Scrap steel rating method and device, electronic equipment and medium

Abstract

A scrap steel rating method is provided. The method comprises the steps that multiple pieces of single-layer scrap steel data are obtained, and each piece of single-layer scrap steel data comprises image data and point cloud data which are obtained by collecting a target area when scrap steel materials of the corresponding layer become surface scrap steel materials of a scrap steel material pile in the discharging process; determining the stacking density of the steel scrap material pile; for each layer of scrap steel material of the scrap steel material pile, performing image segmentation processing on image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an image segmentation result for the layer of scrap steel material; determining the single-layer volume of the layer of scrap steel material according to the point cloud data in the single-layer scrap steel data corresponding to the layer of scrap steel material; determining the single-layer weight of the layer of scrap steel material according to the single-layer volume and the stacking density; and according to the image segmentation result and the single-layer weight, determining the single-layer rating result of the layer of scrap steel material. And according to the multiple single-layer rating results corresponding to the multiple layers of scrap steel materials, the overall rating result of the scrap steel material pile is determined.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a scrap steel grading method, device, electronic device, computer-readable storage medium and computer program product. Background Art

[0002] With the development requirements of the country's green economy, in order to promote the early realization of the goals of carbon peak and carbon neutrality, many steel mills at home and abroad use scrap steel as an important steelmaking raw material to reduce dependence on iron ore. Steel mills need to purchase a large amount of scrap steel every year. These scrap steels are usually of large types, complex material types, and a variety of shapes and sizes. In addition, they are often attached with impurities such as soil residue and oil. Traditional steel mills use manual visual quality inspection to grade the scrap steel they purchase. After the scrap steel is collected, stored, and transported, the rating results are manually entered and uploaded to the ERP or MES system. With the continuous advancement of technology and the continuous development of machine vision, some scrap steel rating methods based on deep learning have also begun to enter the field of scrap steel rating.

[0003] In the prior art, images of each layer of scrap steel material in the scrap steel pile are usually collected during unloading, and the number of steel blocks or area included in each layer of scrap steel is identified by performing image segmentation processing on the collected images to obtain the classification level of the scrap steel layer. Summary of the invention

[0004] The present disclosure provides a scrap steel grading method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] According to one aspect of the present disclosure, a scrap steel rating method is provided, comprising: acquiring a plurality of single-layer scrap steel data, wherein the plurality of single-layer scrap steel data correspond one-to-one to multiple layers of scrap steel materials included in a scrap steel pile, the scrap steel pile being located in a target area, and each single-layer scrap steel data comprising image data and point cloud data acquired by collecting the target area when the scrap steel materials of the corresponding layer become the surface scrap steel materials of the scrap steel pile during the unloading process; determining the stacking density of the scrap steel pile; for each layer of scrap steel materials in the scrap steel pile, performing image classification on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel materials; The invention relates to a method for performing segmentation processing to obtain an image segmentation result for the layer of scrap steel material, wherein the image segmentation result indicates steel information and non-steel information of the layer of scrap steel material; determining a single-layer volume of the layer of scrap steel material according to point cloud data in the single-layer scrap steel data corresponding to the layer of scrap steel material; determining a single-layer weight of the layer of scrap steel material according to the single-layer volume and the stacking density; and determining a single-layer rating result of the layer of scrap steel material according to the image segmentation result and the single-layer weight; and determining an overall rating result of the scrap steel pile according to at least one single-layer rating result among a plurality of single-layer rating results corresponding to the multiple layers of scrap steel material.

[0006] According to another aspect of the present disclosure, a scrap steel grading device is provided, comprising: a first acquisition module, configured to acquire a plurality of single-layer scrap steel data, wherein the plurality of single-layer scrap steel data correspond one-to-one to multiple layers of scrap steel materials included in a scrap steel pile, the scrap steel pile being located in a target area, and each single-layer scrap steel data comprises image data and point cloud data acquired by collecting the target area when the scrap steel materials of the corresponding layer become the surface scrap steel materials of the scrap steel pile during the unloading process; a determination module, configured to determine the stacking density of the scrap steel pile; a processing module, configured to process, for each layer of scrap steel materials in the scrap steel pile, the single-layer scrap steel data corresponding to the layer of scrap steel materials; The image data in the image segmentation processing is performed to obtain an image segmentation result for the layer of scrap steel material, wherein the image segmentation result indicates the steel information and non-steel information of the layer of scrap steel material; the single-layer volume of the layer of scrap steel material is determined according to the point cloud data in the single-layer scrap steel data corresponding to the layer of scrap steel material; the single-layer weight of the layer of scrap steel material is determined according to the single-layer volume and the stacking density; and the single-layer rating result of the layer of scrap steel material is determined according to the image segmentation result and the single-layer weight; and a rating module is configured to determine the overall rating result of the scrap steel pile according to at least one single-layer rating result among the multiple single-layer rating results corresponding to the multiple layers of scrap steel material.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above method.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the above method.

