Stone particle size detection method, device, electronic device and storage medium

Abstract

The present invention discloses a method, device, electronic device and storage medium for detecting the particle size of stones, belonging to the technical field of image processing. The method includes: obtaining multiple training stone images of a training stone at different irradiation angles; determining the contour point coordinates of the training stone; training different stone contour models corresponding to different irradiation angles based on an image segmentation algorithm, the contour point coordinates of the training stone, and the irradiation angles corresponding to each training stone image; obtaining multiple target stone images of a target stone at different irradiation angles, and inputting each target stone image into the corresponding stone contour model to obtain the contour point coordinates of the target stone in each target stone image; and determining the particle size value of the target stone based on the contour point coordinates of the target stone. The technical solution provided by the embodiments of the present invention synthesizes a stone image by using stone images at different irradiation angles, and then determines the particle size value of the stone according to the stone image, thereby improving the accuracy of stone particle size detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and particularly relates to a method, device, electronic device and storage medium for detecting the particle size of stones. Background Art

[0002] With the development of science and technology, in the concrete engineering, the particle size of stones affects the strength, durability and construction performance of concrete. Therefore, the determination of the particle size of stones is a very important issue.

[0003] In the prior art, the method for calculating the particle size of stones is mainly manual. For example, a sieve mesh with an appropriate aperture and a vibrating sieve device are selected, then the stones are weighed and screened step by step, and the weight of the particles obtained from each screening is recorded, and the particle size of the stones is calculated. However, this calculation method has a large error and low calculation accuracy. Summary of the Invention

[0004] Embodiments of the present invention provide a solution to solve the problem that in the related art, the traditional method for calculating the particle size of stones has a large error and low calculation accuracy.

[0005] In a first aspect, the present invention provides a method for detecting the particle size of stones, the method comprising:

[0006] Obtaining a plurality of training stone images of a training stone at different illumination angles of a light source;

[0007] Determining the contour point coordinates of the training stone in the plurality of training stone images;

[0008] Training different stone contour models corresponding to different illumination angles based on an image segmentation algorithm, the contour point coordinates of the training stone in the plurality of training stone images, and the illumination angle corresponding to each training stone image;

[0009] Obtaining a plurality of target stone images of a target stone at different illumination angles of the light source, and inputting each target stone image into the stone contour model corresponding to the illumination angle corresponding to each target stone image to obtain the contour point coordinates of the target stone in each target stone image;

[0010] Determining the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image.

[0011] In a second aspect, the present invention provides a device for detecting the particle size of stones, the device comprising:

[0012] An obtaining unit, configured to obtain a plurality of training stone images of a training stone at different illumination angles of a light source;

[0013] A determining unit, configured to determine the contour point coordinates of the training stone in the plurality of training stone images;

[0014] A training unit, configured to train different stone contour models corresponding to different illumination angles based on an image segmentation algorithm, the contour point coordinates of training stones in the multiple training stone images, and the illumination angles corresponding to the respective training stone images;

[0015] An input unit, configured to obtain multiple target stone images of a target stone at different illumination angles of a light source, and input each target stone image into the stone contour model corresponding to the illumination angle corresponding to each target stone image, so as to obtain the contour point coordinates of the target stone in each target stone image;

[0016] The determining unit is further configured to determine the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image.

[0017] In a third aspect, the present invention provides an electronic device, including:

[0018] A processor; and

[0019] A memory, configured to store executable instructions of the processor;

[0020] Wherein, the processor is configured to execute any method in the first aspect or any possible implementation manner of the first aspect by executing the executable instructions.

[0021] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, any method in the first aspect or any possible implementation manner of the first aspect is implemented.

