Automatic detection and evaluation method and system for scrap recycled steel

Abstract

The application relates to the field of automatic detection technology, and relates to an automatic detection and evaluation method for waste recycled steel, which comprises the following steps: performing automatic image collection on the waste recycled steel to obtain recycled steel collection images, storing the recycled steel collection images into an image storage unit, performing image preprocessing on the recycled steel collection images to obtain preprocessed images, performing fuzzy marking on the preprocessed images to obtain a fuzzy boundary set, sequentially extracting the fuzzy boundaries, judging whether the fuzzy boundaries are defect boundaries, judging the defect types of the defect boundaries, calculating defect scores of the defect boundaries based on the defect types, if the fuzzy boundary extraction is completed, summarizing the defect scores to obtain a defect score set, calculating a comprehensive defect score based on the defect score set, performing evaluation grading on the waste recycled steel based on the score level and the comprehensive defect score, and obtaining graded recycled steel. The application can improve the detection and evaluation efficiency of the waste recycled steel.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic detection technology, and in particular to an automatic detection and evaluation method and system for waste recycled steel, an electronic device and a computer readable storage medium. BACKGROUND

[0002] With the continuous development of waste metal recycling, the detection and evaluation of waste recycled steel has become an important link to improve resource utilization efficiency.

[0003] The existing detection method for waste recycled steel relies on manual detection, and the inspectors visually inspect the appearance defects of the recycled steel, such as cracks, holes, rust, etc.

[0004] Although the above method can realize the detection of waste recycled steel, manual detection is low in efficiency and easily affected by subjective factors. In addition, when facing complex background and light change conditions, the inspectors are prone to misjudgment, affecting the reliability of the evaluation results. Furthermore, manual detection lacks systematicness in defect classification and evaluation, and cannot effectively quantify and evaluate different types of defects. Therefore, the current detection and evaluation method for waste recycled steel has the problem of low detection and evaluation efficiency. SUMMARY

[0005] The present application provides an automatic detection and evaluation method for waste recycled steel and a computer readable storage medium, which mainly aims to improve the detection and evaluation efficiency of waste recycled steel.

[0006] To achieve the above purpose, the present application provides an automatic detection and evaluation method for waste recycled steel, which comprises:

[0007] receiving a detection instruction and starting a pre-constructed image detection unit based on the detection instruction, wherein the image detection unit comprises an image acquisition unit, an image storage unit and an image processing unit;

[0008] using the image acquisition unit to perform automatic image acquisition on the preset waste recycled steel, obtaining a recycled steel acquisition image and generating an image storage instruction;

[0009] using the image storage unit to receive the image storage instruction, storing the recycled steel acquisition image in the image storage unit and generating an image processing instruction;

[0010] using the image processing unit to receive the image processing instruction and execute processing instruction analysis to obtain an instruction analysis result;

[0011] based on the instruction analysis result and the image processing unit, performing image preprocessing on the recycled steel acquisition image to obtain a preprocessed image, wherein the image preprocessing is median filtering and binarization;

[0012] performing blur marking on the preprocessed image by using a preset blur marking method to obtain a blur boundary set;

[0013] extracting blur boundaries in the blur boundary set in sequence;

[0014] judging whether the blur boundary is a preset defect boundary by using a preset defect threshold;

[0015] if the blur boundary is not a defect boundary, returning to the step of extracting blur boundaries in the blur boundary set in sequence;

[0016] if the blur boundary is a defect boundary, judging a defect type of the defect boundary based on a preset defect standard, wherein the defect type includes a crack defect, a hole defect and a rust defect;

[0017] calculating a defect score of the defect boundary based on the defect type;

[0018] judging whether the blur boundary extraction is completed;

[0019] if the blur boundary extraction is not completed, returning to the step of extracting blur boundaries in the blur boundary set in sequence;

[0020] if the blur boundary extraction is completed, summarizing the defect scores to obtain a defect score set, and calculating a comprehensive defect score based on the defect score set;

[0021] evaluating and grading the waste recycling steel based on a preset score level and the comprehensive defect score to obtain a graded recycling steel.