[0009] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0010] According to one or more embodiments of the present disclosure, when unloading a scrap steel pile, the image data and point cloud data of a single layer of scrap steel material in the scrap steel pile are collected layer by layer and data processing is performed, so that the volume information of a single layer of scrap steel material can be further determined based on the point cloud data on the basis of visual detection, so as to determine the weight information of the layer of scrap steel material according to its volume information and the stacking density of the scrap steel pile. Based on this, the weight information obtained based on the point cloud data can be introduced as a supplement when rating the single layer of scrap steel material to improve the accuracy of the rating result.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0013] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0014] Figure 2 An exemplary flow chart of a scrap steel grading method according to an embodiment of the present disclosure is shown;

[0015] Figure 3 A partial exemplary flow chart of a scrap steel grading method according to an embodiment of the present disclosure is shown;

[0016] Figure 4 Another exemplary flow chart of a part of the scrap steel grading method according to an embodiment of the present disclosure is shown;

[0017] Figure 5 A further exemplary flow chart showing a part of the scrap steel grading method according to an embodiment of the present disclosure is shown;

[0018] Figure 6 A further exemplary flow chart showing a part of the scrap steel grading method according to an embodiment of the present disclosure is shown;

[0019] Figure 7 A structural block diagram of a scrap steel grading device according to an embodiment of the present disclosure is shown; and

[0020] Figure 8 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0023] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0024] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 is a schematic diagram illustrating an example system 100 in which the various methods described herein may be implemented, according to an example embodiment.

[0026] refer to Figure 1 The system 100 includes a client device 110 , a server 120 , and a network 130 that communicatively couples the client device 110 and the server 120 .

[0027] The client device 110 includes a display 114 and a client application (APP) 112 that can be displayed via the display 114. The client application 112 can be an application that needs to be downloaded and installed before running or a small program (lite app) as a lightweight application. In the case where the client application 112 is an application that needs to be downloaded and installed before running, the client application 112 can be pre-installed on the client device 110 and activated. In the case where the client application 112 is a small program, the user 102 can directly run the client application 112 on the client device 110 by searching for the client application 112 in the host application (for example, by the name of the client application 112, etc.) or scanning the graphic code of the client application 112 (for example, a bar code, a QR code, etc.), without installing the client application 112. In some embodiments, the client device 110 can be any type of mobile computer device, including a mobile computer, a mobile phone, a wearable computer device (for example, a head-mounted device such as a smart watch, smart glasses, etc.) or other types of mobile devices. In some embodiments, the client device 110 can be a fixed computer device, such as a desktop, a server computer or other types of fixed computer devices.

[0028] The server 120 is typically a server deployed by an Internet Service Provider (ISP) or an Internet Content Provider (ICP). The server 120 may represent a single server, a cluster of multiple servers, a distributed system, or a cloud server that provides basic cloud services (such as cloud databases, cloud computing, cloud storage, and cloud communications). It will be understood that although Figure 1 The server 120 is shown in FIG. 1 in communicating with only one client device 110 , but the server 120 may provide background services for multiple client devices simultaneously.

[0029] Examples of network 130 include a local area network (LAN), a wide area network (WAN), a personal area network (PAN), and / or a combination of communication networks such as the Internet. Network 130 can be a wired or wireless network. In some embodiments, the data exchanged through network 130 is processed using technologies and / or formats including hypertext markup language (HTML), extensible markup language (XML), etc. In addition, encryption technologies such as secure socket layer (SSL), transport layer security (TLS), virtual private network (VPN), Internet protocol security (IPsec) can also be used to encrypt all or some links. In some embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0030] For the purpose of the embodiments of this disclosure, Figure 1 In the example of , the client application 112 may be a scrap steel rating application, which may provide various functions based on scrap steel rating, such as obtaining and displaying the collected scrap steel images and scrap steel rating results. Accordingly, the server 120 may be a server used together with the scrap steel rating application. The server 120 may provide online scrap steel rating services to the client application 112 running in the client device 110. Alternatively, the client application 112 running in the client device 110 may provide local scrap steel rating services.

[0031] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0032] In the related art, images of each layer of scrap steel in the scrap steel pile are usually collected during unloading, and the number of steel blocks or area included in each layer of scrap steel is identified by image segmentation processing to obtain the classification level of the scrap steel layer. However, this rating method based only on visual image detection is often less accurate.

[0033] to this end, Figure 2An exemplary flow chart of a scrap steel rating method 200 according to an embodiment of the present disclosure is shown. Figure 1 The client or server implementation shown in Figure 2 Method 200 in.

