal load weight detection method, device and storage medium to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical scheme:

[0007] In a first aspect, the present application provides a railway freight car coal load weight detection method, comprising:

[0008] obtaining laser point cloud data of a to-be-measured freight car compartment loaded with coal and a plurality of sampling images on a conveying belt used to load coal into the to-be-measured freight car compartment;

[0009] extracting a three-dimensional contour model containing the to-be-measured freight car compartment body and the coal in the compartment body based on the laser point cloud data;

[0010] determining the volume of the coal loaded in the to-be-measured freight car compartment based on the size of the to-be-measured freight car compartment and the three-dimensional contour model;

[0011] performing contour recognition on the plurality of sampling images to obtain the coal contour in each sampling image in the plurality of sampling images;

[0012] based on the coal outline in each of the plurality of sampling images, the size of all the coals in the plurality of sampling images is counted;

[0013] based on the size of all the coals in the plurality of sampling images, the distribution proportion of each size interval of the coals is obtained;

[0014] based on the volume of the coal loaded in the to-be-tested truck compartment and the distribution proportion of each size interval of the coals, the coal load in the to-be-tested truck compartment is estimated, and the coal load of the to-be-tested truck compartment is obtained, so that when the coal load of the to-be-tested truck compartment exceeds a first preset weight, the loading of the coal into the to-be-tested truck compartment is stopped.

[0015] Based on the above disclosure, the present application obtains the laser point cloud data of the to-be-tested truck compartment loaded with coal and a plurality of sampling images on the conveying belt for loading coal into the to-be-tested truck compartment; based on the laser point cloud data, a three-dimensional contour model containing the to-be-tested truck compartment and the coal in the compartment is extracted; based on the size of the to-be-tested truck compartment and the three-dimensional contour model, the volume of the coal loaded in the to-be-tested truck compartment is determined; then, the contour recognition is performed on the plurality of sampling images to obtain the coal outline in each of the plurality of sampling images; based on the coal outline in each of the plurality of sampling images, the size of all the coals in the plurality of sampling images is counted; based on the size of all the coals in the plurality of sampling images, the distribution interval of the coal size is obtained; finally, based on the volume of the coal loaded in the to-be-tested truck compartment and the distribution interval of the coal size, the coal load in the to-be-tested truck compartment is estimated, and the coal load of the to-be-tested truck compartment is obtained, so that when the coal load of the to-be-tested truck compartment exceeds a first preset weight, the loading of the coal into the to-be-tested truck compartment is stopped. In this way, the truck compartment can be recognized by the point cloud data, and the three-dimensional contour of the medium in the truck compartment can be recognized, so that the volume of the coal loaded in the truck compartment is determined, and the distribution interval of the coal size is counted according to the sampling images on the conveying belt. Finally, the coal load of the truck compartment is accurately detected according to the volume of the coal loaded in the truck compartment and the distribution interval of the coal size, so as to avoid the overloading of the coal load of the truck compartment, thereby avoiding the risk caused by the overloading of the railway truck.

[0016] Through the above design, the volume of the coal loaded in the truck compartment and the distribution interval of the coal size can be recognized, so that the coal load of the truck compartment can be accurately detected, the overloading of the coal load of the truck compartment can be avoided, and the risk caused by the overloading of the railway truck can be avoided, which is convenient for practical application and promotion.

[0017] In one possible design, the three-dimensional contour model containing the to-be-tested truck compartment and the coal in the compartment is extracted based on the laser point cloud data, which includes:

[0018] The laser point cloud data is denoised to obtain denoised laser point cloud data.

[0019] An edge contour line corresponding to the denoised laser point cloud data is detected by a Hough transform method.

[0020] The edge contour line corresponding to the denoised laser point cloud data is taken as an edge contour of the to-be-measured truck compartment body, and a three-dimensional contour model containing the to-be-measured truck compartment body and coal in the compartment body is established.

