Methods, devices, equipment, and media for detecting moving objects during ore transportation

Abstract

This disclosure presents a method, apparatus, device, and medium for detecting moving objects during ore transportation. One specific implementation of the method includes: performing grayscale transformation on a ore transportation image to generate a grayscale transportation image; inputting the grayscale transportation image into a preset filter; sharpening the ore transportation image; binarizing the sharpened transportation image; determining at least one moving object image; cropping the ore transportation image to generate at least one moving object image; and for each moving object image in the at least one moving object image, inputting the moving object image into a pre-trained moving object recognition model to obtain a moving object recognition result. This implementation avoids the waste of crushing equipment resources and transportation equipment resources.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to methods, apparatus, devices, and media for detecting moving objects based on ore transportation. Background Technology

[0002] During ore crushing and transportation, it is necessary to detect moving metal objects in the ore pile to prevent damage to crushing equipment (e.g., jaw crushers) and transportation equipment (e.g., conveyor belts). Currently, the common method for detecting moving metal objects in ore piles is to deploy cameras at locations such as the conveyor belt discharge port and above the belt to acquire images of the ore being transported. A pre-trained neural network model then analyzes the object image information in the ore transport images in real time to identify and trigger alarms for moving metal objects.

[0003] However, when using the above method to detect moving metal objects in ore piles, the following technical problems often arise:

[0004] First, due to the varying brightness and low brightness of different areas during ore crushing and transportation, the trained neural network model cannot accurately identify moving metal objects, resulting in the passage of moving metal objects through the crushing and transportation equipment, thus wasting the resources of the crushing and transportation equipment.

[0005] Secondly, when sharpening mineral transport images to improve the resolution of image edges, the Unsharpened Mask (USM) sharpening method is usually used. However, because mineral transport images are often blurry, the USM sharpening method is not very effective at improving the resolution of mineral transport image edges. This may result in the inability to identify moving metal objects due to low edge resolution, leading to the waste of crushing and transport equipment resources as these objects pass through.

[0006] Third, during the crushing and transportation of ore, smaller ore and metal moving objects will not cause damage to the crushing and transportation equipment. However, when the object image information of the mineral transportation image is analyzed in real time by a pre-trained neural network model, all moving objects in the mineral transportation image will be identified, which will take a long time to identify the metal moving objects displayed in the mineral transportation image. Summary of the Invention

[0007] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion later. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0008] Some embodiments of this disclosure provide methods, apparatus, electronic devices, computer-readable media, and computer program products for detecting moving objects based on ore transportation, in order to solve one or more of the technical problems mentioned in the background section above.

[0009] In a first aspect, some embodiments of this disclosure provide a moving object detection method based on ore transportation. The method includes: acquiring a ore transportation image and a preset ore transportation mask image; performing masking processing on the ore transportation image according to the preset ore transportation mask image to generate a ore transportation image; performing grayscale transformation processing on the ore transportation image to generate a grayscale transportation image; inputting the grayscale transportation image into a preset filter to obtain a filtered transportation image; performing sharpening processing on the ore transportation image based on the filtered transportation image to generate a sharpened transportation image; performing binarization processing on the sharpened transportation image to generate a binarized transportation image; determining at least one moving object image information based on the binarized transportation image; performing cropping processing on the ore transportation image based on the at least one moving object image information to generate at least one moving object image; and inputting each of the at least one moving object images into a pre-trained moving object recognition model to obtain a moving object recognition result.

[0010] Secondly, some embodiments of this disclosure provide a moving object detection device based on ore transportation. The device includes: an acquisition unit configured to acquire a ore transportation image and a preset ore transportation mask image; a mask processing unit configured to perform mask processing on the ore transportation image according to the preset ore transportation mask image to generate a ore transportation image; a grayscale transformation processing unit configured to perform grayscale transformation processing on the ore transportation image to generate a grayscale transportation image; a first input unit configured to input the grayscale transportation image into a preset filter to obtain a filtered transportation image; and a sharpening processing unit configured to perform sharpening processing on the ore transportation image based on the filtered transportation image. The system includes a sharpening unit for generating a sharpened transport image, a binarization unit configured to perform binarization processing on the sharpened transport image to generate a binarized transport image, an opening unit configured to determine at least one moving object image based on the binarized transport image, a cropping unit configured to crop the mineral transport image based on the at least one moving object image information to generate at least one moving object image, and a second input unit configured to input each of the at least one moving object image into a pre-trained moving object recognition model to obtain a moving object recognition result.