[0022] Optionally, the using the image acquisition unit to perform automatic image acquisition on the preset waste recycling steel to obtain a recycling steel acquisition image and generate an image storage instruction comprises:

[0023] using the image acquisition unit to perform 3s continuous shooting on the waste recycling steel based on a shooting frequency of 5 pictures / s to obtain a recycling steel image set;

[0024] selecting two images with the highest clarity based on the recycling steel image set to obtain a first representative image and a second representative image;

[0025] obtaining a first pixel value set of the first representative image and a second pixel value set of the second representative image;

[0026] expanding the first pixel value set and the second pixel value set into one-dimensional arrays to obtain a first pixel array and a second pixel array;

[0027] calculating image similarity of the first representative image and the second representative image based on the first pixel array and the second pixel array;

[0028] judging whether the image similarity is greater than a preset similarity threshold value;

[0029] if the image similarity is greater than the similarity threshold value, randomly selecting one of the first representative image and the second representative image as a recycled steel collection image, and generating an image storage instruction based on the recycled steel collection image;

[0030] if the image similarity is not greater than the similarity threshold value, taking the first representative image and the second representative image as the recycled steel collection image, and generating an image storage instruction based on the recycled steel collection image.

[0031] Optionally, the calculating of the image similarity of the first representative image and the second representative image based on the first pixel array and the second pixel array comprises:

[0032] obtaining a total number of pixels based on the first pixel array and the second pixel array, wherein the total number of pixels is a total number of pixels of the first pixel array or a total number of pixels of the second pixel array, and the total number of pixels of the first pixel array is equal to the total number of pixels of the second pixel array;

[0033] calculating the image similarity of the first representative image and the second representative image by using the total number of pixels, the first pixel array and the second pixel array:

[0034]

[0035] wherein T represents the image similarity, n represents the total number of pixels, Q i represents the i-th pixel value in the first pixel array, W i represents the i-th pixel value in the second pixel array.

[0036] Optionally, the receiving of the image processing instruction by the image processing unit and the execution of the processing instruction analysis to obtain an instruction analysis result comprises:

[0037] the image processing unit comprises a first image processing unit and a second image processing unit;

[0038] the processing instruction analysis is as follows:

[0039] calculating a running load of the first image processing unit, and judging whether the running load is less than a preset running load threshold value;

[0040] if the running load is less than the running load threshold value, the instruction analysis result is determined as inputting the recycled steel collection image into the first image processing unit.

[0041] If the running load is equal to or greater than the running load threshold, the instruction resolution result is determined to input the recycled steel collection image into the second image processing unit, and after waiting for the running load to be less than the running load threshold, the recycled steel collection image is input into the first image collection unit.

[0042] Optionally, the calculation of the running load of the first image processing unit comprises:

[0043] The CPU usage, memory usage, bandwidth usage and IO rate of the first image processing unit are obtained.

[0044] The CPU load weight, memory load weight, bandwidth load weight and IO load weight of the first image processing unit are obtained.

[0045] The running load of the first image processing unit is calculated based on the CPU usage, memory usage, bandwidth usage, IO rate, CPU load weight, memory load weight, bandwidth load weight and IO load weight:

[0046] H = p1 x R1 + p2 x R2 + p3 x R3 + p4 x R4

[0047] Wherein, H refers to the running load of the first image processing unit, p1 refers to the CPU load weight, R1 refers to the CPU usage, p2 refers to the memory load weight, R2 refers to the memory usage, p3 refers to the bandwidth load weight, R3 refers to the bandwidth usage, p4 refers to the IO load weight, and R4 refers to the IO rate.

[0048] Optionally, the determination of whether the fuzzy boundary is a defect boundary by using a preset defect threshold comprises:

[0049] The total amount of fuzzy boundary pixels of the fuzzy boundary and the pixel equivalent of the fuzzy boundary are obtained.

[0050] The fuzzy boundary area of the fuzzy boundary is calculated based on the total amount of fuzzy boundary pixels of the fuzzy boundary and the pixel equivalent of the fuzzy boundary:

[0051] M = S x Z

[0052] Wherein, M refers to the fuzzy boundary area, S refers to the total amount of fuzzy boundary pixels, and Z refers to the pixel equivalent.

[0053] It is determined whether the fuzzy boundary area is less than the defect threshold.