[0021] In one possible design, the contour recognition on the plurality of sampling images to obtain the coal contour in each sampling image of the plurality of sampling images comprises:

[0022] The plurality of sampling images are subjected to contrast adjustment to obtain a plurality of adjusted images corresponding one-to-one to the plurality of sampling images.

[0023] The plurality of adjusted images are subjected to binaryzation processing to obtain a plurality of binaryzation images corresponding one-to-one to the plurality of adjusted images.

[0024] The coal contour in each binaryzation image of the plurality of binaryzation images is recognized by an OpenCV algorithm.

[0025] In one possible design, the method further comprises:

[0026] When the coal load of the to-be-measured truck compartment exceeds a second preset weight, a prompt information is generated to reduce the rate at which the conveyor belt loads coal to the to-be-measured truck compartment, and the second preset weight is less than the first preset weight.

[0027] In one possible design, the granularity of the coal is a surface area of the coal.

[0028] In one possible design, the method further comprises:

[0029] A truck compartment image of the to-be-measured truck compartment is acquired.

[0030] A carried truck compartment number in the truck compartment image is recognized to obtain a truck compartment number of the to-be-measured truck compartment, and the size of the to-be-measured truck compartment is determined based on the truck compartment number of the to-be-measured truck compartment; or

[0031] The truck compartment image is matched with an image of a sample truck compartment with a known size in an image database to obtain the size of the to-be-measured truck compartment.

[0032] In one possible design, the laser point cloud data of the to-be-measured truck compartment is obtained by fusing laser point cloud data acquired from a plurality of angles.

[0033] The second aspect of the present application provides a railway freight car coal load weight detection device, comprising:

[0034] An acquisition unit is configured to acquire laser point cloud data of a coal-loaded to-be-detected freight car and a plurality of sampling images on a conveyor belt for loading coal into the to-be-detected freight car;

[0035] An extraction unit is configured to extract a three-dimensional contour model containing the to-be-detected freight car body and coal in the to-be-detected freight car body based on the laser point cloud data;

[0036] A determination unit is configured to determine a volume of coal loaded in the to-be-detected freight car based on a size of the to-be-detected freight car and the three-dimensional contour model;

[0037] A contour recognition unit is configured to perform contour recognition on the plurality of sampling images to obtain a coal contour in each sampling image of the plurality of sampling images;

[0038] A statistical unit is configured to statistically determine a particle size of all coal in the plurality of sampling images based on the coal contour in each sampling image of the plurality of sampling images;

[0039] The statistical unit is further configured to obtain a coal distribution proportion of each particle size interval based on the particle size of all coal in the plurality of sampling images;

[0040] An operation unit is configured to estimate a coal load weight in the to-be-detected freight car based on the volume of coal loaded in the to-be-detected freight car and the coal distribution proportion of each particle size interval to obtain the coal load weight of the to-be-detected freight car, so that coal loading into the to-be-detected freight car is stopped when the coal load weight of the to-be-detected freight car exceeds a first preset weight.

[0041] The third aspect of the present application provides a railway freight car coal load weight detection device, comprising a memory, a processor and a transceiver connected in sequence and in communication, wherein the memory is configured to store a computer program, the transceiver is configured to transceive messages, and the processor is configured to read the computer program and execute the railway freight car coal load weight detection method of the first aspect.

[0042] The fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on a computer, the railway freight car coal load weight detection method of the first aspect is executed.

[0043] The fifth aspect of the present application provides a computer program product comprising instructions, and when the instructions run on a computer, the computer is caused to execute the railway freight car coal load weight detection method of the first aspect.

[0044] Beneficial effects:

[0045] The railway freight car coal load detection method, device and storage medium disclosed by the application can identify the volume of the coal loaded in the freight car and the particle size distribution interval of the coal, thereby more accurately detecting the coal load of the freight car, avoiding overloading of the coal load of the freight car, and further avoiding risks caused by overloading of the railway freight car, and facilitating practical application and promotion. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A flowchart of a railway freight car coal load detection method provided by an embodiment of the application is shown in the figure.