[0011] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0012] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0013] Fifthly, some embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0014] The various embodiments of this disclosure have the following beneficial effects: the moving object detection method based on ore transportation according to some embodiments of this disclosure avoids the waste of crushing equipment resources and transportation equipment resources. Specifically, the waste of crushing equipment resources and transportation equipment resources is caused by the fact that the brightness of different areas during ore crushing and transportation is different and the brightness is low, which makes the trained neural network model unable to accurately identify moving metal objects, resulting in the moving metal objects passing through the crushing and transportation equipment, thus wasting crushing equipment resources and transportation equipment resources. Based on this, the moving object detection method based on ore transportation according to some embodiments of this disclosure first performs grayscale transformation processing on the ore transportation image to generate a grayscale transportation image. This can enhance the contrast of the ore transportation image, making it easier to distinguish the ore image from the background. Second, the grayscale transportation image is input into a preset filter to obtain a filtered transportation image. This can smooth and denoise the grayscale transportation image while preserving the edge details of the grayscale transportation image. Then, based on the filtered transportation image, the ore transportation image is sharpened to generate a sharpened transportation image; the sharpened transportation image is binarized to generate a binarized transportation image. Therefore, the mineral transport image can be converted into a binary image, facilitating the determination of the position of moving metal objects within the mineral transport image. Then, based on the binarized transport image, at least one moving object image is determined; based on this at least one moving object image, the mineral transport image is cropped to generate at least one moving object image. This allows for the cropping of moving object images from the mineral transport image. Finally, for each of the at least one moving object image, it is input into a pre-trained moving object recognition model to obtain the moving object recognition result. Thus, moving metal objects in the mineral transport image can be identified before they pass through crushing or transport equipment, preventing damage to the equipment and thus avoiding waste of crushing and transport equipment resources. Attached Figure Description

[0015] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0016] Figure 1 This is a flowchart of some embodiments of the moving object detection method based on ore transportation according to the present disclosure;

[0017] Figure 2 This is a schematic diagram of the deployment of the imaging equipment according to the moving object detection method based on ore transportation disclosed herein;

[0018] Figure 3 These are schematic diagrams of some embodiments of the moving object detection device based on ore transportation according to the present disclosure;

[0019] Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0020] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0021] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0022] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0023] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0024] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0025] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] Figure 1 A flow 100 of some embodiments of a moving object detection method based on ore transportation according to the present disclosure is shown. The moving object detection method based on ore transportation includes the following steps:

[0027] Step 101: Perform grayscale transformation on the mineral transport image to generate a grayscale transport image.

[0028] In some embodiments, the executing entity (e.g., a computing device) of the moving object detection method based on ore transportation can perform grayscale transformation processing on the aforementioned mineral transportation image to generate a grayscale transportation image. The aforementioned mineral transportation image may be a photographed image of minerals within a jaw crusher.

[0029] In some alternative implementations of some embodiments, such as Figure 2 As shown, the aforementioned execution entity can use a pre-set shooting device with communication capabilities (such as...). Figure 2 (As shown in 201, 202, and 203) acquiring mineral transportation images. In practice, firstly, the aforementioned executing entity can acquire mineral transportation video sent by the capturing device. Secondly, the aforementioned executing entity can perform video frame extraction processing on the aforementioned mineral transportation video to generate a mineral transportation video frame sequence. This video frame extraction processing can involve extracting individual video frames from the mineral transportation video. Thirdly, the aforementioned executing entity can determine any mineral transportation video frame from the aforementioned mineral transportation video frame sequence as a mineral transportation image. For example... Figure 2 As shown, imaging devices 201 and 202 can capture images of mineral transport at the inlet of the jaw crusher. Imaging device 203 can capture images of mineral transport at the outlet of the jaw crusher. The jaw crusher can be a device used for crushing ore. For example, the jaw crusher can be a jaw crusher. The inlet of the jaw crusher is connected to a chamber. The outlet of the jaw crusher is connected to a conveyor belt. The chamber can be an area for storing mined ore.

[0030] In practice, the aforementioned implementing entity can perform grayscale transformation processing on the above-mentioned mineral transportation images through the following steps to generate grayscale transportation images:

[0031] The first step is to obtain a preset mineral transport mask image.

[0032] In some embodiments, the executing entity may obtain a preset mineral transport mask image from a target database via a wired or wireless connection. The target database may be a database storing the preset mineral transport mask images.

[0033] The second step is to perform masking processing on the mineral transport image based on the preset mineral transport mask image to generate a masked transport image.

[0034] In some embodiments, the execution entity may perform masking processing on the mineral transport image based on the preset mineral transport mask image to generate a masked transport image. The preset mineral transport mask image may be a pre-defined mineral transport mask image used for masking.