[0034] like Figure 2 As shown, according to an embodiment of the present disclosure, a scrap steel grading method 200 is provided, comprising the following steps 210 to 240.

[0035] Step 210, obtaining multiple single-layer scrap steel data. The multiple single-layer scrap steel data correspond one-to-one to multiple layers of scrap steel materials included in the scrap steel pile, the scrap steel pile is located in the target area, and each single-layer scrap steel data includes image data and point cloud data collected for the target area when the scrap steel materials of the corresponding layer become the surface scrap steel materials of the scrap steel pile during the unloading process.

[0036] In some embodiments, the target area may be the unloading area of ​​the scrap steel transport truck parked in the steel plant, or may be the whole or part of the area in the scrap steel transport truck bucket. In the example, after the camera coordinate system and the world coordinate system are calibrated, the transport truck bucket in the camera field of view may be evenly divided into a plurality of rectangular areas, and one or more of the rectangular areas may be used as the target area.

[0037] Steel mills usually use electromagnetic suction cups or mobile steel grabbers to unload scrap steel piles layer by layer, and the thickness of the scrap steel material sucked by the electromagnetic suction cup (or mobile steel grabber) each time may be different. Therefore, in some embodiments, the number of times the electromagnetic suction cup (or mobile steel grabber) sucks scrap steel materials in the target area during unloading can be used as the number of layers of the scrap steel pile in the target area, so that the collected multiple image data and multiple point cloud data can more comprehensively and effectively characterize the characteristic information of the scrap steel pile.

[0038] In some embodiments, one or more cameras and 3D scanning devices facing the scrap steel pile may be arranged above the designated unloading point to collect the above image data and point cloud data. In other embodiments, only cameras may be arranged to collect image data, and then NeRF (Neural Radiance Fields) technology may be used to generate 3D point cloud data based on 2D image data to save costs.

[0039] Step 220, determining the bulk density of the scrap steel pile.

[0040] In some embodiments, for multiple scrap steel piles on the same transport vehicle, after the stacking density of the scrap steel pile in the non-target area is determined, the stacking density can be directly used as the stacking density of the scrap steel pile in the target area.

[0041] In other embodiments, the bulk density can also be directly calculated for the current scrap steel pile. Figure 3 A partial exemplary flow chart of a scrap steel grading method according to an embodiment of the present disclosure is shown.

[0042] like Figure 3 As shown, according to some embodiments, step 220 includes the following steps 310 to 340.

[0043] Step 310, obtaining the entire weight of the scrap steel pile.

[0044] In some embodiments, the gross weight data and tare weight data measured by the steel plant's scale when the transport vehicle enters the plant and when it leaves the plant after unloading can be obtained from the steel plant's scale metering system, so that the net weight of all scrap steel can be obtained based on the difference between the gross weight and the tare weight.

[0045] In one example, the target area includes the entire area within the truck bed, and in this case, the net weight is the entire weight of the scrap steel pile.

[0046] In another example, the truck bed is divided into two identical rectangular areas, and the target area corresponds to one of the rectangular areas. In this case, the overall weight of the scrap pile is 1 / 2 of the net weight of all the scrap steel. It should be understood that in this case, the overall weight of the scrap pile will vary according to the different positions and sizes corresponding to the target areas.

[0047] Step 320: determining the single-layer volume of each layer of scrap steel material in the multi-layer scrap steel material according to the plurality of single-layer scrap steel data.

[0048] Figure 4 Another partial exemplary flow chart of a scrap steel grading method according to an embodiment of the present disclosure is shown.

[0049] like Figure 4 As shown, according to some embodiments, the target area is located in the cargo box of the transport vehicle, and the scrap steel pile includes the first to nth layers of scrap steel materials from bottom to top, where n is an integer greater than or equal to 1. In this case, step 320 may include the following steps 410 to 430.

[0050] Step 410, obtaining the actual height of the transport vehicle from the lowest point of the vehicle bucket to the ground, and the actual length and width of the target area.

[0051] Step 420, for the first layer of scrap steel material in the scrap steel pile. In one example, step 420 includes: step 421, determining the first point cloud height of the highest point of the first layer of scrap steel material from the ground and the first point cloud width of the target area according to the point cloud data in the single layer of scrap steel data corresponding to the first layer of scrap steel material; step 422, determining the size conversion ratio according to the ratio of the actual width of the area and the first point cloud width; step 423, determining the first actual height of the highest point of the first layer of scrap steel material from the ground according to the size conversion ratio and the first point cloud height; step 424, determining the first layer actual height of the first layer of scrap steel material according to the difference between the first actual height and the actual height of the vehicle; and step 425, determining the single layer volume of the first layer of scrap steel material according to the actual length of the area, the actual width of the area and the actual height of the first layer.

