Obstacle identification method and device for grain depot, computer equipment and storage medium

Abstract

The embodiment of the invention discloses an obstacle recognition method and device for a grain depot, computer equipment and a storage medium. The method comprises the steps that original image data and operation data of the current internal environment of the grain depot are acquired; performing image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; the preprocessed image data and a pre-trained obstacle recognition model are used for obstacle recognition, a recognition result is obtained, and the recognition result comprises an obstacle area in the image data and an obstacle type corresponding to the obstacle area; and performing comprehensive judgment processing on the operation risk according to the operation data, the obstacle area and the obstacle type, and determining a current operation risk prompt. By means of the mode, the obstacles in the internal environment can be automatically recognized through the image data of the grain depot, the obstacle recognition efficiency is improved, comprehensive judgment processing of operation risks is conducted, and the management efficiency and safety of the grain depot are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of grain depot management, and in particular to a method, device, computer equipment and storage medium for identifying obstacles in a grain depot. Background Art

[0002] In grain storage operations, fixed obstacles (such as walls, temperature measurement cables, pillars, etc.) may pose hidden dangers to grain storage, handling, mechanical operation and personnel safety. Traditional management methods rely on manual inspections and records, but this method is not only inefficient, but also prone to missed inspections. It is difficult to obtain the specific location, size and shape of obstacles in real time. The obstacle recognition efficiency is low and cannot meet the needs of modern grain storage intelligent and automated management. Summary of the invention

[0003] The main purpose of the present invention is to provide a method, device, computer equipment and storage medium for obstacle recognition in a grain warehouse, which can solve the problem of low obstacle recognition efficiency in the prior art.

[0004] To achieve the above object, the present invention provides a method for identifying obstacles in a grain depot in a first aspect, the method comprising: Obtain the original image data and operation data of the current internal environment of the grain depot; The original image data is subjected to image preprocessing by sequentially performing denoising, image enhancement and target segmentation to obtain preprocessed image data; Using the preprocessed image data and the pre-trained obstacle recognition model to perform obstacle recognition to obtain a recognition result, wherein the recognition result includes an obstacle area in the image data and an obstacle type corresponding to the obstacle area; A comprehensive judgment and processing of the operation risk is performed based on the operation data, obstacle area and obstacle type to determine the current operation risk prompt.

[0005] In a feasible implementation, the image preprocessing of performing denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data includes: Performing denoising on the original image data using a preset Gaussian filtering algorithm to obtain denoised image data; Performing image enhancement processing on the denoised image data using a preset histogram equalization algorithm to obtain enhanced image data; The enhanced image data is subjected to target segmentation processing using a preset binarization algorithm to obtain a segmented binarized image, and the pre-processed image data includes the segmented binarized image.

[0006] In a feasible implementation, the comprehensive judgment and processing of the operation risk is performed according to the operation data, obstacle area and obstacle type to determine the current operation risk prompt, including: Performing feature extraction using a preset feature extraction algorithm and pixel data of the obstacle area to obtain obstacle features of the obstacle area; A comprehensive judgment and processing of the operation risk is performed based on the operation data, obstacle characteristics, obstacle types and preset operation warning rules to determine the current operation risk prompt.

[0007] In a feasible implementation, the using a preset feature extraction algorithm and the pixel data of the obstacle area to perform feature extraction to obtain obstacle features of the obstacle area includes: Using a preset center of gravity position algorithm, the number of pixels in the obstacle area and the coordinates of each pixel, the center of gravity position coordinates of the obstacle area are obtained, wherein the obstacle feature includes the center of gravity position coordinates; The size of the obstacle area is obtained by using the maximum horizontal and vertical coordinates and the minimum horizontal and vertical coordinates of the pixels in the obstacle area, a preset width algorithm and a height algorithm, and the obstacle feature also includes the size.