[0035] The third step involves dividing the masked transport image into at least one segmented transport image as a set of segmented transport images. In practice, the masked transport image can be divided into multiple images of preset sizes. These preset sizes can be pre-defined image sizes. For example, the preset-size image could be a 3x3 pixel image. As another example, the preset-size image could be a 7x7 pixel image.

[0036] Fourth, for each segmented transportation image in the above-mentioned segmented transportation image set, perform the following processing steps:

[0037] The first processing step is to determine the mean pixel value of each segmented transportation pixel in the above-mentioned segmented transportation image. In practice, Gaussian filtering can be used to determine the mean pixel value of each segmented transportation pixel in the segmented transportation image, and the above mean value can be used as the pixel mean.

[0038] The second processing step involves, for each segmented transportation pixel in the segmented transportation image, modifying the pixel value of the segmented transportation pixel to a first preset pixel value in response to the pixel value being greater than or equal to the pixel mean. The first preset pixel value can be a pre-defined pixel value. For example, the first preset pixel value can be 255.

[0039] The third processing step involves combining the modified segmented transport images to generate a grayscale transport image. This combination process can be performed by merging the modified segmented transport images according to their positions within the masked transport image to generate the grayscale transport image.

[0040] Optionally, after the second processing step, for each segmented transportation pixel in the segmented transportation image, in response to the pixel value of the segmented transportation pixel being less than the pixel mean, the pixel value of the segmented transportation pixel is modified to a second preset pixel value. The second preset pixel value can be a pixel value that is pre-set and different from the first preset pixel value. For example, the second preset pixel value can be 0.

[0041] Step 102: Input the grayscale transport image into a preset filter to obtain a filtered transport image.

[0042] In some embodiments, the executing entity may input the grayscale transport image into a preset filter to obtain a filtered transport image. The preset filter may be a pre-defined filter. For example, the preset filter may be a bilateral filter.

[0043] Step 103: Based on the filtered transport image, sharpen the mineral transport image to generate a sharpened transport image.

[0044] In some embodiments, the execution entity may sharpen the mineral transport image based on the filtered transport image to generate a sharpened transport image.

[0045] In practice, the aforementioned executing entity can perform sharpening processing on the aforementioned mineral transportation image based on the aforementioned filtered transportation image through the following steps to generate a sharpened transportation image:

[0046] First, the filtered transport image is determined as the first sharpening channel.

[0047] Second, extract the luminance component of the color space from the aforementioned mineral transport image. In practice, firstly, the executing entity can extract the RGB color components of the pixels in the aforementioned mineral transport image using an RGB component extraction algorithm. Secondly, the executing entity can use an RGB and HSV mutual conversion algorithm to convert the aforementioned RGB color components into HSV color components (luminance components of the color space).

[0048] Third, the luminance component of the aforementioned color space is determined as a lightness channel and superimposed on the first sharpening channel. Then, according to a set sharpening factor, the mineral transport image is sharpened to generate a sharpened transport image. Here, each pixel in the mineral transport image is sharpened according to the set sharpening factor to generate the sharpened transport image.

[0049] In practice, the aforementioned executing entity can use the following formula to sharpen the mineral transport images to generate sharpened transport images:

[0050] Img_out=Img_source+(Img_v×β+Img_fuzzy×α),

[0051] Wherein, Img_o represents the sharpened pixel value. Img_source represents the pixel value of the target filtered transport pixel. The aforementioned target filtered transport pixel can be a pixel in the filtered transport image that has the same pixel position as the pixel in the mineral transport image. Img_v represents the luminance component of the color space. Img_fuzzy represents the pixel value of the mineral transport image pixel. α represents the first sharpening factor. β represents the second sharpening factor. Here, there are no restrictions on the setting of the first and second sharpening factors. They can be sharpening factors obtained experimentally.

[0052] The fifth sharpening step involves updating the pixel values ​​of the mineral transport image pixels based on the aforementioned sharpening pixel values. In practice, the pixel values ​​of the mineral transport image pixels can be changed to the aforementioned sharpening pixel values.

[0053] The second step is to determine the mineral transport image as a sharpened transport image in response to the detection that all the pixels of each mineral transport image included in the mineral transport image have been updated.