[0022] The technical solution provided by the present invention is as follows: obtaining multiple scene images of a target scene from different shooting perspectives; obtaining multiple training stone images of training stones under different irradiation angles of a light source; determining the contour point coordinates of the training stones in the multiple training stone images; training different stone contour models corresponding to different irradiation angles based on an image segmentation algorithm, the contour point coordinates of the training stones in the multiple training stone images, and the irradiation angles corresponding to the respective training stone images; obtaining multiple target stone images of a target stone under different irradiation angles of the light source, and inputting each target stone image into the stone contour model corresponding to the irradiation angle corresponding to the target stone image to obtain the contour point coordinates of the target stone in each target stone image; and determining the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image. The technical solutions provided by the embodiments of the present invention obtain multiple training stone images of training stones under different irradiation angles of a light source, and train different stone contour models corresponding to different irradiation angles according to the contour point coordinates of the training stones in the multiple training stone images and the irradiation angles corresponding to the respective training stone images. Furthermore, by using the stone contour models and the multiple target stone images of the obtained target stone, the contour point coordinates of the target stone in each target stone image can be obtained; and the particle size value of the target stone is determined based on the contour point coordinates of the target stone in each target stone image, without calculating the particle size value of the target stone manually, greatly improving the accuracy of calculating the particle size value of the stone and also improving the work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the related art, the following will briefly introduce the drawings required for use in the description of the embodiments or the related art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0024] Figure 1 is a schematic flowchart of a method for detecting the particle size of stones provided by an embodiment of the present invention;

[0025] Figure 2 is a schematic structural diagram of a device for detecting the particle size of stones provided by an embodiment of the present invention;

[0026] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The following will describe in detail the embodiments of the present invention, and the examples of the embodiments are shown in the drawings. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention, and should not be construed as limiting the present invention.

[0028] In the description, claims, and drawings of the embodiments of the present invention, terms such as "first" and "second" are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0029] The stone particle size detection method provided by the embodiments of the present invention can run on a terminal device or a server. Among them, the terminal device can be a local terminal device. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the terminal device can be a wearable device, and can also include desktops, mobile phones, tablets, etc., which are not limited here.

[0030] With the development of science and technology, in concrete engineering, the particle size of stones affects the strength, durability, and construction performance of concrete. Therefore, the determination of the particle size of stones is a very important issue.

[0031] In the prior art, the method for calculating the particle size of stones is mainly manual. For example, a sieve mesh with an appropriate aperture and a vibrating sieve device are selected, then the stones are weighed, and gradually screened. The particles obtained from each screening are weighed and recorded, and the particle size of the stones is calculated. However, this calculation method has a large error and low calculation accuracy.

[0032] The following uses specific embodiments to elaborate in detail on the technical solutions of the present invention and how the technical solutions of the present invention solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following will describe the embodiments of the present invention in conjunction with the drawings.

[0033] Figure 1 FIG. is a schematic flowchart of a stone particle size detection method provided for an exemplary embodiment of the present invention. This method can be applied to an electronic device with data processing capabilities. Taking the application of this method to a photographing device as an example, this solution at least includes the following steps S101 - S105:

[0034] S101. Obtain multiple training stone images of the training stone at different illumination angles of the light source.

[0035] In some embodiments, the multiple training stone images are captured by a photographing device at the same photographing perspective.

[0036] Specifically, during the actual photographing process, a light source is arranged above the training stone. After turning on the light source, the photographing device is used to take a picture to obtain a training stone image. After setting the light source at another position and then turning on the light source again, the photographing device takes a picture at the same position to obtain another training stone image.

[0037] In some embodiments, the method is applicable to a photographing device, and a plurality of light source devices are arranged on the photographing device, and each light source device is arranged at a different position; wherein, the light source devices correspond to the illumination angles one by one.

[0038] In this embodiment, the illumination angle is preset.

[0039] Specifically, in order to improve the photographing efficiency, a plurality of light sources can be arranged above the training stone, and each light source is located at a different position. When the first light source is turned on alone, the photographing device takes a picture at a preset position to obtain the first training stone image. Until the Nth light source is turned on alone, the photographing device takes a picture at the preset position to obtain the Nth training stone image, and a total of N training stone images are obtained, where N is a positive integer.

[0040] In some embodiments, the method further includes: preprocessing the multiple training stone images to improve the quality of the multiple training stone images.

[0041] Wherein, the preprocessing at least includes: denoising processing and edge sharpening.

[0042] S102. Determine the contour point coordinates of the training stone in the multiple training stone images.

[0043] In some embodiments, the contour point coordinates are pixel coordinates.