[0047] Figure 2 A structural schematic diagram of a railway freight car coal load detection device provided by an embodiment of the application is shown in the figure.

[0048] Figure 3 A structural schematic diagram of another railway freight car coal load detection device provided by an embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the application will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the drawings is only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings. It should be noted that the description of these embodiments is used to help understand the application, but does not constitute a limitation on the application.

[0050] It should be understood that although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element can be called a second element, and similarly, a second element can be called a first element without departing from the scope of the example embodiments of the application.

[0051] It should be understood that for the term "and / or" that may appear in the present text, it only describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which means that there are three cases of A alone, B alone, and A and B together; for the term " / and" that may appear in the present text, it describes another association object relationship, which means that there can be two kinds of relationships, for example, A / and B, which means that there are two cases of A alone and A and B together; in addition, for the character " / " that may appear in the present text, it generally means that the associated objects before and after are an "or" relationship.

[0052] In order to accurately detect the coal load of a railway wagon, an embodiment of the present application provides a railway wagon coal load detection method, device and storage medium, which can accurately detect the coal load of a railway wagon, avoid overloading of the coal load of the railway wagon, and thus avoid risks caused by overloading of the railway wagon.

[0053] The railway wagon coal load detection method provided by the embodiment of the present application can be applied to an industrial computer or a user terminal for coal loading control. The user terminal can be, but is not limited to, a personal computer, a smart phone, a tablet computer, a laptop computer, a personal digital assistant (PDA), and the like. It can be understood that the execution subject does not constitute a limitation on the embodiment of the present application.

[0054] The railway wagon coal load detection method provided by the embodiment of the present application will be described in detail below.

[0055] As shown in Figure 1 FIG. 1 is a flowchart of a railway wagon coal load detection method provided by a first aspect of the present application. The railway wagon coal load detection method can include, but is not limited to, the following steps S101-S107.

[0056] Step S101. Obtain laser point cloud data of a coal-loaded railway wagon to be detected and multiple sample images on a conveyor belt for loading coal into the railway wagon to be detected.

[0057] The laser point cloud data of the coal-loaded railway wagon to be detected can be obtained by a laser radar. The laser point cloud data of the railway wagon to be detected can be obtained by obtaining laser point cloud data of the railway wagon to be detected from different angles, and then fusing the laser point cloud data obtained from different angles. The fusion of the laser point cloud data can use an existing point cloud data fusion method, which will not be described in detail in the embodiment of the present application.

[0058] In the embodiment of the present application, coal can be loaded into the railway wagon to be detected by the conveyor belt, and a camera can be arranged above the conveyor belt to sample and shoot the coal on the conveyor belt to obtain sample images. When shooting, the camera can shoot once every certain time interval, so as to obtain multiple sample images. The conveyor belt can use a color different from that of the coal, so as to facilitate elimination of the background of the image during analysis of the coal in the image.

[0059] Step S102. Extract a three-dimensional contour model containing the wagon body of the railway wagon to be detected and the coal in the wagon body based on the laser point cloud data.

[0060] Specifically, extracting a three-dimensional contour model containing the compartment of the to-be-tested freight car and the coal in the compartment can include, but is not limited to, the following steps S1021-S1023.

[0061] Step S1021. The laser point cloud data is denoised to obtain denoised laser point cloud data.

[0062] The laser point cloud data can be denoised by using an existing denoising method, which will not be described in detail in the embodiments of the present application.

[0063] Step S1022. The edge contour line in the denoised laser point cloud data is detected by a Hough transform method.

[0064] Hough Transform is a feature extraction method widely used in image analysis, computer vision, and digital image processing. Hough Transform is used to identify features in objects, such as lines. The algorithm flow is roughly as follows: given an object and the type of shape to be identified, the algorithm performs voting in the parameter space to determine the shape of the object, which is determined by the local maximum in the accumulator space. The widely used Hough Transform was invented by Richard Duda and Peter Hart in 1972 and is called generalized Hough Transform. Hough Transform can not only identify straight lines, but also identify any shape, such as circles, ellipses, etc.