[0054] The relevant content in step 103 above serves as an inventive point of this disclosure, solving the second technical problem mentioned in the background art: "When sharpening mineral transport images to improve the resolution of image edges, the USM (Unsharpen Mask) sharpening method is usually used. However, because mineral transport images are usually blurry, the USM sharpening method is ineffective in improving the resolution of mineral transport image edges. This low resolution may lead to the inability to identify moving metal objects, resulting in the passage of moving metal objects through crushing and transport equipment, thus wasting crushing and transport equipment resources." The factors causing this waste of crushing and transport equipment resources are often as follows: When sharpening mineral transport images to improve the resolution of image edges, the USM (Unsharpen Mask) sharpening method is usually used. However, because mineral transport images are usually blurry, the USM sharpening method is ineffective in improving the resolution of mineral transport image edges. This low resolution may lead to the inability to identify moving metal objects, thus causing the passage of moving metal objects through crushing and transport equipment, thus wasting crushing and transport equipment resources. Solving the above factors can prevent the waste of crushing and transportation equipment resources. To achieve this, firstly, the filtered transportation image is used as the first sharpening channel. This provides data support for color component conversion. Secondly, the luminance component of the color space is extracted from the mineral transportation image. This allows the RGB color components to be converted to HSV color components. This provides data support for sharpening the pixels of the mineral transportation image. Finally, the luminance component of the color space is superimposed on the first sharpening channel as a brightness channel, and the mineral transportation image is sharpened according to a set sharpening factor to obtain a sharpened transportation image. This avoids poor sharpening results due to blurry mineral transportation images. Therefore, the resolution of the mineral transportation image edges is improved, and moving metal objects at the edges of the mineral transportation image can be effectively identified, avoiding the waste of crushing and transportation equipment resources.

[0055] Step 104: Binarize the sharpened transport image to generate a binarized transport image.

[0056] In some embodiments, the execution entity may perform binarization processing on the sharpened transport image to generate a binarized transport image. In practice, firstly, the sharpened transport image is segmented to generate a set of segmented sharpened transport images. Secondly, for each segmented sharpened transport image in the set, the average pixel value of the segmented sharpened transport image is determined using a Gaussian filtering method. Furthermore, for each segmented sharpened transport pixel in the segmented sharpened transport image, in response to the segmented sharpened transport pixel being greater than the average pixel value of the segmented sharpened transport image, the pixel value of the segmented sharpened transport pixel is changed to a first preset pixel value. In response to the segmented sharpened transport pixel being less than or equal to the average pixel value of the segmented sharpened transport image, the pixel value of the segmented sharpened transport pixel is changed to a second preset pixel value.

[0057] Step 105: Determine at least one moving object image information based on the binarized transport image.

[0058] In some embodiments, the execution entity may determine at least one moving object image information based on the binarized transport image.

[0059] In practice, the aforementioned executing entity can determine at least one moving object image information through the following steps:

[0060] The first step is to perform an opening operation on the aforementioned binarized transport image to generate an opened binarized transport image as a compressed binary image. This opening operation can be an image opening operation.

[0061] The second step is to perform a dilation operation on the compressed binary image to generate a dilated binary image, which can be used as an expanded binary image.

[0062] Third, in response to the detection that at least one connected component exists in the above-mentioned expanded binary image, for each of the at least one connected component, the following determination steps are performed:

[0063] The first step is to determine the contours of the connected regions. In practice, the executing entity can use an OpenCV-based contour detection algorithm to determine the contours of the connected regions. Alternatively, the executing entity can use an 8-direction connected component statistical algorithm to determine the individual connected regions included in the extended binary image.

[0064] The second determination step involves determining the set of contour coordinates for the connected region contour, based on the aforementioned contour of the connected region. Each contour coordinate in this set can be the coordinate of a key point of the connected region contour in a Cartesian coordinate system with the lower left corner of the expanded binary image as the origin. In practice, the execution entity can use an OpenCV-based contour scanning algorithm to find key points and determine the set of contour coordinates corresponding to each key point of the connected region contour.

[0065] The third step involves determining the coordinate set of the circumscribed rectangle corresponding to the aforementioned connected region based on the aforementioned contour coordinate set. In practice, the executing entity can use the minimum bounding rectangle algorithm based on OpenCV to determine the minimum bounding rectangle of the connected region based on the aforementioned contour coordinate set, and to determine the coordinates of each vertex of the minimum bounding rectangle as the circumscribed rectangle coordinate set. Each circumscribed rectangle coordinate in the aforementioned circumscribed rectangle coordinate set can be the coordinate of each vertex of the minimum bounding rectangle in a Cartesian coordinate system established with the lower left corner of the expanded binary image as the origin.