[0054] If the fuzzy boundary area is less than the defect threshold, it is determined that the fuzzy boundary is not a defect boundary.

[0055] If the fuzzy boundary area is not less than the defect threshold, the fuzzy boundary is determined as a defect boundary.

[0056] Optionally, the defect type of the defect boundary is determined based on a preset defect criterion, including:

[0057] An area of the defect boundary is obtained, and it is determined whether the area of the defect boundary is less than a preset crack area threshold;

[0058] If the area of the defect boundary is less than the crack area threshold, the defect type of the defect boundary is determined as a crack defect.

[0059] If the area of the defect boundary is not less than the crack area threshold, a defect boundary roundness of the defect boundary is calculated.

[0060] The calculation method is as follows:

[0061] The defect pixel point, the total amount of defect pixel points, the horizontal coordinate and the vertical coordinate of the defect pixel point of the defect boundary are obtained.

[0062] The defect boundary circumference is calculated by using a preset dist function, the defect pixel point, the total amount of defect pixel points, the horizontal coordinate and the vertical coordinate of the defect pixel point of the defect boundary.

[0063]

[0064] Wherein, X refers to the defect boundary circumference, E refers to the total amount of defect pixel points, dist refers to the dist function, x τ refers to the horizontal coordinate of the τth defect pixel point, y τ refers to the vertical coordinate of the τth defect pixel point, x τ+1 refers to the horizontal coordinate of the τ+1th defect pixel point, y τ+1 refers to the vertical coordinate of the τ+1th defect pixel point.

[0065] The defect boundary roundness is calculated as follows:

[0066]

[0067] Wherein, Y refers to the defect boundary roundness, A refers to the area of the defect boundary, X refers to the defect boundary circumference, and π refers to the circular constant.

[0068] It is determined whether the defect boundary roundness of the defect boundary is less than a preset hole roundness threshold.

[0069] If the defect boundary roundness of the defect boundary is not less than the hole roundness threshold, the defect type of the defect boundary is determined as a hole defect.

[0070] If the defect boundary circularity of the defect boundary is less than the hole circularity threshold, it is determined that the defect type of the defect boundary is a rust defect.

[0071] Optionally, the calculating the defect score of the defect boundary based on the defect type comprises:

[0072] If the defect type is a crack defect, a crack area, a crack depth and a crack length of the crack defect are obtained.

[0073] The crack area, the crack depth and the crack length are substituted into preset crack area criteria, crack depth criteria and crack length criteria respectively to obtain a crack area score, a crack depth score and a crack length score, wherein the crack area criteria are: (0, 5] cm: 2 points, (5, 10] cm: 6 points, (10, +∞) cm: 10 points, the crack depth criteria are: (0, 0.5] mm: 2 points, (0.5, 1.5] mm: 6 points, (1.5, +∞) mm: 10 points, and the crack length criteria are: (0, 2] cm: 2 points, (2, 6] cm: 6 points, (6, +∞) cm: 10 points. 2 2 2

[0074] The crack area score, the crack depth score and the crack length score are used to calculate the defect score of the defect type being the crack defect.

[0075] U1=b1+b2+b3

[0076] wherein U1 refers to the defect score of the defect type being the crack defect, b1 refers to the crack area score, b2 refers to the crack depth score, and b3 refers to the crack length score.

[0077] If the defect type is a hole defect, a hole diameter, a hole depth and a hole circularity of the hole defect are obtained.

[0078] The hole diameter, the hole depth and the hole circularity are substituted into preset hole diameter criteria, hole depth criteria and hole circularity criteria to obtain a hole diameter score, a hole depth score and a hole circularity score, wherein the hole diameter criteria are: (0, 0.5] cm: 2 points, (0.5, 4] cm: 6 points, (4, +∞) cm: 10 points, the hole depth criteria are: (0, 0.5] mm: 2 points, (0.5, 3] mm: 6 points, (3, +∞) mm: 10 points, and the hole circularity criteria are: (0, 0.5]: 10 points, (0.5, 0.8], 6 points, (0.8, 1.0): 2 points.