[0052] Step 430, for the i-th layer of scrap steel material in the scrap steel pile, wherein i is an integer and the value range of i is (1, n]. In one example, step 430 includes: step 431, determining a second point cloud height of the highest point of the i-th layer of scrap steel material from the ground according to the point cloud data in the single-layer scrap steel data corresponding to the i-th layer of scrap steel material; step 432, determining a third point cloud height of the highest point of the i-1-th layer of scrap steel material from the ground according to the point cloud data in the single-layer scrap steel data corresponding to the i-1-th layer of scrap steel material; step 433, determining the i-th layer point cloud height of the i-th layer of scrap steel material according to the second point cloud height and the third point cloud height; step 434, determining the i-th layer actual height of the i-th layer of scrap steel material according to the size transformation ratio and the i-th layer point cloud height; and step 435, determining the single-layer volume of the i-th layer of scrap steel material according to the actual length of the area, the actual width of the area and the actual height of the i-th layer.

[0053] For step 420 and step 430, the size transformation ratio of the size change of the same object in the corresponding point cloud data and the actual scene where it is located is first determined based on the ratio between the actual width of the target area measured and the point cloud width of the target area determined from the point cloud data, so that the size value of the single-layer scrap steel material in the point cloud data can be directly transformed into the medium size value in the actual scene according to the size transformation ratio. Based on this, the volume-related data of the layer of scrap steel material can be directly determined based on the point cloud data of the single-layer scrap steel material, without the need to measure the actual volume of the single-layer scrap steel every time the scrap steel is sucked, which effectively improves the efficiency of obtaining the volume of the single-layer scrap steel material and reduces the difficulty of implementation.

[0054] In this example, the actual height of the lowest point of the truck bed from the ground is h, the actual width of the vehicle is w, and the actual length of the vehicle is l. According to the length l of the truck bed, the truck bed can be evenly divided into m areas, each with a width of w and a length of The target area is the jth area in the truck bed, and the value range of j is (0, m].

[0055] For the first layer of scrap steel material in the target area, determine the first point cloud height h of its highest point from the ground based on the point cloud data. 1j ' and the first point cloud width of the target area is w1', based on this, the formula of the size transformation ratio q is expressed as:

[0056]

[0057] The first actual height h of the highest point of the first layer of scrap steel from the ground 1j The formula is:

[0058] h 1j =qh 1j '

[0059] The actual height Δh of the first layer of scrap steel material 1j The formula is:

[0060] Δh 1j =h 1j -h

[0061] The single layer volume L of the first layer of scrap steel material 1j The formula is:

[0062]

[0063] For the i-th layer of scrap steel material after the first layer in the target area, the second point cloud height h of its highest point from the ground is determined according to the point cloud data. ij 'The third point cloud height h of the i-1th layer of scrap steel material from the bottom i-1j ', the point cloud height of the i-th layer of scrap steel material Δh ij The formula of ' is:

[0064] Δh ij '=h ij '-h (i-1)j '

[0065] The actual height of the i-th layer of scrap steel material Δh ij The formula is:

[0066] Δh ij =qΔh ij '

[0067] The single layer volume L of the i-th layer of scrap steel material ij The formula is:

[0068]

[0069] Return to reference Figure 3In step 330, the overall volume of the scrap steel pile is determined based on the volumes of the multiple single layers corresponding to the multiple layers of scrap steel material.

[0070] In some embodiments, the calculated volumes of multiple single layers may be added together to obtain the overall volume of the scrap steel pile, which is expressed as:

[0071] L=∑L ij

[0072] Step 340, determining the bulk density based on the overall weight and overall volume.

[0073] In some embodiments, the total weight of the scrap steel pile is T, and the bulk density is expressed as:

[0074]

[0075] In some embodiments, based on the calculated overall stacking density of the scrap steel pile and the volume of a single layer of scrap steel material, the weight information of the single layer of scrap steel material can be determined, so that the single layer of scrap steel material can be graded more accurately by combining the weight information and the image segmentation result.

[0076] In some embodiments, by calculating the volume and stacking density of each layer of scrap steel materials in each of the m areas in the truck bed, the density distribution curve of the scrap steel of the entire truck and the weight distribution ratio information of each layer of scrap steel materials can be obtained, so that scrap steel can be further graded for the scrap steel of the entire truck.

[0077] Return to reference Figure 2 In step 230, for each layer of scrap steel material in the scrap steel pile, the following steps 2310 to 2340 are performed.

[0078] Step 2310, performing image segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an image segmentation result for the layer of scrap steel material, wherein the image segmentation result indicates steel material information and non-steel material information of the layer of scrap steel material.

[0079] Figure 5 A further exemplary flow chart of a portion of a method for grading scrap steel according to an embodiment of the present disclosure is shown.

[0080] like Figure 5 As shown, according to some embodiments, step 2310 includes the following steps 510 to 530.