[0008] In a feasible implementation, the operation warning rule includes a risk threshold, and the operation data includes the position coordinates of the operator or the operation equipment. Then, the operation risk is comprehensively judged and processed according to the operation data, obstacle characteristics, obstacle type and preset operation warning rules to determine the current operation risk prompt, including: Using the position coordinates and the center of gravity position coordinates, the distance between the obstacle area and the operator or the operating equipment is obtained; Obtaining a target risk threshold using the distance, obstacle type, size, and a preset first weighted algorithm; Using distance, obstacle type, size and a preset second weighted algorithm, a target risk value is obtained; A current operation risk prompt is determined according to the target risk threshold and the target risk value.

[0009] In a feasible implementation, determining the current operation risk prompt according to the target risk threshold and the target risk value includes: If the target risk value is greater than the target risk threshold, the current operation risk prompt is determined to be a first prompt, where the first prompt is used to prompt the operator or the operation equipment that there is a risk of collision with an obstacle; If the target risk value is less than or equal to the target risk threshold, the current operation risk prompt is determined to be the second prompt, and the second prompt is used to prompt the operator or operating equipment that there is no risk of collision with obstacles, and return to execute the step of obtaining the original image data and operation data of the current internal environment of the grain warehouse.

[0010] In a feasible implementation, the mathematical expression of the first weighted algorithm is as follows: ; In the formula, is the target risk threshold, For distance, is the risk function of the obstacle type, is the risk function of size, For environmental factors, , , and They are , , and The weight coefficient of The mathematical expression of the second weighted algorithm is as follows: ; In the formula, is the target risk value, For distance, is the risk weight of the obstacle type, is the risk weight of the size, , and They are , and The weight coefficient of .

[0011] To achieve the above object, the second aspect of the present invention provides an obstacle identification device for a grain depot, the device comprising: Data acquisition module: used to obtain the original image data and operation data of the current internal environment of the grain depot; Image preprocessing module: used for performing image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; Obstacle recognition module: used to use the pre-processed image data and the pre-trained obstacle recognition model to perform obstacle recognition to obtain a recognition result, wherein the recognition result includes an obstacle area in the image data and an obstacle type corresponding to the obstacle area; Risk warning module: used to make a comprehensive judgment and processing of the operation risk according to the operation data, obstacle area and obstacle type, and determine the current operation risk warning.

[0012] To achieve the above-mentioned purpose, the third aspect of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps shown in the first aspect and any feasible implementation method.

[0013] To achieve the above-mentioned purpose, the fourth aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps shown in the first aspect and any feasible implementation method.

[0014] The embodiments of the present invention have the following beneficial effects: The present invention provides an obstacle recognition method for a grain depot, the method comprising: obtaining original image data and operation data of the current internal environment of the grain depot; performing image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; performing obstacle recognition using the preprocessed image data and a pre-trained obstacle recognition model to obtain a recognition result, the recognition result including an obstacle area in the image data and an obstacle type corresponding to the obstacle area; performing a comprehensive judgment and processing of the operation risk according to the operation data, the obstacle area and the obstacle type, and determining the current operation risk prompt. Through the above-mentioned method, obstacles in the internal environment can be automatically recognized through the image data of the grain depot, the efficiency of obstacle recognition can be improved, and a comprehensive judgment and processing of the operation risk can be performed according to the operation data, the obstacle area and the obstacle type, so as to improve the intelligence and automation of the grain depot, and improve the management efficiency and safety of the grain depot. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] in: Figure 1 This is a flow chart of a method for identifying obstacles in a grain depot in an embodiment of the present invention; Figure 2 Another flow chart of a method for identifying obstacles in a grain depot according to an embodiment of the present invention; Figure 3It is a structural block diagram of an obstacle identification device for a grain depot in an embodiment of the present invention; Figure 4 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1 , Figure 1 This is a flow chart of a method for identifying obstacles in a grain depot in an embodiment of the present invention. The method can be applied to both a terminal and a server. The terminal can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server can be implemented by an independent server or a server cluster composed of multiple servers. This embodiment is described by applying to a terminal as an example. Figure 1 The method shown includes the following steps: 101. Obtain the original image data and operation data of the current internal environment of the grain depot; It should be noted that in order to identify obstacles in the grain warehouse, a camera is installed in advance inside the grain warehouse. The camera is used to collect images of the internal environment so that subsequent obstacle identification can be performed based on the captured images. High-definition cameras or other imaging devices can be installed at multiple key locations in the grain warehouse to collect image data of the grain pile surface and the surrounding environment in real time. The image data should have sufficient resolution and clarity to ensure that fixed obstacles such as walls, temperature measurement cables, and pillars can be clearly identified. There is a communication connection between the camera and the server or terminal, and the captured image data can be transmitted to the server or terminal. The server or terminal further processes the image data, and in order to automatically evaluate the operation risk, the operation data is also obtained. The operation data is used to reflect the current operation situation. The operation data includes but is not limited to the location coordinates of the operator or the operation equipment. By obtaining the original image data and operation data of the current internal environment of the grain warehouse, the subsequent obstacle identification and operation risk assessment are realized.