[0066] The fourth determination step involves determining the moving object image information corresponding to the connected region based on the aforementioned set of circumscribed rectangle coordinates. This moving object image information may include the moving object area value and the moving object category. The moving object area value can be the area of ​​the moving object in the aforementioned binary transport image. The moving object category can be a pre-defined shape category. For example, the moving object category can be a rectangular moving object. It can also be a strip-shaped moving object. In practice, firstly, the executing entity can determine the difference in horizontal and vertical coordinate distances of the minimum circumscribed rectangle based on the set of circumscribed rectangle coordinates. The difference in horizontal coordinate distance can be the difference between the maximum and minimum horizontal coordinate values ​​in the set of circumscribed rectangle coordinates. The difference in vertical coordinate distance can be the difference between the maximum and minimum vertical coordinate values ​​in the set of circumscribed rectangle coordinates. Secondly, the executing entity can determine the moving object area value by multiplying the difference in horizontal and vertical coordinate distances of the minimum circumscribed rectangle. Then, in response to the ratio of the difference in horizontal coordinate distance to the difference in vertical coordinate distance being within a preset ratio range, the moving object category of the aforementioned connected region can be determined as a rectangular moving object. Finally, in response to the ratio of the difference in horizontal coordinate distance to the difference in vertical coordinate distance being outside the aforementioned preset ratio range, the moving object category of the aforementioned connected region can be determined as a strip-shaped moving object. The aforementioned preset ratio range can be a pre-defined range of the ratio of the difference in horizontal coordinate distance to the difference in vertical coordinate distance. For example, the aforementioned preset ratio range can be greater than or equal to 0.5 and less than or equal to 2.

[0067] The aforementioned optional content serves as an inventive point of this disclosure, solving the third technical problem mentioned in the background art: "During ore crushing and transportation, smaller ore and metal moving objects will not cause damage to the crushing and transportation equipment. However, when a pre-trained neural network model analyzes the object image information of the mineral transportation image in real time, it will identify all moving objects in the mineral transportation image, resulting in a long time required to identify the metal moving objects displayed in the mineral transportation image." The factors causing this long time requirement for identifying metal moving objects displayed in the mineral transportation image are often as follows: During ore crushing and transportation, smaller ore and metal moving objects will not cause damage to the crushing and transportation equipment. However, when a pre-trained neural network model analyzes the object image information of the mineral transportation image in real time, it will identify all moving objects in the mineral transportation image, resulting in a long time required to identify the metal moving objects displayed in the mineral transportation image. Solving these factors can reduce the time required to identify metal moving objects displayed in the mineral transportation image. To achieve this effect, firstly, for each pixel in the aforementioned mineral transport image, the following sharpening steps are performed: First, the binarized transport image is subjected to an opening operation to generate an opened binarized transport image as a compressed binary image. This removes small mineral particles and small moving metal objects from the binarized transport image, thus avoiding the need to identify them and reducing the time required to identify moving metal objects displayed in the mineral transport image. Secondly, the compressed binary image is subjected to a dilation operation to generate a dilated compressed binary image as an expanded binary image. This restores any mineral and moving metal objects that were not removed and shrunk during the opening operation. Then, in response to the detection of at least one connected region in the expanded binary image, for each connected region, the following determination steps are performed: First, the contour of the connected region is determined. This accurately determines the contours of larger mineral and moving metal objects in the mineral transport image. Second, based on the contour of the connected region, the set of contour coordinates of the connected region is determined; based on the set of contour coordinates, the set of coordinates of the circumscribed rectangle corresponding to the connected region is determined. Therefore, the image information of the moving object corresponding to the connected region can be determined by using the coordinate set of the circumscribed rectangle. Finally, based on the aforementioned coordinate set of the circumscribed rectangle, the image information of the moving object corresponding to the aforementioned connected region is determined. This allows for the identification of the information of the moving object corresponding to the connected region. It avoids the need to identify small mineral particles and small metal moving objects, reducing the time required to identify metal moving objects displayed in mineral transport images.

[0068] Step 106: Based on the image information of at least one moving object, crop the mineral transport image to generate at least one moving object image.

[0069] In some embodiments, the execution entity may crop the mineral transport image based on the image information of at least one moving object to generate at least one moving object image.

[0070] In practice, the above mineral transport images can be cropped using the following steps to generate at least one image of a moving object:

[0071] The first step involves, for each of the at least one moving object image information, in response to the moving object area value included in the moving object image information satisfying a target area condition, determining the connected region corresponding to the moving object image information as a target connected region. The target area condition can be a preset area condition corresponding to the category of the moving object included in the moving object image information. For example, in response to the moving object category being a strip-shaped moving object, the target area condition can be that the moving object area value included in the moving object image information is greater than or equal to a first area value. In response to the moving object category being a rectangular moving object, the target area condition can be that the moving object area value included in the moving object image information is greater than or equal to a second area value. The first area value and the second area value can be preset moving object area values.

[0072] The second step involves cropping the mineral transport image for each of the identified target connected regions to generate a moving object image. In practice, for each of the identified target connected regions, the region corresponding to the smallest circumscribed rectangle of that target connected region in the mineral transport image can be cropped to generate the moving object image.