[0081] Step 510, semantic segmentation processing is performed on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain a semantic segmentation result, wherein the semantic segmentation result indicates the result of identifying and removing impurities of the layer of scrap steel material as a whole.

[0082] In some embodiments, the collected image data not only contains scrap steel materials, but also includes information on non-steel objects such as soil residue and oil stains, as well as irrelevant areas such as the truck bed baffle or bottom plate or the background outside the car. Therefore, the image data of a single layer of scrap steel materials can be semantically segmented to obtain feature information of each semantic feature area.

[0083] In some embodiments, the above-mentioned semantic segmentation results include but are not limited to foreground area information indicating scrap steel materials, background area information indicating non-scrap steel materials, miscellaneous area information indicating non-steel materials, and stacking information indicating the stacking size and stacking method of scrap steel materials.

[0084] In some embodiments, the semantic segmentation model includes an image data input module, a feature extraction module, and a prediction recognition result output module. In the example, a deep learning neural network model can be used as a semantic segmentation model. For example, an encoder based on a convolutional neural network such as VGG-16 and Resnet can be used as a feature extractor for the backbone network part of the semantic segmentation model, and an encoder based on a Transformer structure can also be used as a feature extractor for the backbone network part of the semantic segmentation model.

[0085] Step 520, performing instance segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an instance segmentation result, wherein the instance segmentation result indicates the result of identifying and removing impurities for each steel material in the layer of scrap steel material.

[0086] In some embodiments, data such as the thickness of steel, the type of steel material, the size of steel, the number of dangerous objects, and the number of rejected items directly affect the rating results of the scrap steel pile. Therefore, the image data of a single layer of scrap steel material can be segmented to obtain the characteristic information of a single piece of scrap steel material.

[0087] In some embodiments, the above-mentioned example segmentation results include but are not limited to information indicating the thickness of a single piece of scrap steel material, information indicating the material type of a single piece of scrap steel, information indicating the size of a single piece of scrap steel material, and information indicating toxic and hazardous substances or other rejected materials.

[0088] In some embodiments, the instance segmentation model includes an image data input module, a feature extraction module, and a prediction recognition result output module. In an example, the above instance segmentation process can be implemented using a Mask R-CNN model based on deep learning.

[0089] It should be noted that the specific processing process of the above-mentioned semantic segmentation model and instance segmentation model is the existing technology and will not be repeated here.

[0090] Step 530: Generate an image segmentation result according to the semantic segmentation result and the instance segmentation result.

[0091] By combining the semantic segmentation results and instance segmentation results, it is possible to perform feature extraction and complementary correction of scrap steel materials from both the overall and individual perspectives, thereby enriching the extracted image feature information and effectively improving the accuracy of the final scrap steel grading results.

[0092] Return to reference Figure 2 In step 2320, the single-layer volume of the layer of scrap steel material is determined based on the point cloud data in the single-layer scrap steel data corresponding to the layer of scrap steel material.

[0093] In some embodiments, if the stacking density of the scrap steel pile in the non-target area of ​​the same transport vehicle is directly used as the stacking density in the target area, the actual volume of the single-layer scrap steel material can be determined based on the point cloud data by referring to the above steps 420 to 430, which will not be repeated here.

[0094] In other embodiments, if the stacking density is calculated separately for the scrap steel pile in the target area, the single-layer volume of the scrap steel material layer obtained during the calculation process can be directly obtained.

[0095] Step 2330, determining the single layer weight of the layer of scrap steel material according to the single layer volume and bulk density.

[0096] In some embodiments, according to the above example, the single layer weight T of the layer of scrap steel material is ij The formula is:

[0097] T ij =ρL ij

[0098] Step 2340, determining the single-layer rating result of the layer of scrap steel material according to the image segmentation result and the single-layer weight.

[0099] In some embodiments, the above image segmentation results and single-layer weights can be further processed based on a decision tree algorithm or a deep learning neural model to obtain a single-layer rating result.

[0100] Step 240 , determining an overall rating result of the scrap steel pile according to at least one single-layer rating result among a plurality of single-layer rating results corresponding to the multi-layer scrap steel material.

[0101] In some embodiments, at least one single-layer rating result may be subjected to statistical processing such as weighting, averaging, maximizing, or minimizing to obtain an overall rating result of the scrap steel pile.

[0102] According to the embodiments of the present disclosure, by introducing point cloud data of a single layer of scrap steel, the stacking density and volume information of the scrap steel pile can be determined, and the weight information of the single layer of scrap steel can be further determined, so that scrap steel grading can be performed based on the image segmentation results and weight information of the single layer of scrap steel image, thereby effectively improving the accuracy of scrap steel grading.

[0103] Figure 6 A further exemplary flow chart of a part of a method for grading scrap steel according to an embodiment of the present disclosure is shown.