[0019] 102. Perform image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; Furthermore, after obtaining the above-mentioned original image data, the original image data can be preprocessed to reduce the interference of noise and make the obstacle area more obvious. The collected original image can be preprocessed, including denoising, illumination compensation, image enhancement and other operations. Afterwards, the fixed obstacle area in the image is separated from the background using an image segmentation algorithm to ensure the accuracy of subsequent analysis. Specifically, the original image data can be subjected to image preprocessing for denoising, image enhancement and target segmentation in sequence to obtain preprocessed image data, wherein denoising methods include but are not limited to Gaussian filtering, median filtering, etc., image enhancement methods include but are not limited to histogram equalization and other methods for improving image contrast, and target segmentation methods include but are not limited to thresholding methods to achieve image segmentation, such as binarization.

[0020] 103. Perform obstacle recognition using the preprocessed image data and the pre-trained obstacle recognition model to obtain a recognition result, wherein the recognition result includes an obstacle region in the image data and an obstacle type corresponding to the obstacle region; In order to more accurately identify obstacles, an obstacle recognition model is pre-trained, and a deep learning or machine learning algorithm (such as a convolutional neural network CNN) is used to analyze and identify the segmented target area. After a lot of training, the model can identify fixed obstacles such as walls, pillars, and temperature measuring cables, and distinguish different types of obstacles. Therefore, the pre-processed image data and the pre-trained obstacle recognition model can be used to identify obstacles and obtain recognition results. The obstacle types include but are not limited to fixed obstacles such as walls, temperature measuring cables, pillars, etc. In addition, after identifying the fixed obstacles, the system will extract relevant information of the obstacles, including their size, position, shape, etc., and mark this information in the system. Position: the coordinates of the obstacle in the grain warehouse (x, y, z); size: the size of the obstacle (width, height, depth); shape: the geometric shape of the obstacle, such as rectangle, circle, etc.

[0021] For example, a convolutional neural network (CNN) is used to classify and identify fixed obstacles. The convolution layer of CNN can be calculated by the following formula: Convolution operation formula: ; in, I is the input image, K is the convolution kernel, is the feature map after convolution, k is the size of the convolution kernel.

[0022] Pooling operation: The pooling operation is used to reduce the size of the feature map, and the pooling method is maximum pooling.

[0023] ; in, pool region is the pooling area, is the result after pooling. The pooling operation is used to reduce the size of the feature map and extract the most significant features.

[0024] 104. Perform a comprehensive judgment and processing of the operation risk based on the operation data, obstacle area and obstacle type, and determine the current operation risk prompt.

[0025] Furthermore, the system can comprehensively judge the operation risk based on the current operation data and the current obstacle situation, determine the current operation risk prompt, and improve the safety of grain storage operations. It can provide real-time feedback based on the location information of the obstacle and provide operation warnings. When equipment or personnel approach obstacles, the system will issue an alarm to avoid collisions or accidents.