[0065] In the embodiments of the present application, the edge contour points in the denoised laser point cloud data can be detected by the Hough transform method, and the straight line connected by the edge contour points is taken as the edge contour line corresponding to the denoised laser point cloud data.

[0066] Step S1023. The edge contour line corresponding to the denoised laser point cloud data is taken as the edge contour of the to-be-tested freight car compartment, and a three-dimensional contour model containing the to-be-tested freight car compartment and the coal in the compartment is established.

[0067] In the embodiments of the present application, the edge contour line corresponding to the denoised laser point cloud data can be taken as the edge contour of the to-be-tested freight car compartment, and a three-dimensional contour model of the to-be-tested freight car compartment is established.

[0068] In the process of acquiring the laser point cloud data of the to-be-measured truck compartment, although the point cloud data of all surfaces of the truck compartment can not be acquired due to the shielding of some areas (such as the bottom surface of the truck compartment), the truck compartment can be regarded as a cuboid structure, and thus only the profiles of three connected edges need to be known to reconstruct the three-dimensional profile model of the truck compartment (since the truck compartment has no upper cover, the upper surface of the truck compartment is not reconstructed during the reconstruction), and then the three-dimensional profile model of the coal in the truck compartment is constructed by using the point cloud data located in the three-dimensional profile model of the truck compartment, so as to obtain the three-dimensional profile model of the to-be-measured truck compartment and the coal in the truck compartment.

[0069] Step S103. Determine the volume of the coal loaded in the to-be-measured truck compartment based on the size and the three-dimensional profile model of the to-be-measured truck compartment.

[0070] In the embodiments of the present application, the size of the to-be-measured truck compartment can be pre-set, which can include the size (length, width, height, etc.) of the outer surface of the truck compartment and the size of the inner surface.

[0071] If the to-be-measured truck compartment has multiple models and corresponds to different sizes, the truck compartment image of the to-be-measured truck compartment can be acquired, and then the truck compartment number carried in the truck compartment image is recognized (if the truck compartment number is written on the surface of the truck compartment), the model of the to-be-measured truck compartment is found according to the truck compartment number, and the size of the to-be-measured truck compartment is determined based on the model of the to-be-measured truck compartment. The truck compartment image can also be matched with the images of sample truck compartments with known sizes in the image database after the truck compartment image of the to-be-measured truck compartment is acquired, the image of the sample truck compartment matched with the truck compartment image is determined, and thus the size of the to-be-measured truck compartment is obtained.

[0072] In the embodiments of the present application, a three-dimensional coordinate system can be established, and the size corresponding to a unit coordinate (for example, 1 unit coordinate corresponds to 1 meter) is obtained by conversion according to the coordinates of the three-dimensional profile model in the three-dimensional coordinate system and the size of the to-be-measured truck compartment, and then the volume of the coal loaded in the to-be-measured truck compartment is calculated according to the profile coordinates of the three-dimensional profile model of the coal in the truck compartment.

[0073] Step S104. Perform profile recognition on the multiple sampling images to obtain the coal profile in each sampling image in the multiple sampling images.

[0074] Specifically, the contrast of the multiple sampling images can be adjusted first to obtain multiple adjusted images corresponding one-to-one to the multiple sampling images, the purpose of the contrast adjustment is to enhance the display effect of the coal in the image to facilitate the identification of the coal profile in the image, then the multiple adjusted images are subjected to binaryzation processing to obtain multiple binaryzation images corresponding one-to-one to the multiple adjusted images, and finally the coal profile in each binaryzation image in the multiple binaryzation images is identified through the OpenCV algorithm.

[0075] In the embodiment of the present application, the image backgrounds of the plurality of sampling images can be first modified before the contrast of the plurality of sampling images is adjusted.

[0076] It can be understood that the order of step S104 and the aforementioned steps S102 and S103 is not limited.