[0104] like Figure 6 As shown, according to some embodiments, the method 200 includes steps 610 to 640 in addition to steps 210 to 240.

[0105] Step 610: Acquire at least one instance segmentation feature data corresponding to at least one target material type of steel from the image segmentation result.

[0106] Step 620, topological transformation is performed on at least one instance segmentation feature data one by one to obtain at least one steel material graph corresponding to at least one steel material mapped to the topological space.

[0107] Step 630: compare at least one steel material pattern with reference steel material patterns of the target material type in a steel material pattern reference database.

[0108] Step 640: Correct the steel information in the image segmentation result according to the comparison result.

[0109] In some embodiments, the feature information corresponding to each steel material can be obtained from the image segmentation result as instance segmentation feature data, and the instance segmentation feature data indicates the feature graph A of the corresponding steel material. After the feature graph A is topologically transformed and mapped to the topological space, the corresponding topological feature graph B can be obtained. According to the topological isoform property, the topological morphological graph properties corresponding to the graphs with different morphological features but belonging to the same material type in the Euclidean space are the same. Therefore, by comparing the topological feature graph B with the prior reference steel graph of the same material type, the material type category of the steel material can be corrected, thereby improving the accuracy of the rating of scrap steel materials.

[0110] Figure 7 A structural block diagram of a scrap steel grading device according to an embodiment of the present disclosure is shown.

[0111] like Figure 7 As shown, according to an embodiment of the present disclosure, a scrap steel grading device is provided, including a first acquisition module 710 , a determination module 720 , a processing module 730 and a grading module 740 .

[0112] The first acquisition module 710 is configured to acquire multiple single-layer scrap steel data, wherein the multiple single-layer scrap steel data correspond one-to-one to the multiple layers of scrap steel materials included in the scrap steel pile, the scrap steel pile is located in the target area, and each single-layer scrap steel data includes image data and point cloud data collected for the target area when the scrap steel material of the corresponding layer becomes the surface scrap steel material of the scrap steel pile during the unloading process.

[0113] The determination module 720 is configured to determine the bulk density of the scrap steel pile.

[0114] The processing module 730 is configured to process each layer of scrap steel material in the scrap steel pile.

[0115] Performing image segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an image segmentation result for the layer of scrap steel material, wherein the image segmentation result indicates steel material information and non-steel material information of the layer of scrap steel material;

[0116] Determine the single-layer volume of the layer of scrap steel material according to the point cloud data in the single-layer scrap steel data corresponding to the layer of scrap steel material;

[0117] Determine the single-layer weight of the scrap steel material according to the single-layer volume and the stacking density; and determine the single-layer rating result of the scrap steel material according to the image segmentation result and the single-layer weight.

[0118] The rating module 740 is configured to determine an overall rating result of the scrap steel pile according to at least one single-layer rating result among a plurality of single-layer rating results corresponding to the multi-layer scrap steel material.

[0119] Here, the operations of the above-mentioned units 710-740 of the scrap steel rating device 700 are similar to the operations of the steps 210-240 described above, and are not described in detail here. In some embodiments, the scrap steel rating device 700 may also include one or more additional modules to perform functions corresponding to the additional steps (e.g., steps 610-640) of the method 200, which are not shown in the figure for the sake of simplicity. Figure 7 middle.

[0120] Although specific functions are discussed above with reference to specific modules, it should be noted that the functions of the various modules discussed herein may be divided into multiple modules, and / or at least some functions of multiple modules may be combined into a single module. The specific module discussed herein performing an action includes the specific module itself performing the action, or alternatively the specific module calling or otherwise accessing another component or module that performs the action (or performs the action in conjunction with the specific module). Therefore, the specific module that performs an action may include the specific module itself that performs the action and / or another module that the specific module calls or otherwise accesses to perform the action.

[0121] It should also be understood that various techniques may be described herein in the general context of software hardware elements or program modules. Figure 7 The modules described can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these modules can be implemented as computer program code / instructions, which are configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these modules can be implemented as hardware logic / circuits. Hardware logic / circuits can include integrated circuit chips (which include processors (e.g., central processing units (CPU), microcontrollers, microprocessors, digital signal processors (DSP), etc.), memory, one or more communication interfaces, and / or one or more components in other circuits), and can optionally execute the received program code and / or include embedded firmware to perform functions.

[0122] According to an embodiment of the present disclosure, an electronic device, a readable storage medium and a computer program product are also provided.

[0123] refer to Figure 8 , a block diagram of an electronic device 800 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0124] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0125] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. The input unit 806 can be any type of device that can input information to the electronic device 800. The input unit 806 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 807 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 808 can include but is not limited to a disk, an optical disk. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0126] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning network algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the method 200 in any other appropriate manner (e.g., by means of firmware).