[0044] S103. Based on an image segmentation algorithm, the contour point coordinates of the training stone in the multiple training stone images, and the illumination angles corresponding to the respective training stone images, train different stone contour models corresponding to different illumination angles.

[0045] Specifically, based on the deep learning-based image segmentation algorithm Mask R-CNN, the contour point coordinates of the training stones in the multiple training stone images and the illumination angles corresponding to each training stone image are trained. For example, if there are a total of N light sources and N training stone images are taken, the deep learning-based image segmentation algorithm Mask R-CNN can train N stone contour models, with each light source corresponding to one stone contour model. Here, N is a positive integer.

[0046] Among them, Mask R-CNN is a deep learning-based model mainly used for object detection and segmentation tasks, which can accurately segment the contour of the object.

[0047] In some embodiments, to improve the accuracy of the stone training model, the method may further include steps S11 - S13:

[0048] S11: At any illumination angle of the light source, obtain multiple training stone images of the training stone.

[0049] Among them, the number of training stone images at different illumination angles is the same. Specifically, at any illumination angle of the light source, collect the training stone images of different training stones, and improve the accuracy of the training stone contour model by increasing the number of training stone images.

[0050] S12: Determine the contour point coordinates of the training stone in all training stone images.

[0051] S13: For the multiple training stone images corresponding to any illumination angle, based on the image segmentation algorithm, the contour point coordinates of the training stone in the multiple training stone images, and the illumination angle, train to obtain a stone contour model, and then obtain multiple stone contour models corresponding to multiple illumination angles.

[0052] Specifically, if there are a total of N light sources, at the fixed position of each light source, collect 100 training stone images of different training stones, for a total of 100 * N training stone images. Then, based on the deep learning-based image segmentation algorithm Mask R-CNN, train the 100 training stone images corresponding to each light source to obtain a stone contour model, and a total of N stone contour models can be trained, with each light source corresponding to one stone contour model.

[0053] In some embodiments, to improve the accuracy and applicability of the stone contour model, during actual use, the collected target stone is used as the training stone to optimize the stone contour model.

[0054] S104. Obtain multiple target stone images of the target stone at different irradiation angles of the light source, and input each target stone image into the stone contour model corresponding to the irradiation angle corresponding to the target stone image, to obtain the contour point coordinates of the target stone in each target stone image.

[0055] In some embodiments, according to the different stone contour models corresponding to different irradiation angles obtained in the above step S103, input the obtained multiple target stone images into the stone contour models corresponding to the irradiation angles corresponding to each target stone image, to obtain the contour point coordinates of the target stone in each target stone image. For example, if there are a total of M irradiation angles, M stone contour models are trained, namely stone contour model 1, stone contour model 2... stone contour model M, M is a positive integer, and the M obtained target stone images, namely target stone image 1, target stone image 2... target stone image M, input target stone image 1 into stone contour model 1, input target stone image 2 into stone contour model 3... input target stone image M into stone contour model M, to obtain the contour point coordinates of the target stone in each target stone image output by each stone contour model.

[0056] S105. Determine the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image.

[0057] In some embodiments, determining the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image includes: performing non-maximum suppression based on each target stone image and the contour point coordinates of the target stone in each target stone image, to obtain a target image, and determining the target contour point coordinates of the target stone in the target image, and determining the particle size value of the target stone based on the target contour point coordinates of the target stone in the target image.

[0058] Among them, non-maximum suppression (Non-Maximum Suppression, NMS) refers to suppressing elements that are not maxima, which can be understood as local maximum search.

[0059] In some embodiments, the method further includes: determining the confidence of the contour point coordinates of the target stone in each target stone image.

[0060] Among them, the confidence refers to the ratio of the number of intervals containing the population parameter to the total number among multiple sample intervals for constructing the population parameter, generally represented by 1-α.

[0061] In this embodiment, the performing non-maximum suppression based on each target stone image and the contour point coordinates of the target stone in each target stone image, to obtain a target image, and determining the target contour point coordinates of the target stone in the target image includes:

[0062] Based on the target stone images, the confidence levels of the contour point coordinates of the target stones in each target stone image, and the contour point coordinates of the target stones in each target stone image, perform non-maximum suppression to obtain a target image, and determine the target contour point coordinates of the target stone in the target image.