[0077] Step S105. Based on the coal contours in each of the plurality of sampling images, the particle sizes of all the coals in the plurality of sampling images are counted.

[0078] The particle size refers to the size of a particle. The particle size of a spherical particle is usually represented by the diameter, and the particle size of a cubic particle is usually represented by the edge length. In the embodiment of the present application, the coal (block) has an irregular shape, and the surface area of the coal can be taken as the particle size of the coal.

[0079] Step S106. Based on the particle sizes of all the coals in the plurality of sampling images, the coal distribution proportion of each particle size interval is obtained.

[0080] In the embodiment of the present application, the particle size of the coal can be divided into a plurality of different particle size distribution intervals. After the particle sizes of all the coals in the plurality of sampling images are obtained, the coal distribution proportion of each particle size interval can be counted.

[0081] Step S107. Based on the volume of the coal loaded in the to-be-measured truck compartment and the coal distribution proportion of each particle size interval, the coal load of the to-be-measured truck compartment is estimated to obtain the coal load of the to-be-measured truck compartment, so that the loading of the coal into the to-be-measured truck compartment is stopped when the coal load of the to-be-measured truck compartment exceeds a first preset weight.

[0082] In the embodiment of the present application, the coal distribution proportion of each particle size interval under different proportions can be measured by a preliminary test to obtain the weight of the coal per unit volume, and then the weight of the coal per unit volume is determined based on the obtained coal distribution proportion of each particle size interval, and the coal load of the to-be-measured truck compartment is more accurately estimated according to the volume of the coal loaded in the to-be-measured truck compartment and the determined weight of the coal per unit volume.

[0083] In the embodiment of the present application, the first preset weight is also preset, which is slightly less than the defined load of the truck compartment. When the coal load of the to-be-measured truck compartment just exceeds the first preset weight, it indicates that the coal load of the to-be-measured truck compartment is close to the defined load. At this time, the loading of the coal into the to-be-measured truck compartment can be stopped, so as to avoid the coal load of the truck compartment exceeding the limit and further avoid the risk caused by the overweight of the railway truck.

[0084] Further, a second preset weight can be set in advance, the second preset weight is slightly less than the first preset weight, when the coal load of the to-be-tested wagon exceeds the second preset weight, a prompt information can be generated to prompt, at this time, the lowering conveying rate of the conveyor belt can be controlled to reduce the speed of the conveyor belt loading coal into the to-be-tested wagon, so as to avoid the situation that the coal load of the wagon exceeds the limit due to the too fast conveying rate of the conveyor belt.

[0085] In summary, the railway wagon coal load detection method provided by the present application can obtain the laser point cloud data of the to-be-tested wagon loaded with coal and the multiple sampling images on the conveyor belt used to load coal into the to-be-tested wagon, extract a three-dimensional contour model containing the to-be-tested wagon body and the coal in the wagon body based on the laser point cloud data, determine the volume of the coal loaded in the to-be-tested wagon based on the size of the to-be-tested wagon and the three-dimensional contour model, perform contour recognition on the multiple sampling images to obtain the coal contour in each sampling image in the multiple sampling images, count the particle size of all the coal in the multiple sampling images based on the coal contour in each sampling image in the multiple sampling images, obtain the coal particle size distribution interval based on the particle size of all the coal in the multiple sampling images, and finally estimate the coal load in the to-be-tested wagon based on the volume of the coal loaded in the to-be-tested wagon and the coal particle size distribution interval to obtain the coal load of the to-be-tested wagon, so that the coal loading into the to-be-tested wagon can be stopped when the coal load of the to-be-tested wagon exceeds the first preset weight. In this way, the wagon body can be recognized by the point cloud data, the three-dimensional contour of the medium in the wagon body can be recognized, the volume of the coal loaded in the wagon can be determined, the coal particle size distribution interval can be counted according to the sampling images on the conveyor belt, the coal load of the wagon can be accurately detected according to the volume of the coal loaded in the wagon and the coal particle size distribution interval, the coal load of the wagon can be prevented from exceeding the limit, the risk caused by the overweight of the railway wagon can be avoided, and the present application is convenient for practical application and promotion.