[0079] The hole diameter score, the hole depth score and the hole circularity score are used to calculate the defect score of the defect type being the hole defect.​​​

[0080] U2=g1+g2+g3

[0081] wherein, U2 refers to the defect score of the defect type of hole defect, g1 refers to the hole diameter score, g2 refers to the hole depth score, and g3 refers to the hole roundness score;

[0082] If the defect type is rust defect, the rust area, rust depth and texture complexity of the rust defect are obtained, wherein the texture complexity includes smooth, rough and extremely rough;

[0083] The rust area, rust depth and texture complexity are substituted into the preset rust area standard, rust depth standard and texture complexity standard to obtain the rust area score, rust depth score and texture complexity score, wherein the rust area standard is (0, 5] cm 2 : 2 points, (5, 10] cm 2 : 6 points, (10, +∞) cm 2 : 10 points, the rust depth standard is (0, 1] mm: 2 points, (1, 4] mm: 6 points, (4, +∞) mm: 10 points, and the texture complexity standard is smooth: 2 points, rough: 6 points, and extremely rough: 10 points;

[0084] The rust area score, rust depth score and texture complexity score are used to calculate the defect score of the defect type of rust defect:

[0085] U3=k1+k2+k3

[0086] wherein, U3 refers to the defect score of the defect type of rust defect, k1 refers to the rust area score, k2 refers to the rust depth score, and k3 refers to the texture complexity score.

[0087] Optionally, the calculating the comprehensive defect score based on the defect score set comprises:

[0088] The defect score set is divided into a crack score set, a hole score set and a rust score set based on the defect type, and the number of crack scores, the number of hole scores, the number of rust scores, the crack score, the hole score and the rust score are obtained by using the crack score set, the hole score set and the rust score set;

[0089] The crack score weight, the hole score weight and the rust score weight are obtained, and the comprehensive defect score is calculated based on the number of crack scores, the number of hole scores, the number of rust scores, the crack score, the hole score, the rust score, the crack score weight, the hole score weight and the rust score weight:

[0090]

[0091] wherein, U4 refers to the comprehensive defect score, l1 refers to the crack score weight, f refers to the number of crack scores, h α refers to the first crack score, l2 refers to the hole score weight, t refers to the number of hole scores, c β refers to the first hole score, l3 refers to the rust score weight, o refers to the number of rust scores, j γ refers to the first rust score.

[0092] To achieve the above purpose, the application further provides an automatic detection and evaluation system for waste recycled steel, comprising:

[0093] An image acquisition module is configured to receive a detection instruction, and start a pre-constructed image detection unit based on the detection instruction, wherein the image detection unit comprises an image acquisition unit, an image storage unit and an image processing unit, the image acquisition unit is configured to perform automatic image acquisition on a preset waste recycled steel, obtain a recycled steel acquisition image and generate an image storage instruction;

[0094] An image preprocessing module is configured to receive the image storage instruction by using the image storage unit, store the recycled steel acquisition image in the image storage unit and generate an image processing instruction, receive the image processing instruction by using the image processing unit and perform processing instruction analysis to obtain an instruction analysis result, perform image preprocessing on the recycled steel acquisition image based on the instruction analysis result and the image processing unit to obtain a preprocessed image, wherein the image preprocessing comprises median filtering and binarization.

[0095] A defect boundary judgment module is configured to perform fuzzy labeling on the preprocessed image by using a preset fuzzy labeling method to obtain a fuzzy boundary set, sequentially extract fuzzy boundaries in the fuzzy boundary set, judge whether the fuzzy boundaries are preset defect boundaries by using a preset defect threshold, if the fuzzy boundaries are not defect boundaries, return to the step of sequentially extracting fuzzy boundaries in the fuzzy boundary set, and if the fuzzy boundaries are defect boundaries, judge the defect types of the defect boundaries based on a preset defect standard, wherein the defect types comprise crack defects, hole defects and rust defects.

[0096] A recycled steel grading module is configured to calculate defect scores of the defect boundaries based on the defect types, judge whether the fuzzy boundaries are extracted completely, if the fuzzy boundaries are not extracted completely, return to the step of sequentially extracting fuzzy boundaries in the fuzzy boundary set, if the fuzzy boundaries are extracted completely, aggregate the defect scores to obtain a defect score set, calculate a comprehensive defect score based on the defect score set, and evaluate and grade the waste recycled steel based on a preset score level and the comprehensive defect score.