[0063] Specifically, there are three target stone images, namely target stone image 1, target stone image 2, and target stone image 3;

[0064] The contour point coordinates of the target stone in target stone image 1 include: contour point coordinate 1 (confidence level is 3), contour point coordinate 2 (confidence level is 4), contour point coordinate 3 (confidence level is 5), and contour point coordinate 4 (confidence level is 4);

[0065] The contour point coordinates of the target stone in target stone image 2 include: contour point coordinate 1 (confidence level is 2), contour point coordinate 2 (confidence level is 5), contour point coordinate 3 (confidence level is 4), and contour point coordinate 4 (confidence level is 3);

[0066] The contour point coordinates of the target stone in target stone image 3 include: contour point coordinate 2 (confidence level is 4), contour point coordinate 3 (confidence level is 5), contour point coordinate 4 (confidence level is 4), and contour point coordinate 5 (confidence level is 5);

[0067] Combined with the above example, based on the target stone images, the confidence levels of the contour point coordinates of the target stones in each target stone image, and the contour point coordinates of the target stones in each target stone image, perform non-maximum suppression to obtain a target image, and determine the target contour point coordinates of the target stone in the target image. The specific process is as follows:

[0068] Save the one with the maximum confidence level among the same contour point coordinates, and remove the other contour points:

[0069] Contour point coordinate 1 (confidence level is 3) and contour point coordinate 1 (confidence level is 2), keep contour point coordinate 1 (confidence level is 3);

[0070] Contour point coordinate 2 (confidence level is 4), contour point coordinate 2 (confidence level is 5), and contour point coordinate 2 (confidence level is 4), keep contour point coordinate 2 (confidence level is 5);

[0071] Contour point coordinate 3 (confidence level is 5), contour point coordinate 3 (confidence level is 4), and contour point coordinate 3 (confidence level is 5), keep contour point coordinate 3 (confidence level is 5);

[0072] Contour point coordinate 4 (confidence level is 4), contour point coordinate 4 (confidence level is 3), and contour point coordinate 4 (confidence level is 4), keep contour point coordinate 4 (confidence level is 4);

[0073] Contour point coordinates 5 (confidence level is 5), retain contour point coordinates 5 (confidence level is 5);

[0074] According to the above, fuse the target stone images 1, 2, and 3 into a single target stone image, where the contour point coordinates of the target stone in this target stone image are respectively contour point coordinates 1 (confidence level is 3), contour point coordinates 2 (confidence level is 5), contour point coordinates 3 (confidence level is 5), contour point coordinates 4 (confidence level is 4), and contour point coordinates 5 (confidence level is 5).

[0075] In some embodiments, based on the target contour point coordinates of the target stone in the target image, determining the particle size value of the target stone includes: converting the target contour point coordinates of the target stone in the target image into world coordinates through a calibration method; based on the world coordinates and the target image, determining the particle size value of the target stone.

[0076] In this embodiment, after converting the target contour point coordinates of the target stone in the target image into world coordinates through the calibration method, the size of the target stone in the target image is the actual size of the target stone.

[0077] The technical solution provided by the present invention is to obtain multiple scene images of the target scene from different shooting perspectives; obtain multiple training stone images of the training stone under different illumination angles of the light source; determine the contour point coordinates of the training stone in the multiple training stone images; based on the image segmentation algorithm, the contour point coordinates of the training stone in the multiple training stone images, and the illumination angle corresponding to each training stone image, train different stone contour models corresponding to different illumination angles; obtain multiple target stone images of the target stone under different illumination angles of the light source, and input each target stone image into the stone contour model corresponding to the illumination angle corresponding to each target stone image to obtain the contour point coordinates of the target stone in each target stone image; based on the contour point coordinates of the target stone in each target stone image, determine the particle size value of the target stone. The technical solutions provided by the embodiments of the present invention obtain multiple training stone images of the training stone under different illumination angles of the light source, and train different stone contour models corresponding to different illumination angles according to the contour point coordinates of the training stone in the multiple training stone images and the illumination angle corresponding to each training stone image. Furthermore, by using the stone contour model and the multiple target stone images of the target stone obtained, the contour point coordinates of the target stone in each target stone image can be obtained; based on the contour point coordinates of the target stone in each target stone image, the particle size value of the target stone is determined, without the need to calculate the particle size value of the target stone manually, greatly improving the accuracy of calculating the particle size value of the stone and also improving the work efficiency.