[0086] Please refer to Figure 2 The second aspect of the present application embodiment provides a railway wagon coal load detection device, which comprises:

[0087] An acquisition unit is configured to acquire laser point cloud data of a to-be-tested wagon loaded with coal and multiple sampling images on a conveyor belt used to load coal into the to-be-tested wagon.

[0088] An extraction unit is configured to extract a three-dimensional contour model containing the to-be-tested wagon body and the coal in the wagon body based on the laser point cloud data.

[0089] A determination unit is configured to determine the volume of the coal loaded in the to-be-tested wagon based on the size of the to-be-tested wagon and the three-dimensional contour model.

[0090] a contour recognition unit, configured to perform contour recognition on the plurality of sample images to obtain a coal contour in each sample image in the plurality of sample images;

[0091] a statistics unit, configured to count a granularity of all coals in the plurality of sample images based on the coal contour in each sample image in the plurality of sample images;

[0092] The statistics unit is further configured to obtain a coal distribution proportion of each granularity interval based on the granularity of all coals in the plurality of sample images.

[0093] an operation unit, configured to estimate a coal load of the to-be-tested railway wagon based on a volume of the coal loaded in the to-be-tested railway wagon and the coal distribution proportion of each granularity interval, to obtain the coal load of the to-be-tested railway wagon, so that the to-be-tested railway wagon stops loading the coal when the coal load of the to-be-tested railway wagon exceeds a first preset weight.

[0094] The working process, working details and technical effects of the device provided in the second aspect of the embodiment can be referred to the first aspect of the embodiment, which will not be repeated here.

[0095] As shown in Figure 3 The third aspect of the embodiment of the present application provides another railway wagon coal load detection device, which comprises a memory, a processor and a transceiver connected in sequence and in communication, wherein the memory is configured to store a computer program, the transceiver is configured to transceive messages, and the processor is configured to read the computer program and execute the railway wagon coal load detection method as described in the first aspect of the embodiment.

[0096] For example, the memory can include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a flash memory, a first-in-first-out memory (FIFO) and / or a first-in-last-out memory (FILO), etc.; the processor can be, but is not limited to, a microprocessor of STM32F105 series, an ARM (Advanced RISC Machines) processor or an X86 architecture processor, or a processor integrated with NPU (neural-network processing units); the transceiver can be, but is not limited to, a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0097] The fourth aspect of the embodiment provides a computer readable storage medium storing instructions of the method for detecting the coal load of a railway wagon compartment according to the first aspect of the embodiment, i.e., the computer readable storage medium stores the instructions, and when the instructions are run on a computer, the method for detecting the coal load of a railway wagon compartment according to the first aspect is executed. The computer readable storage medium is a carrier storing data, which can include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash disk, a Memory Stick, etc., and the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0098] The fifth aspect of the embodiment provides a computer program product containing instructions, which, when run on a computer, cause the computer to execute the method for detecting the coal load of a railway wagon compartment according to the first aspect of the embodiment. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0099] It should be understood that specific details are provided in the following description in order to provide a thorough understanding of the example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments can be practiced without these specific details. For example, systems can be shown in block diagram form in order not to obscure the examples in unnecessary detail. In other instances, well-known processes, structures and techniques can be shown without unnecessary detail in order to avoid obscuring the example embodiments.