[0127] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0129] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0130] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0131] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0132] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0133] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be performed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document is not limited here.

[0134] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A scrap steel rating method comprising: Acquire multiple single-layer scrap steel data, wherein the multiple single-layer scrap steel data correspond one-to-one to multiple layers of scrap steel materials included in a scrap steel pile, the scrap steel pile is located in a target area, and each single-layer scrap steel data includes image data and point cloud data acquired by collecting the target area when the scrap steel materials of the corresponding layer become the surface scrap steel materials of the scrap steel pile during the unloading process; determining a bulk density of the scrap steel stockpile; For each layer of scrap steel material in the scrap steel pile, Performing image segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an image segmentation result for the layer of scrap steel material, wherein the image segmentation result indicates steel material information and non-steel material information of the layer of scrap steel material; Determine the single-layer volume of the layer of scrap steel material according to the point cloud data in the single-layer scrap steel data corresponding to the layer of scrap steel material; Determining the single layer weight of the layer of scrap steel material according to the single layer volume and the bulk density; and Determining a single-layer rating result of the layer of scrap steel material according to the image segmentation result and the single-layer weight; and An overall rating result of the scrap steel pile is determined according to at least one single-layer rating result among a plurality of single-layer rating results corresponding to the multi-layer scrap steel material.

2. The method according to claim 1, wherein: Determining the bulk density of the scrap steel pile comprises: Obtaining the entire weight of the scrap steel pile; Determine a single-layer volume of each layer of scrap steel material in the multiple layers of scrap steel material according to the multiple single-layer scrap steel data; Determining the overall volume of the scrap steel pile according to the volumes of the multiple single layers corresponding to the multiple layers of scrap steel material; and The bulk density is determined based on the overall weight and the overall volume.

3. The method according to claim 2, wherein: The target area is located in the cargo box of the transport vehicle, the scrap steel pile includes the first to nth layers of scrap steel materials from bottom to top, n is an integer greater than or equal to 1, and Wherein, determining the single-layer volume of each layer of scrap steel material in the multiple layers of scrap steel material according to the multiple single-layer scrap steel data comprises: Obtaining the actual height of the vehicle from the lowest point of the bucket of the transport vehicle to the ground, and the actual length and width of the target area; For the first layer of scrap steel material in the scrap steel pile, Determine a first point cloud height of the highest point of the first layer of scrap steel material from the ground and a first point cloud width of the target area according to the point cloud data in the single layer of scrap steel data corresponding to the first layer of scrap steel material; Determining a size transformation ratio according to a ratio of an actual width of the region to a width of the first point cloud; Determine a first actual height of the highest point of the first layer of scrap steel material from the ground according to the size transformation ratio and the first point cloud height; determining the actual height of the first layer of the first layer of scrap steel material according to the difference between the first actual height and the actual height of the vehicle; and Determine the single-layer volume of the first layer of scrap steel material according to the actual length of the area, the actual width of the area and the actual height of the first layer; For the i-th layer of scrap steel material in the scrap steel pile, i is an integer, and the value range of i is (1, n], Determine a second point cloud height of the highest point of the i-th layer of scrap steel material from the ground according to the point cloud data in the single-layer scrap steel data corresponding to the i-th layer of scrap steel material; Determine a third point cloud height of the highest point of the i-1th layer of scrap steel material from the ground according to the point cloud data in the single layer of scrap steel data corresponding to the i-1th layer of scrap steel material; Determine the point cloud height of the i-th layer of scrap steel material according to the second point cloud height and the third point cloud height; Determining the actual height of the i-th layer of the i-th layer of scrap steel material according to the size transformation ratio and the i-th layer of point cloud height; and The single-layer volume of the i-th layer of scrap steel material is determined according to the actual length of the area, the actual width of the area and the actual height of the i-th layer.

4. The method according to claim 1, wherein: The image segmentation process of the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material comprises: Performing semantic segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain a semantic segmentation result, wherein the semantic segmentation result indicates the result of identifying and removing impurities from the entire layer of scrap steel material; Performing instance segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an instance segmentation result, wherein the instance segmentation result indicates the result of identifying and removing impurities for each steel material in the layer of scrap steel material; and The image segmentation result is generated according to the semantic segmentation result and the instance segmentation result.

5. The method according to any one of claims 1 to 4, further comprising: Acquire at least one instance segmentation feature data corresponding to at least one target material type of steel from the image segmentation result; Performing topological transformation on the at least one instance segmentation feature data one by one to obtain at least one steel material graph corresponding to the at least one steel material mapped to the topological space; Comparing the at least one steel material pattern with a reference steel material pattern of the target material type in a steel material pattern reference database; as well as The steel material information in the image segmentation result is corrected according to the comparison result.