[0097] To solve the above problems, the application further provides an electronic device, which comprises:

[0098] a memory, which stores at least one instruction;

[0099] a processor, which executes the instruction stored in the memory to realize the automatic detection and evaluation method of the waste recycled steel.

[0100] To solve the above problems, the application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to realize the automatic detection and evaluation method of the waste recycled steel.

[0101] The present application is to solve the problems described in the background art, by combining the score level and the comprehensive defect score to perform multi-step processing on the image of the waste recycled steel, realizing the automatic detection and evaluation of the waste recycled steel. First, the image acquisition unit is used to perform automatic image acquisition on the waste recycled steel, which can quickly and continuously acquire the image of the waste recycled steel, reducing the waste of manual work and ensuring that the real state of the surface of the waste recycled steel can be captured in time, providing accurate image information for subsequent processing and improving the efficiency of the overall detection and evaluation. Second, the median filtering and binarization preprocessing are performed on the collected image of the recycled steel, which can effectively remove background noise and highlight important features, making the defects easier to observe in the image and making the fuzzy marking and defect recognition more efficient, improving the accuracy and efficiency of the detection. Then, fuzzy marking is performed on the preprocessed image using the fuzzy marking method to obtain a fuzzy boundary set, which can help to more accurately define the defect area and improve the efficiency and accuracy of defect recognition. Further, the fuzzy boundaries in the fuzzy boundary set are extracted in turn, and the defect threshold is used to judge whether the extracted fuzzy boundary is a defect boundary. When it is a defect boundary, the defect type of the defect boundary is judged based on the defect standard, which can reduce subjective judgment and improve the reliability of subsequent defect score calculation. Then, the defect score of the defect boundary is calculated based on the defect type, and each defect is scored to quantify the severity of the defect, making the evaluation result more intuitive. Not only does it provide a data basis for evaluation grading, but it also reduces the error of human judgment. Then, when the fuzzy boundary extraction is completed, the defect scores are summarized to obtain a defect score set, and the comprehensive defect score is calculated based on the defect score set. Based on the defect score, the quality status of the waste recycled steel can be more clearly and explicitly, and the evaluation efficiency is improved. Finally, the waste recycled steel is evaluated and graded based on the score level and the comprehensive defect score. According to the comprehensive defect score and the score level, effective grading can be performed to quickly evaluate the quality of the waste recycled steel. This standardized evaluation process simplifies the operation process and makes the evaluation of the waste recycled steel more efficient. Therefore, the present application can improve the detection and evaluation efficiency of the waste recycled steel. BRIEF DESCRIPTION OF DRAWINGS

[0102] Figure 1 The flowchart of the automatic detection and evaluation method of the waste recycled steel provided by an embodiment of the present application;

[0103] Figure 2 The functional module diagram of the automatic detection and evaluation system of the waste recycled steel provided by an embodiment of the present application;

[0104] Figure 3 The structural diagram of the electronic device for realizing the automatic detection and evaluation method of the waste recycled steel provided by an embodiment of the present application.

[0105] The objectives, functional characteristics and advantages of the present application will be further explained in conjunction with the embodiments, with reference to the accompanying drawings. DETAILED DESCRIPTION

[0106] It should be understood that the specific embodiments described herein merely exemplify the application and do not limit the application.

[0107] Embodiments of the present application provide an automatic detection and evaluation method for waste recycling steel. The execution subject of the automatic detection and evaluation method for waste recycling steel includes but is not limited to at least one of electronic devices such as a server, a terminal, etc., which can be configured to execute the method provided by the embodiments of the present application. In other words, the automatic detection and evaluation method for waste recycling steel can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0108] Reference Figure 1 Fig. 1 shows a flowchart of the automatic detection and evaluation method for waste recycling steel provided by an embodiment of the present application. In this embodiment, the automatic detection and evaluation method for waste recycling steel includes:

[0109] S1, receiving a detection instruction, and starting a pre-constructed image detection unit based on the detection instruction, wherein the image detection unit includes an image acquisition unit, an image storage unit, and an image processing unit.