[0100] Finally, it should be noted that the above only describes the preferred embodiments of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method of detecting the coal load of a railway wagon, characterized in that, The method comprises the following steps: acquiring laser point cloud data of a coal-loaded test wagon and a plurality of sample images on a conveyor belt for loading coal into the test wagon; extracting a three-dimensional contour model containing the test wagon body and coal in the test wagon body based on the laser point cloud data; determining the volume of the coal loaded in the test wagon based on the size of the test wagon and the three-dimensional contour model; performing contour recognition on the plurality of sample images to obtain the coal contour in each sample image of the plurality of sample images; counting the particle size of all the coal in the plurality of sample images based on the coal contour in each sample image of the plurality of sample images; obtaining the coal distribution proportion of each particle size interval based on the particle size of all the coal in the plurality of sample images; estimating the coal load of the test wagon based on the volume of the coal loaded in the test wagon and the coal distribution proportion of each particle size interval to obtain the coal load of the test wagon, so that the loading of coal into the test wagon is stopped when the coal load of the test wagon exceeds a first preset weight.

2. The method of claim 1, wherein, The method further comprises the following steps: performing denoising processing on the laser point cloud data to obtain denoised laser point cloud data; detecting the edge contour line corresponding to the denoised laser point cloud data by a Hough transform method; using the edge contour line corresponding to the denoised laser point cloud data as the edge contour of the test wagon body to establish the three-dimensional contour model containing the test wagon body and the coal in the test wagon body.

3. The method of claim 1, wherein, The method further comprises the following steps: adjusting the contrast of the plurality of sample images to obtain a plurality of adjusted images corresponding to the plurality of sample images one by one; performing binaryzation processing on the plurality of adjusted images to obtain a plurality of binaryzation images corresponding to the plurality of adjusted images one by one; recognizing the coal contour in each binaryzation image of the plurality of binaryzation images by an OpenCV algorithm.

4. The method of claim 1, wherein, The method further comprises the following steps: when the coal load of the test wagon exceeds a second preset weight, generating a prompt information to reduce the speed of the conveyor belt for loading coal into the test wagon, wherein the second preset weight is less than the first preset weight.

5. The method of claim 1, wherein, The particle size of the coal is the surface area of the coal.

6. The method of claim 1, wherein, The method further comprises the following steps: acquiring a wagon image of the test wagon; recognizing the wagon number carried in the wagon image to obtain the wagon number of the test wagon, and determining the size of the test wagon based on the wagon number of the test wagon; or matching the wagon image with the images of sample wagons with known sizes in an image database to obtain the size of the test wagon.

7. The method of claim 1, wherein, The laser point cloud data of the test wagon is obtained by fusing laser point cloud data acquired from a plurality of angles.

8. A railway car coal load weight detection apparatus, characterized by, The method comprises the following steps: An acquisition unit is configured to acquire laser point cloud data of a coal-loaded to-be-tested railway wagon and a plurality of sampling images on a conveyor belt for loading coal to the to-be-tested railway wagon; An extraction unit is configured to extract a three-dimensional contour model of the to-be-tested railway wagon and coal in the to-be-tested railway wagon based on the laser point cloud data; A determination unit is configured to determine a volume of the coal loaded in the to-be-tested railway wagon based on a size of the to-be-tested railway wagon and the three-dimensional contour model; A contour identification unit is configured to perform contour identification on the plurality of sampling images to obtain a coal contour in each of the plurality of sampling images; A statistical unit is configured to count a granularity of all the coal in the plurality of sampling images based on the coal contour in each of the plurality of sampling images; The statistical unit is further configured to obtain a coal distribution proportion of each granularity interval based on the granularity of all the coal in the plurality of sampling images; An operation unit is configured to estimate a coal load of the to-be-tested railway wagon based on the volume of the coal loaded in the to-be-tested railway wagon and the coal distribution proportion of each granularity interval, to obtain the coal load of the to-be-tested railway wagon, so that the to-be-tested railway wagon stops loading coal when the coal load of the to-be-tested railway wagon exceeds a first preset weight.

9. A railway car coal load weight detection apparatus, characterized by, A device comprising a memory, a processor and a transceiver connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive messages, and the processor is configured to read the computer program and execute the railway wagon coal load detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions, and when the instructions run on the computer, the railway wagon coal load detection method according to any one of claims 1-7 is executed.

Images