6. A scrap steel grading device, comprising: A first acquisition module is configured to acquire a plurality of single-layer scrap steel data, wherein the plurality of single-layer scrap steel data correspond one-to-one to multiple layers of scrap steel materials included in a scrap steel pile, the scrap steel pile is located in a target area, and each single-layer scrap steel data includes image data and point cloud data acquired by collecting the target area when the scrap steel materials of a corresponding layer become surface scrap steel materials of the scrap steel pile during unloading; A determination module configured to determine a bulk density of the scrap steel pile; A processing module is configured to process each layer of scrap steel material in the scrap steel pile. Performing image segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an image segmentation result for the layer of scrap steel material, wherein the image segmentation result indicates steel material information and non-steel material information of the layer of scrap steel material; Determine the single-layer volume of the layer of scrap steel material according to the point cloud data in the single-layer scrap steel data corresponding to the layer of scrap steel material; Determining the single layer weight of the layer of scrap steel material according to the single layer volume and the bulk density; and Determining a single-layer rating result of the layer of scrap steel material according to the image segmentation result and the single-layer weight; and The rating module is configured to determine an overall rating result of the scrap steel pile according to at least one single-layer rating result among a plurality of single-layer rating results corresponding to the multi-layer scrap steel material.

7. The device according to claim 6, wherein: The determining module comprises: An acquisition submodule, configured to acquire the overall weight of the scrap steel pile; A first determining submodule is configured to determine a single-layer volume of each layer of scrap steel material in the multiple layers of scrap steel material according to the multiple single-layer scrap steel data; A second determining submodule is configured to determine the overall volume of the scrap steel pile according to a plurality of single-layer volumes corresponding to the multi-layer scrap steel material; and The third determination submodule is configured to determine the stacking density according to the overall weight and the overall volume.

8. The device according to claim 7, wherein: The target area is located in the cargo box of the transport vehicle, the scrap steel pile includes the first to nth layers of scrap steel materials from bottom to top, n is an integer greater than or equal to 1, and Wherein, the first determination submodule is configured as follows: Obtaining the actual height of the vehicle from the lowest point of the bucket of the transport vehicle to the ground, and the actual length and width of the target area; For the first layer of scrap steel material in the scrap steel pile, Determine a first point cloud height of the highest point of the first layer of scrap steel material from the ground and a first point cloud width of the target area according to the point cloud data in the single layer of scrap steel data corresponding to the first layer of scrap steel material; Determining a size transformation ratio according to a ratio of an actual width of the region to a width of the first point cloud; Determine a first actual height of the highest point of the first layer of scrap steel material from the ground according to the size transformation ratio and the first point cloud height; determining the actual height of the first layer of the first layer of scrap steel material according to the difference between the first actual height and the actual height of the vehicle; and Determine the single-layer volume of the first layer of scrap steel material according to the actual length of the area, the actual width of the area and the actual height of the first layer; For the i-th layer of scrap steel material in the scrap steel pile, i is an integer, and the value range of i is (1, n], Determine a second point cloud height of the highest point of the i-th layer of scrap steel material from the ground according to the point cloud data in the single-layer scrap steel data corresponding to the i-th layer of scrap steel material; Determine a third point cloud height of the highest point of the i-1th layer of scrap steel material from the ground according to the point cloud data in the single layer of scrap steel data corresponding to the i-1th layer of scrap steel material; Determine the point cloud height of the i-th layer of scrap steel material according to the second point cloud height and the third point cloud height; Determining the actual height of the i-th layer of the i-th layer of scrap steel material according to the size transformation ratio and the i-th layer of point cloud height; and The single-layer volume of the i-th layer of scrap steel material is determined according to the actual length of the area, the actual width of the area and the actual height of the i-th layer.

9. The device according to claim 6, wherein: The processing module is configured to: Performing semantic segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain a semantic segmentation result, wherein the semantic segmentation result indicates the result of identifying and removing impurities from the entire layer of scrap steel material; Performing instance segmentation processing on the image data in the single-layer scrap steel data corresponding to the layer of scrap steel material to obtain an instance segmentation result, wherein the instance segmentation result indicates the result of identifying and removing impurities for each steel material in the layer of scrap steel material; and The image segmentation result is generated according to the semantic segmentation result and the instance segmentation result.

10. The device according to any one of claims 6 to 9, further comprising: A second acquisition module is used to acquire at least one instance segmentation feature data corresponding to at least one target material type of steel from the image segmentation result; A transformation module, used for performing topological transformation on the at least one instance segmentation feature data one by one, so as to obtain at least one steel material graph corresponding to the at least one steel material mapped to the topological space; A comparison module, comparing the at least one steel material pattern with a reference steel material pattern of the target material type in a steel material pattern reference database; as well as The correction module is used to correct the steel information in the image segmentation result according to the comparison result.

11. An electronic device, comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

13. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images