[0026] In one feasible implementation, all identified and labeled obstacle information (including location, size, shape, etc.) will be stored in a database for later query, data analysis or accident tracing.

[0027] The present invention provides an obstacle recognition method for a grain depot, the method comprising: obtaining original image data and operation data of the current internal environment of the grain depot; performing image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; performing obstacle recognition using the preprocessed image data and a pre-trained obstacle recognition model to obtain a recognition result, the recognition result including an obstacle area in the image data and an obstacle type corresponding to the obstacle area; performing a comprehensive judgment and processing of the operation risk according to the operation data, the obstacle area and the obstacle type, and determining the current operation risk prompt. Through the above-mentioned method, obstacles in the internal environment can be automatically recognized through the image data of the grain depot, the efficiency of obstacle recognition can be improved, and a comprehensive judgment and processing of the operation risk can be performed according to the operation data, the obstacle area and the obstacle type, so as to improve the intelligence and automation of the grain depot, and improve the management efficiency and safety of the grain depot.

[0028] See also Figure 2 , Figure 2 FIG. 4 is another flow chart of a method for identifying obstacles in a grain depot according to an embodiment of the present invention. Figure 2 The method shown includes the following steps: 201. Obtaining original image data and operation data of the current internal environment of the grain depot; 202. Perform image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; It should be noted that the contents shown in steps 201 and 202 are the same as Figure 1 The contents of steps 101 and 102 are similar, and are not described here to avoid repetition. For details, please refer to Figure 1 The contents of steps 101 and 102 are shown.

[0029] In a feasible implementation, step 202 includes steps A01 to A03: A01. Perform denoising on the original image data using a preset Gaussian filtering algorithm to obtain denoised image data; Exemplarily, the Gaussian filter formula is as follows: ; In the formula, is the original image pixel value, is the pixel value of the filtered image, that is, the denoised image data, is the standard deviation, which determines the smoothness of the filter. k : Usually take 3 The integer part of is used to determine the size of the Gaussian kernel. I ( x + i , y + j ): indicates that the original image is at position ( x + i , y + j ), i and j : Represents the offset of each element in the Gaussian kernel relative to the center.

[0030] A02. Performing image enhancement processing on the denoised image data using a preset histogram equalization algorithm to obtain enhanced image data; A03. Perform target segmentation processing on the enhanced image data using a preset binarization algorithm to obtain a segmented binary image, wherein the pre-processed image data includes the segmented binary image.

[0031] Exemplarily, the binarization formula is: ; in, is the preset threshold, is the pixel intensity of the image, is the binary image after segmentation.

[0032] 203. Perform obstacle recognition using the preprocessed image data and the pre-trained obstacle recognition model to obtain a recognition result, wherein the recognition result includes an obstacle region in the image data and an obstacle type corresponding to the obstacle region; It should be noted that the content shown in step 203 is the same as Figure 1 The contents of step 103 are similar, and are not described here to avoid repetition. Figure 1 The content of step 103 is shown.

[0033] 204. Perform feature extraction using a preset feature extraction algorithm and the pixel data of the obstacle area to obtain obstacle features of the obstacle area; Furthermore, obstacle information is extracted and annotated. Specifically, a preset feature extraction algorithm and pixel data of the obstacle area are used to extract features, obstacle features of the obstacle area are obtained, and the features are annotated on the image. Obstacle features include but are not limited to position, size and shape, wherein the position may be the center of gravity position, and the size may be the dimensions, such as length, width and height. The feature extraction algorithm includes a center of gravity position algorithm, a width algorithm and a height algorithm.

[0034] In a feasible implementation, step 204 includes steps B01 to B02: B01. Obtaining the coordinates of the center of gravity of the obstacle area by using a preset center of gravity position algorithm, the number of pixels in the obstacle area, and the coordinates of each pixel, wherein the obstacle feature includes the center of gravity position coordinates; Exemplarily, the center of gravity position algorithm includes the following expression: , ; In the formula, , is the coordinate of the center of gravity of the obstacle area, x i , y i are the coordinates of each pixel point in the obstacle area, N is the number of pixels in this area.