[0073] Step 107: For each moving object image in at least one moving object image, input the moving object image into a pre-trained moving object recognition model to obtain the moving object recognition result.

[0074] In some embodiments, the execution entity may input each of the at least one moving object image into a pre-trained moving object recognition model to obtain a moving object recognition result. The moving object recognition model may be a pre-trained neural network model that takes moving object images as input and outputs moving object recognition results. For example, the neural network model may be a convolutional neural network model.

[0075] In some optional implementations of certain embodiments, the moving object recognition model described above can be a pre-trained GAN (Generative Adversarial Network). In practice, an initial GAN ​​model can be trained to obtain the moving object recognition model. This initial GAN ​​network can include a generator G and a discriminator D. The pre-trained moving object recognition model can be a fully trained GAN model with the generator G removed.

[0076] Optionally, in response to any of the obtained moving object recognition results satisfying the preset recognition conditions, the above-mentioned mineral transportation image is sent to the target terminal for display.

[0077] In some embodiments, the executing entity may send the mineral transport image to a target terminal for display in response to any of the obtained moving object recognition results satisfying a preset recognition condition. The target terminal may be a terminal belonging to an employee connected to the executing entity via a wired or wireless connection. The preset recognition condition may be that the moving object recognition result indicates the corresponding moving object is a metallic moving object.

[0078] The various embodiments of this disclosure have the following beneficial effects: the moving object detection method based on ore transportation according to some embodiments of this disclosure avoids the waste of crushing equipment resources and transportation equipment resources. Specifically, the waste of crushing equipment resources and transportation equipment resources is caused by the fact that the brightness of different areas during ore crushing and transportation is different and the brightness is low, which makes the trained neural network model unable to accurately identify moving metal objects, resulting in the moving metal objects passing through the crushing and transportation equipment, thus wasting crushing equipment resources and transportation equipment resources. Based on this, the moving object detection method based on ore transportation according to some embodiments of this disclosure first performs grayscale transformation processing on the ore transportation image to generate a grayscale transportation image. This can enhance the contrast of the ore transportation image, making it easier to distinguish the ore image from the background. Second, the grayscale transportation image is input into a preset filter to obtain a filtered transportation image. This can smooth and denoise the grayscale transportation image while preserving the edge details of the grayscale transportation image. Then, based on the filtered transportation image, the ore transportation image is sharpened to generate a sharpened transportation image; the sharpened transportation image is binarized to generate a binarized transportation image. Therefore, the mineral transport image can be converted into a binary image, facilitating the determination of the position of moving metal objects within the mineral transport image. Then, based on the binarized transport image, at least one moving object image is determined; based on this at least one moving object image, the mineral transport image is cropped to generate at least one moving object image. This allows for the cropping of moving object images from the mineral transport image. Finally, for each of the at least one moving object image, it is input into a pre-trained moving object recognition model to obtain the moving object recognition result. Thus, moving metal objects in the mineral transport image can be identified before they pass through crushing or transport equipment, preventing damage to the equipment and thus avoiding waste of crushing and transport equipment resources.

[0079] Further reference Figure 3 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a moving object detection device based on ore transportation. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, this moving object detection device based on ore transportation can be specifically applied to various electronic devices.

[0080] like Figure 3As shown, a moving object detection device 300 based on ore transportation in some embodiments includes: a grayscale transformation processing unit 301, a first input unit 302, a sharpening processing unit 303, a binarization processing unit 304, a determination unit 305, a cropping processing unit 306, and a second input unit 307. The system includes a grayscale transformation processing unit 301 configured to perform grayscale transformation processing on the mineral transport image to generate a grayscale transport image; a first input unit 302 configured to input the grayscale transport image into a preset filter to obtain a filtered transport image; a sharpening processing unit 303 configured to sharpen the mineral transport image based on the filtered transport image to generate a sharpened transport image; a binarization processing unit 304 configured to binarize the sharpened transport image to generate a binarized transport image; a determination unit 305 configured to determine at least one moving object image information based on the binarized transport image; a cropping processing unit 306 configured to crop the mineral transport image based on the at least one moving object image information to generate at least one moving object image; and a second input unit 307 configured to input each of the at least one moving object images into a pre-trained moving object recognition model to obtain a moving object recognition result.

[0081] It is understandable that the various units described in the ore transport moving object detection device 300 are related to the reference. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the moving object detection device 300 based on ore transportation and the units contained therein, and will not be repeated here.