[0078] Figure 2Schematic structural diagram of a stone particle size detection device provided by an exemplary embodiment of the present invention;

[0079] Among them, the device includes: an acquisition unit 201, a determination unit 202, a training unit 203, and an input unit 204;

[0080] The acquisition unit 201 is configured to acquire multiple training stone images of the training stone at different irradiation angles of the light source;

[0081] The determination unit 202 is configured to determine the contour point coordinates of the training stone in the multiple training stone images;

[0082] The training unit 203 is configured to train different stone contour models corresponding to different irradiation angles based on an image segmentation algorithm, the contour point coordinates of the training stone in the multiple training stone images, and the irradiation angle corresponding to each training stone image;

[0083] The input unit 204 is configured to acquire multiple target stone images of the target stone at different irradiation angles of the light source, and input each target stone image into the stone contour model corresponding to the irradiation angle corresponding to each target stone image to obtain the contour point coordinates of the target stone in each target stone image;

[0084] The determination unit 202 is further configured to determine the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image.

[0085] In some embodiments, the device is configured to determine the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image. Specifically, the device is configured to:

[0086] Based on each target stone image and the contour point coordinates of the target stone in each target stone image, and performing non-maximum suppression, obtain a target image, and determine the target contour point coordinates of the target stone in the target image;

[0087] Based on the target contour point coordinates of the target stone in the target image, determine the particle size value of the target stone.

[0088] In some embodiments, the device is configured to determine the particle size value of the target stone based on the target contour point coordinates of the target stone in the target image. Specifically, the device is configured to:

[0089] Convert the target contour point coordinates of the target stone in the target image into world coordinates through a calibration method;

[0090] Based on the world coordinates and the target image, determine the particle size value of the target stone.

[0091] In some embodiments, the device is further configured to: determine the confidence of the contour point coordinates of the target stones in each target stone image;

[0092] The device is further configured to perform non-maximum suppression based on each target stone image and the contour point coordinates of the target stones in each target stone image to obtain a target image, and determine the target contour point coordinates of the target stones in the target image. Specifically, the device is configured to:

[0093] Perform non-maximum suppression based on each target stone image, the confidence of the contour point coordinates of the target stones in each target stone image, and the contour point coordinates of the target stones in each target stone image to obtain a target image, and determine the target contour point coordinates of the target stones in the target image.

[0094] In some embodiments, the device is further configured to: preprocess the multiple training stone images to improve the quality of the multiple training stone images;

[0095] Wherein, the preprocessing at least includes: denoising processing and edge sharpening.

[0096] In some embodiments, the contour point coordinates are pixel coordinates.

[0097] In some embodiments, the device is applicable to a photographing device, and a plurality of light source devices are arranged on the photographing device, and the positions of each light source device are different;

[0098] Wherein, the light source devices correspond to the irradiation angles one by one.

[0099] The technical solution provided by the present invention is as follows: obtaining multiple scene images of a target scene from different shooting perspectives; obtaining multiple training stone images of a training stone under different illumination angles of a light source; determining the contour point coordinates of the training stone in the multiple training stone images; training different stone contour models corresponding to different illumination angles based on an image segmentation algorithm, the contour point coordinates of the training stone in the multiple training stone images, and the illumination angle corresponding to each training stone image; obtaining multiple target stone images of a target stone under different illumination angles of the light source, and inputting each target stone image into the stone contour model corresponding to the illumination angle of the target stone image to obtain the contour point coordinates of the target stone in each target stone image; and determining the particle size value of the target stone based on the contour point coordinates of the target stone in each target stone image. The technical solutions provided by the embodiments of the present invention obtain multiple training stone images of a training stone under different illumination angles of a light source, and train different stone contour models corresponding to different illumination angles according to the contour point coordinates of the training stone in the multiple training stone images and the illumination angle corresponding to each training stone image. Furthermore, by using the stone contour model and the multiple target stone images of the obtained target stone, the contour point coordinates of the target stone in each target stone image can be obtained; and the particle size value of the target stone is determined based on the contour point coordinates of the target stone in each target stone image, without calculating the particle size value of the target stone manually, greatly improving the accuracy of calculating the particle size value of the stone and improving the work efficiency.