[0035] B02. Utilizing the maximum horizontal and vertical coordinates and the minimum horizontal and vertical coordinates of the pixels in the obstacle area, a preset width algorithm, and a preset height algorithm, the size of the obstacle area is obtained, wherein the obstacle feature also includes the size.

[0036] Exemplarily, the size includes width and height, wherein the width algorithm includes the following expression: ; In the formula, is the width of the obstacle area, is the maximum horizontal coordinate of the pixel points in the obstacle area, is the minimum horizontal coordinate of the pixel points in the obstacle area; Exemplarily, the height algorithm includes the following expression: ; In the formula, is the height of the obstacle area, is the maximum ordinate of the pixel points in the obstacle area, is the minimum vertical coordinate of the pixel point in the obstacle area.

[0037] 205. Perform a comprehensive judgment and processing of the operation risk based on the operation data, obstacle characteristics, obstacle type and preset operation warning rules to determine the current operation risk prompt.

[0038] It should be noted that the present invention designs a comprehensive risk assessment model, combines the distance between the obstacle and the person or equipment, the risk weight of the obstacle type, and the weight of the obstacle size, and calculates a more accurate and dynamic alarm determination function. This method comprehensively considers multiple attributes of the obstacle (including location, type, size, etc.), thereby improving the accuracy and safety of the alarm system, wherein the operation warning rule includes a risk threshold, the operation data includes the location coordinates of the operator or the operation equipment, and the comprehensive risk assessment model includes a first weighted algorithm for dynamically calculating the current target risk threshold and a second weighted algorithm for the target risk value, then step 205 includes steps C01 to C04: C01. Obtaining the distance between the obstacle area and the operator or operating equipment using the position coordinates and the center of gravity position coordinates; For example, the distance The following mathematical expression is used: ; In the formula, ( , ) is the position coordinate of the operator or equipment, the operator or equipment can be an operating robot, ( , ) is the position coordinate of the obstacle, wherein the position coordinate can be the center of gravity position coordinate.

[0039] C02. Obtaining a target risk threshold by using the distance, obstacle type, size, and a preset first weighted algorithm; It is understandable that traditional alarm systems usually use fixed thresholds. This method is simple but lacks flexibility and adaptability and cannot cope with complex operating environments. For this reason, the present invention proposes a threshold calculation method based on dynamic environmental changes, which uses the robot's real-time position, environmental changes (such as grain pile density, temperature and humidity, etc.) and operating status to adaptively calculate the alarm threshold. This threshold is not only based on the distance between the target and the obstacle, but also takes into account factors such as the type, size, and operating environment of the obstacle, ensuring that the alarm condition is safer and more adaptable.

[0040] In a feasible implementation, the mathematical expression of the first weighted algorithm is as follows: ; In the formula, is the target risk threshold, For distance, is the risk function of the obstacle type, which assigns different risk values ​​based on the obstacle type. The risk function is a size function that adjusts the size of the obstacle to give different risk values. It is an environmental factor, reflecting the impact of the operating conditions in the grain depot (such as temperature, humidity, light conditions, etc.) on the operation. , , and They are , , and The weight coefficient indicates the relative importance of each factor in the overall threshold calculation.

[0041] It should be noted that the use of the first weighted algorithm has the following advantages: (1) Strong adaptability: The dynamically calculated threshold can automatically adjust the alarm conditions according to changes in the operating environment, thereby improving the system's adaptability. For example, in an environment with high temperature or high humidity, the system will appropriately adjust the alarm threshold to ensure that the robot's safe distance and alarm trigger conditions are more in line with the actual operating environment. (2) Enhanced safety: By introducing environmental factors, the system can comprehensively consider the complexity of the grain warehouse environment (such as operating conditions, obstacle density, etc.), so that the alarm system can more accurately respond to potential dangers and avoid false alarms or missed alarms caused by fixed thresholds. (3) Refined management: The dynamic calculation of the threshold can be optimized for different operating areas, operating stages, and operating objectives, making the design of alarm conditions during the robot's operation more refined and further improving operational safety.