[0082] The following is for reference. Figure 4 This document illustrates a structural schematic of an electronic device 400 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0083] like Figure 3As shown, electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. RAM 403 also stores various programs and data required for the operation of electronic device 400. Processing device 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0084] Typically, the following devices can be connected to I / O interface 405: input devices 405 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0085] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from storage device 408, or installed from ROM 402. When the computer program is executed by processing device 401, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0086] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0087] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0088] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: perform grayscale transformation processing on the mineral transport image to generate a grayscale transport image; input the grayscale transport image into a preset filter to obtain a filtered transport image; based on the filtered transport image, sharpen the mineral transport image to generate a sharpened transport image; binarize the sharpened transport image to generate a binarized transport image; determine at least one moving object image based on the binarized transport image; crop the mineral transport image based on the at least one moving object image to generate at least one moving object image; and for each of the at least one moving object images, input the moving object image into a pre-trained moving object recognition model to obtain a moving object recognition result.

[0089] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0091] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a mask processing unit, a grayscale transformation processing unit, a first input unit, a sharpening processing unit, a binarization processing unit, a determination unit, a cropping processing unit, and a second input unit. The names of these units do not necessarily limit the specific unit; for example, the grayscale transformation processing unit may also be described as "a unit that performs grayscale transformation processing on a mineral transport image to generate a grayscale transport image."

[0092] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0093] Some embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements any of the above-described methods for detecting moving objects based on ore transportation.

[0094] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for detecting moving objects based on ore transportation, comprising: The mineral transport image is subjected to grayscale transformation to generate a grayscale transport image; The grayscale transport image is input into a preset filter to obtain a filtered transport image; Based on the filtered transport image, the mineral transport image is sharpened to generate a sharpened transport image, including: The filtered transport image is designated as the first sharpening channel; Extract the color space luminance component from the mineral transport image; The luminance component of the color space is determined as a lightness channel and superimposed on the first sharpening channel. Based on a set sharpening factor, the sharpened pixel value is calculated using the following formula: ， in, Indicates the sharpening pixel value. This represents the pixel value of the target filtered transport pixel, which is a pixel in the filtered transport image that has the same pixel position as a pixel in the mineral transport image. Represents the luminance component of the color space. The pixel value representing the image of mineral transport. This represents the first sharpening factor. This indicates the second sharpening factor; The pixel values ​​of the mineral transport image pixels are updated based on the sharpened pixel values. In response to the detection that all the pixels of each mineral transport image included in the mineral transport image have been updated, the mineral transport image is determined as a sharpened transport image; The sharpened transport image is binarized to generate a binarized transport image; Based on the binarized transport image, determine at least one moving object image information, including: The binarized transport image is subjected to an opening operation to generate an open-binary transport image as a compressed binary image. The compressed binary image is subjected to a dilation operation to generate a dilated compressed binary image as an expanded binary image. In response to the detection that at least one connected component exists in the expanded binary image, for each connected component in the at least one connected component, the following determination steps are performed: Determine the connected region outline of the connected region; Based on the contour of the connected region, determine the set of contour coordinates of the connected region contour; Based on the set of contour coordinates, determine the minimum bounding rectangle of the connected region, and determine the coordinates of each vertex of the minimum bounding rectangle as the set of coordinates of the circumscribed rectangle; Based on the set of coordinates of the circumscribed rectangle, the image information of the moving object corresponding to the connected region is determined. The image information of the moving object includes the area value of the moving object and the category of the moving object. The area value of the moving object is the area of ​​the moving object in the binary transport image. The category of the moving object is a pre-defined shape category of the moving object, including rectangular moving objects and strip-shaped moving objects. Based on the coordinate set of the circumscribed rectangles, determine the difference in the horizontal and vertical coordinates of the minimum circumscribed rectangle; The area of ​​the moving object is determined by multiplying the difference in the horizontal coordinate distance of the smallest bounding rectangle by the difference in the vertical coordinate distance. In response to the ratio of the difference in horizontal coordinate distance to the difference in vertical coordinate distance being within a preset ratio range, the category of moving objects in the connected region is determined to be a rectangular moving object. In response to the fact that the ratio of the difference in the horizontal coordinate distance to the difference in the vertical coordinate distance is not within the preset ratio range, the category of the moving object in the connected region is determined to be a strip-shaped moving object; Based on the image information of the at least one moving object, the mineral transport image is cropped to generate at least one moving object image; For each of the at least one moving object images, the moving object image is input into a pre-trained moving object recognition model to obtain the moving object recognition result.

2. The method according to claim 1, wherein, The method further includes: In response to any of the obtained moving object recognition results satisfying the preset recognition conditions, the mineral transportation image is sent to the target terminal for display.