[0100] It should be understood that the device embodiments and the method embodiments can correspond to each other, and similar descriptions can refer to the method embodiments. To avoid repetition, it will not be elaborated here. Specifically, the device can execute the above method embodiments, and the foregoing and other operations and / or functions of each module in the device respectively correspond to the corresponding processes in each method in the above method embodiments. For the sake of brevity, it will not be elaborated here.

[0101] In the foregoing, the device of the embodiments of the present invention has been described from the perspective of functional modules. It should be understood that the functional modules can be implemented in the form of hardware, or in the form of instructions in software, or in a combination of hardware and software modules. Specifically, the steps of the method embodiments in the present invention can be completed by the integrated logic circuit in the hardware in the processor and / or the instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps in the above method embodiments.

[0102] Figure 3 It is a schematic block diagram of an electronic device provided by an embodiment of the present invention. The electronic device may include:

[0103] A memory 301 and a processor 302. The memory 301 is used to store a computer program and transmit the program code to the processor 302. In other words, the processor 302 can call and run the computer program from the memory 301 to implement the method in the embodiment of the present invention.

[0104] For example, the processor 302 can be used to execute the above method embodiment according to the instructions in the computer program.

[0105] In some embodiments of the present invention, the processor 302 may include but is not limited to:

[0106] A general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on.

[0107] In some embodiments of the present invention, the memory 301 includes but is not limited to:

[0108] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be Read-Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically EPROM (EEPROM) or flash memory. The volatile memory can be Random Access Memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double DataRate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), synch link DRAM (SLDRAM) and Direct Rambus RAM (DR RAM).

[0109] In some embodiments of the present invention, the computer program can be divided into one or more modules, and the one or more modules are stored in the memory 301 and executed by the processor 302 to complete the method provided by the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0110] As Figure 3 shown, the electronic device may further include:

[0111] A transceiver 303, and the transceiver 303 can be connected to the processor 302 or the memory 301.

[0112] Among them, the processor 302 can control the transceiver 303 to communicate with other devices. Specifically, it can send information or data to other devices, or receive information or data sent by other devices. The transceiver 303 can include a transmitter and a receiver. The transceiver 303 may further include an antenna, and the number of antennas can be one or more.

[0113] It should be understood that the various components in the electronic device are connected through a bus system. Among them, the bus system includes, in addition to the data bus, a power bus, a control bus, and a status signal bus.

[0114] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a computer, the computer can execute the methods in the above method embodiments. Or rather, the embodiments of the present invention also provide a computer program product containing instructions. When the instructions are executed by a computer, the computer executes the methods in the above method embodiments.