[0042] C03. Obtain the target risk value by using the distance, obstacle type, size and the preset second weighted algorithm; In a feasible implementation, the mathematical expression of the second weighted algorithm is as follows: ; In the formula, is the target risk value, For distance, The risk weight of the obstacle type. For example, obstacles such as walls, temperature measurement cables, and pillars have different risk levels and weights. The risk weight for size is the effect of the size of the obstacle on the robot’s operation. A larger obstacle may have a greater impact on the robot’s operating area. , and They are , and The weight coefficient of .

[0043] It should be noted that the use of the second weighted algorithm has the following benefits: (1) Accurate risk assessment: Compared with traditional methods, the present invention takes into account the different effects of obstacle types and sizes on operations and can more accurately assess potential risks. For example, the impact of collisions between walls and small items (such as tools) is significantly different, and the present invention can reasonably adjust the alarm mechanism based on these differences. (2) Reducing false alarms and missed alarms: By combining the weights of multiple risk factors, the system can dynamically adjust the alarm conditions according to the different requirements of the actual operation scenario, avoid unnecessary false alarms, and improve the response speed to important obstacles.

[0044] C04. Determine the current operation risk warning according to the target risk threshold and the target risk value.

[0045] It can be understood that after obtaining the target risk threshold and the target risk value, the target risk threshold and the target risk value can be used to judge the operation risk situation, so as to provide a more accurate current operation risk prompt.

[0046] In a feasible implementation, step C04 includes steps D01 to D02: D01. If the target risk value is greater than the target risk threshold, the current operation risk prompt is determined to be the first prompt, where the first prompt is used to prompt the operator or the operation equipment that there is a risk of collision with an obstacle; D02. If the target risk value is less than or equal to the target risk threshold, the current operation risk prompt is determined to be the second prompt, and the second prompt is used to prompt the operator or operating equipment that there is no risk of collision with obstacles, and return to execute the step of obtaining the original image data and operation data of the current internal environment of the grain warehouse.

[0047] Furthermore, by comparing the dynamically calculated target risk value with the target risk threshold, an operation risk prompt is output. If the target risk value is greater than the target risk threshold, it is considered that the obstacle affects the robot operation and there is a collision risk. The current operation risk prompt is determined to be the first prompt. The first prompt is used to prompt the operator or the operating equipment that there is a collision risk with the obstacle. On the contrary, if the target risk value is less than or equal to the target risk threshold, it is considered that the obstacle does not affect the robot operation and there is no collision risk for the time being. The current operation risk prompt is determined to be the second prompt. The second prompt is used to prompt the operator or the operating equipment that there is no collision risk with the obstacle. In this way, real-time monitoring can be maintained. Therefore, the step of obtaining the original image data and operation data of the current internal environment of the grain warehouse is returned to execute. By real-time monitoring of the position of the obstacle, a safety alarm is triggered when the equipment or personnel approach the obstacle.

[0048] In summary, the present invention solves the common problems of false alarms, missed alarms and poor adaptability in traditional alarm systems through a comprehensive risk assessment model and a dynamic threshold calculation method. The innovative alarm judgment formula takes into account multiple factors such as the distance between the target and the obstacle, the risk weight of the obstacle type, and the weight of the obstacle size, further optimizing the alarm mechanism. By introducing dynamically calculated thresholds, adjustments are made according to environmental factors and operating conditions to ensure the flexibility and safety of the alarm conditions, thereby improving the intelligence level and safety of the system.