3. The method according to claim 1, wherein, The grayscale transformation processing of the mineral transport image to generate a grayscale transport image includes: Obtain a preset mineral transport mask image; Based on the preset mineral transport mask image, the mineral transport image is masked to generate a masked transport image; The masked transport image is divided to generate at least one divided transport image as a set of divided transport images; For each segmented transportation image in the segmented transportation image set, the following processing steps are performed: Determine the average pixel value of each segmented transportation pixel in the segmented transportation image; For each segmented transportation pixel in the segmented transportation image, in response to the pixel value of the segmented transportation pixel being greater than or equal to the pixel mean, the pixel value of the segmented transportation pixel is modified to a first preset pixel value; For each segmented transportation pixel in the segmented transportation image, in response to the pixel value of the segmented transportation pixel being less than the pixel mean, the pixel value of the segmented transportation pixel is modified to a second preset pixel value; The modified segmented transportation images are combined to generate a grayscale transportation image.

4. The method according to claim 1, wherein, The step of cropping the mineral transport image based on the image information of the at least one moving object to generate at least one moving object image includes: For each of the at least one moving object image information, in response to the moving object area value included in the moving object image information satisfying the target area condition, the connected region corresponding to the moving object image information is determined as the target connected region, wherein the target area condition is a preset area condition corresponding to the moving object category included in the moving object image information. For each of the identified target connected regions, the mineral transport image is cropped based on the target connected region to generate a moving object image.

5. A moving object detection device based on ore transportation, comprising: The grayscale transformation processing unit is configured to perform grayscale transformation processing on the mineral transport image to generate a grayscale transport image; The first input unit is configured to input the grayscale transport image into a preset filter to obtain a filtered transport image; A sharpening processing unit is configured to sharpen the mineral transport image based on the filtered transport image to generate a sharpened transport image, including: determining the filtered transport image as a first sharpening channel; extracting the color space luminance component from the mineral transport image; determining the color space luminance component as a lightness channel and superimposing it on the first sharpening channel; and calculating the sharpened pixel value according to a set sharpening degree factor using the following formula: ， in, Indicates the sharpening pixel value. This represents the pixel value of the target filtered transport pixel, which is a pixel in the filtered transport image that has the same pixel position as a pixel in the mineral transport image. Represents the luminance component of the color space. The pixel value representing the image of mineral transport. This represents the first sharpening factor. The second sharpening factor is represented; the pixel values ​​of the mineral transport image pixels are updated according to the sharpened pixel values; in response to detecting that all mineral transport image pixels included in the mineral transport image have been updated, the mineral transport image is determined as a sharpened transport image; A binarization processing unit is configured to binarize the sharpened transport image to generate a binarized transport image. The determining unit is configured to determine at least one moving object image information based on the binarized transport image, including: The binarized transport image is subjected to an opening operation to generate an open-binary transport image as a compressed binary image. The compressed binary image is subjected to a dilation operation to generate a dilated compressed binary image as an expanded binary image. In response to the detection that at least one connected component exists in the expanded binary image, for each connected component in the at least one connected component, the following determination steps are performed: Determine the connected region outline of the connected region; Based on the contour of the connected region, determine the set of contour coordinates of the connected region contour; Based on the set of contour coordinates, determine the minimum bounding rectangle of the connected region, and determine the coordinates of each vertex of the minimum bounding rectangle as the set of coordinates of the circumscribed rectangle; Based on the set of coordinates of the circumscribed rectangle, the image information of the moving object corresponding to the connected region is determined. The image information of the moving object includes the area value of the moving object and the category of the moving object. The area value of the moving object is the area of ​​the moving object in the binary transport image. The category of the moving object is a pre-defined shape category of the moving object, including rectangular moving objects and strip-shaped moving objects. Based on the coordinate set of the circumscribed rectangles, determine the difference in the horizontal and vertical coordinates of the minimum circumscribed rectangle; The area of ​​the moving object is determined by multiplying the difference in the horizontal coordinate distance of the smallest bounding rectangle by the difference in the vertical coordinate distance. In response to the ratio of the difference in horizontal coordinate distance to the difference in vertical coordinate distance being within a preset ratio range, the category of moving objects in the connected region is determined to be a rectangular moving object. In response to the fact that the ratio of the difference in the horizontal coordinate distance to the difference in the vertical coordinate distance is not within the preset ratio range, the category of the moving object in the connected region is determined to be a strip-shaped moving object; The cropping processing unit is configured to crop the mineral transport image based on the image information of the at least one moving object to generate at least one moving object image. The second input unit is configured to input the moving object image into a pre-trained moving object recognition model for each moving object image in the at least one moving object image, and obtain the moving object recognition result.

6. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 4.

7. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 4.

8. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 4.

Images