[0115] When implemented using software, it can be fully or partially implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a digital video disc (DVD)), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0116] Those of ordinary skill in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0117] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0118] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. For example, in each embodiment of the present invention, the various functional modules can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0119] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for detecting stone particle size, characterized in that: Methods include: Acquire multiple training stone images of the training stone under different illumination angles of the light source; Determining the coordinates of the contour points of the training stones in the plurality of training stone images; Based on the image segmentation algorithm, the coordinates of the contour points of the training stones in the plurality of training stone images and the illumination angles corresponding to the training stone images, different stone contour models corresponding to different illumination angles are obtained through training; Under different illumination angles of the light source, multiple target stone images of the target stone are obtained, and each target stone image is input into a stone contour model corresponding to the illumination angle corresponding to each target stone image, so as to obtain the contour point coordinates of the target stone in each target stone image; Determine the particle size value of the target stone based on the coordinates of the contour points of the target stone in each target stone image; Based on the coordinates of the contour points of the target stones in each target stone image, the particle size value of the target stone is determined, including: Based on each target stone image and the coordinates of the contour points of the target stone in each target stone image and performing non-maximum suppression, a target image is obtained, and the coordinates of the target contour points of the target stone in the target image are determined; Determining a particle size value of the target stone based on target contour point coordinates of the target stone in the target image; The method further comprises: determining the confidence of the coordinates of the contour points of the target stone in each target stone image; The method of obtaining a target image based on each target stone image and the coordinates of the contour points of the target stone in each target stone image and performing non-maximum suppression, and determining the coordinates of the target contour points of the target stone in the target image, comprises: Based on each target stone image, the confidence of the contour point coordinates of the target stone in each target stone image and the contour point coordinates of the target stone in each target stone image, non-maximum suppression is performed to obtain a target image, and the target contour point coordinates of the target stone in the target image are determined; Wherein, the method is applicable to a photographing device, wherein a plurality of light source devices are arranged on the photographing device, and each light source device is arranged at a different position; Wherein, the light source equipment corresponds to the illumination angle one by one; The step of obtaining a plurality of target stone images of the target stone under different illumination angles of the light source includes: A plurality of light source devices are turned on separately and in sequence, and the target stone is photographed at a preset position by the photographing device to obtain a plurality of target stone images of the target stone at different irradiation angles of the light source.

2. The method according to claim 1, characterized in that Determining the particle size value of the target stone based on the target contour point coordinates of the target stone in the target image includes: The target contour point coordinates of the target stone in the target image are converted into world coordinates by a calibration method; Based on the world coordinates and the target image, a particle size value of the target stone is determined.

3. The method according to claim 1, characterized in that: The method further comprises: preprocessing the plurality of training stone images to improve the quality of the plurality of training stone images; Wherein, the preprocessing at least includes: denoising and edge sharpening.

4. The method according to claim 1, characterized in that The contour point coordinates are pixel coordinates.

5. A stone particle size detection device, characterized in that: The device comprises: An acquisition unit, used for acquiring a plurality of training stone images of the training stone under different illumination angles of the light source; A determination unit, used to determine the coordinates of the contour points of the training stones in the plurality of training stone images; A training unit, configured to train and obtain different stone contour models corresponding to different illumination angles based on an image segmentation algorithm, the coordinates of contour points of the training stones in the plurality of training stone images, and the illumination angles corresponding to the training stone images; An input unit is used to obtain multiple target stone images of the target stone under different illumination angles of the light source, and input each target stone image into a stone contour model corresponding to the illumination angle corresponding to each target stone image, so as to obtain the contour point coordinates of the target stone in each target stone image; The determination unit is further used to determine the particle size value of the target stone based on the coordinates of the contour points of the target stone in each target stone image; The device is used to determine the particle size value of the target stone based on the coordinates of the contour points of the target stone in each target stone image, and the device is specifically used to: Based on each target stone image and the coordinates of the contour points of the target stone in each target stone image and performing non-maximum suppression, a target image is obtained, and the coordinates of the target contour points of the target stone in the target image are determined; Determining a particle size value of the target stone based on target contour point coordinates of the target stone in the target image; The device is also used to: determine the confidence level of the coordinates of the contour points of the target stone in each target stone image; The device is used to obtain a target image based on each target stone image and the coordinates of the contour points of the target stone in each target stone image and perform non-maximum suppression, and determine the target contour point coordinates of the target stone in the target image. The device is specifically used for: Based on each target stone image, the confidence of the contour point coordinates of the target stone in each target stone image and the contour point coordinates of the target stone in each target stone image, non-maximum suppression is performed to obtain a target image, and the target contour point coordinates of the target stone in the target image are determined; Wherein, the device is applicable to a photographing device, and a plurality of light source devices are arranged on the photographing device, and each light source device is arranged at a different position; Wherein, the light source equipment corresponds to the illumination angle one by one; The device is used to obtain multiple target stone images of the target stone under different illumination angles of the light source, and the device is specifically used to: A plurality of light source devices are turned on separately and in sequence, and the target stone is photographed at a preset position by the photographing device to obtain a plurality of target stone images of the target stone at different irradiation angles of the light source.

6. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 4 by executing the executable instructions.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images