[0049] The present invention provides an obstacle recognition method for a grain depot, the method comprising: obtaining original image data and operation data of the current internal environment of the grain depot; performing image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; performing obstacle recognition using the preprocessed image data and a pre-trained obstacle recognition model to obtain a recognition result, the recognition result including an obstacle area in the image data and an obstacle type corresponding to the obstacle area; performing feature extraction using a preset feature extraction algorithm and pixel data of the obstacle area to obtain obstacle features of the obstacle area; performing comprehensive judgment processing of operation risks according to the operation data, obstacle features, obstacle types and preset operation warning rules to determine the current operation risk prompt. Through the above-mentioned method, obstacles in the internal environment can be automatically identified through the image data of the grain depot, the efficiency of obstacle recognition can be improved, and comprehensive judgment processing of operation risks can be performed according to the operation data, obstacle area and obstacle type, the intelligence and automation of the grain depot can be improved, and the management efficiency and safety of the grain depot can be improved. The fixed obstacle recognition and marking system of the grain depot of the present invention can significantly improve the safety and efficiency of grain depot operations. Through automatic identification and labeling, human intervention is reduced, the accuracy and response speed of management are improved, the smooth operation of the grain warehouse is ensured, and the process of intelligent and automated grain warehouse management is promoted.

[0050] See also Figure 3 , Figure 3 FIG. 1 is a structural block diagram of an obstacle identification device for a grain depot in an embodiment of the present invention. Figure 3 The device shown comprises: Data acquisition module 301: used to acquire the original image data and operation data of the current internal environment of the grain depot; Image preprocessing module 302: used to perform image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; Obstacle recognition module 303: used to perform obstacle recognition using the preprocessed image data and the pre-trained obstacle recognition model to obtain a recognition result, wherein the recognition result includes an obstacle area in the image data and an obstacle type corresponding to the obstacle area; The risk warning module 304 is used to perform a comprehensive judgment and processing of the operation risk according to the operation data, obstacle area and obstacle type, and determine the current operation risk warning.

[0051] It should be noted that Figure 3 The contents of each module in the device shown are Figure 1 The contents of each step in the method shown are similar. To avoid repetition, they are not described here. For details, please refer to Figure 1 The content of each step in the method shown.

[0052] The present invention provides an obstacle identification device for a grain depot, the device comprising: a data acquisition module: used to acquire the original image data and operation data of the current internal environment of the grain depot; an image preprocessing module: used to perform image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; an obstacle identification module: used to perform obstacle identification using the preprocessed image data and a pre-trained obstacle identification model to obtain an identification result, the identification result including an obstacle area in the image data and an obstacle type corresponding to the obstacle area; a risk warning module: used to perform a comprehensive judgment and processing of the operation risk according to the operation data, the obstacle area and the obstacle type, and determine the current operation risk warning. Through the above device, obstacles in the internal environment can be automatically identified through the image data of the grain depot, the obstacle identification efficiency can be improved, and a comprehensive judgment and processing of the operation risk can be performed according to the operation data, the obstacle area and the obstacle type, so as to improve the intelligence and automation of the grain depot, and improve the management efficiency and safety of the grain depot.

[0053] Figure 4 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 4As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0054] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps: Figure 1 or Figure 2 Steps shown.

[0055] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor performs the following steps: Figure 1 or Figure 2 Steps shown.

[0056] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0057] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0058] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for identifying obstacles in a grain depot, characterized in that: The method comprises: Obtain the original image data and operation data of the current internal environment of the grain depot; The original image data is subjected to image preprocessing by sequentially performing denoising, image enhancement and target segmentation to obtain preprocessed image data; Using the preprocessed image data and the pre-trained obstacle recognition model to perform obstacle recognition to obtain a recognition result, wherein the recognition result includes an obstacle area in the image data and an obstacle type corresponding to the obstacle area; A comprehensive judgment and processing of the operation risk is performed based on the operation data, obstacle area and obstacle type to determine the current operation risk prompt.

2. The method according to claim 1, characterized in that: The image preprocessing of performing denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data includes: Performing denoising on the original image data using a preset Gaussian filtering algorithm to obtain denoised image data; Performing image enhancement processing on the denoised image data using a preset histogram equalization algorithm to obtain enhanced image data; The enhanced image data is subjected to target segmentation processing using a preset binarization algorithm to obtain a segmented binarized image, and the pre-processed image data includes the segmented binarized image.

3. The method according to claim 1, characterized in that: The comprehensive judgment and processing of the operation risk is performed according to the operation data, obstacle area and obstacle type to determine the current operation risk prompt, including: Performing feature extraction using a preset feature extraction algorithm and pixel data of the obstacle area to obtain obstacle features of the obstacle area; A comprehensive judgment and processing of the operation risk is performed based on the operation data, obstacle characteristics, obstacle types and preset operation warning rules to determine the current operation risk prompt.

4. The method according to claim 3, characterized in that: The using a preset feature extraction algorithm and the pixel data of the obstacle area to perform feature extraction to obtain obstacle features of the obstacle area includes: Using a preset center of gravity position algorithm, the number of pixels in the obstacle area and the coordinates of each pixel, the center of gravity position coordinates of the obstacle area are obtained, wherein the obstacle feature includes the center of gravity position coordinates; The size of the obstacle area is obtained by using the maximum horizontal and vertical coordinates and the minimum horizontal and vertical coordinates of the pixels in the obstacle area, a preset width algorithm and a height algorithm, and the obstacle feature also includes the size.

5. The method according to claim 4, characterized in that: The operation warning rule includes a risk threshold, and the operation data includes the position coordinates of the operator or the operation equipment. The operation risk is comprehensively judged and processed according to the operation data, obstacle characteristics, obstacle types and preset operation warning rules to determine the current operation risk prompt, including: Using the position coordinates and the center of gravity position coordinates, the distance between the obstacle area and the operator or the operating equipment is obtained; Obtaining a target risk threshold using the distance, obstacle type, size, and a preset first weighted algorithm; The target risk value is obtained by using the distance, obstacle type, size and a preset second weighted algorithm; A current operation risk prompt is determined according to the target risk threshold and the target risk value.

6. The method according to claim 5, characterized in that: Determining the current operation risk prompt according to the target risk threshold and the target risk value includes: If the target risk value is greater than the target risk threshold, the current operation risk prompt is determined to be a first prompt, where the first prompt is used to prompt the operator or the operation equipment that there is a risk of collision with an obstacle; If the target risk value is less than or equal to the target risk threshold, the current operation risk prompt is determined to be the second prompt, and the second prompt is used to prompt the operator or operating equipment that there is no risk of collision with obstacles, and return to execute the step of obtaining the original image data and operation data of the current internal environment of the grain warehouse.

7. The method according to claim 5, characterized in that: The mathematical expression of the first weighted algorithm is as follows: ； In the formula, is the target risk threshold, For distance, is the risk function of the obstacle type, is the risk function of size, For environmental factors, , , and They are , , and The weight coefficient of The mathematical expression of the second weighted algorithm is as follows: ； In the formula, is the target risk value, For distance, is the risk weight of the obstacle type, is the risk weight of the size, , and They are , and The weight coefficient of .

8. An obstacle identification device for a grain depot, characterized in that: The device comprises: Data acquisition module: used to obtain the original image data and operation data of the current internal environment of the grain depot; Image preprocessing module: used for performing image preprocessing of denoising, image enhancement and target segmentation on the original image data in sequence to obtain preprocessed image data; Obstacle recognition module: used to use the pre-processed image data and the pre-trained obstacle recognition model to perform obstacle recognition to obtain a recognition result, wherein the recognition result includes an obstacle area in the image data and an obstacle type corresponding to the obstacle area; Risk warning module: used to make a comprehensive judgment and processing of the operation risk according to the operation data, obstacle area and obstacle type, and determine the current operation risk warning.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images