[0110] It can be understood that the detection instruction is an instruction initiated by a detection personnel for starting the image detection unit. The image detection unit includes the image acquisition unit, the image storage unit, and the image processing unit. The image acquisition unit is used for image acquisition of the waste recycling steel and generates an image storage instruction. The image storage instruction is an instruction for storing images, which is sent to the image storage unit by the image acquisition unit. The image storage unit is used for receiving the image storage instruction, storing the acquired images, and generating an image processing instruction. The image processing instruction is an instruction for processing images, which is sent to the image processing unit by the image storage unit. The image processing unit is used for receiving the image processing instruction and processing the acquired images.

[0111] For example, a waste recycling steel factory wants to detect and evaluate a batch of waste recycling steel. A detection personnel initiates a detection instruction to start the image detection unit. The image acquisition unit starts automatic image acquisition of the waste recycling steel and stores the acquired images in the image storage unit. When the image acquisition is completed, the image storage unit sends the acquired images to the image processing unit, and the image processing unit processes the images.

[0112] S2, acquiring an image set of the waste recycling steel by the image acquisition unit based on a shooting frequency of 5 pictures per second and a continuous shooting time of 3 seconds.

[0113] The waste recycling steel refers to steel materials that have been used in industrial and construction fields and discarded. These steel materials can be reused after recycling. The automatic image acquisition refers to the image acquisition unit automatically acquiring images of the waste recycling steel. The recycling steel acquisition image refers to the image acquired by the image acquisition unit.

[0114] In detail, the automatic image acquisition of the waste recycling steel by the image acquisition unit includes:

[0115] Acquiring an image set of the waste recycling steel by the image acquisition unit based on a shooting frequency of 5 pictures per second and a continuous shooting time of 3 seconds.

[0116] Selecting two images with the highest clarity from the image set of the waste recycling steel to obtain a first representative image and a second representative image.

[0117] Obtaining a first pixel value set of the first representative image and a second pixel value set of the second representative image.

[0118] Expanding the first pixel value set and the second pixel value set into one-dimensional arrays to obtain a first pixel array and a second pixel array.

[0119] Calculating the image similarity between the first pixel array and the second pixel array.

[0120] Determining whether the image similarity is greater than a preset similarity threshold.

[0121] If the image similarity is greater than the similarity threshold, randomly selecting one of the first representative image and the second representative image as a recycling steel acquisition image, and generating an image storage instruction based on the recycling steel acquisition image.

[0122] If the image similarity is not greater than the similarity threshold, taking the first representative image and the second representative image as the recycling steel acquisition image, and generating an image storage instruction based on the recycling steel acquisition image.

[0123] The recyclable steel image set refers to a set of images obtained by taking pictures of waste recyclable steel for 3s according to a shooting frequency of 5 pictures / s, the first representative image and the second representative image refer to the two images with the highest definition in the recyclable steel image set, the first pixel value set refers to a set of pixel values of the first representative image, the second pixel value set refers to a set of pixel values of the second representative image, the first pixel array refers to an array obtained by unfolding the first pixel value set into a one-dimensional array, the second pixel array refers to an array obtained by unfolding the second pixel value set into a one-dimensional array, for example, assuming that the first pixel value set is in the form of a 3*3 matrix, The first pixel value set is unfolded into a one-dimensional array to obtain [1, 3, 4, 2, 3, 5, 7, 8, 6], and [1, 3, 4, 2, 3, 5, 7, 8, 6] is the first pixel array, the image similarity refers to the degree of similarity between two images, and the similarity threshold refers to a numerical value preset for judging whether two images are similar, when the image similarity is greater than the similarity threshold, it can be considered that the two images are the same.

[0124] In detail, the calculation of the image similarity between the first representative image and the second representative image based on the first pixel array and the second pixel array comprises:

[0125] Based on the first pixel array and the second pixel array, the total number of pixels is obtained, wherein the total number of pixels is the total number of pixels of the first pixel array or the total number of pixels of the second pixel array, and the total number of pixels of the first pixel array and the total number of pixels of the second pixel array are equal;

[0126] The total number of pixels, the first pixel array and the second pixel array are used to calculate the image similarity between the first representative image and the second representative image:

[0127]

[0128] Wherein, T refers to the image similarity, n refers to the total number of pixels, Q i refers to the i-th pixel value in the first pixel array, W i refers to the i-th pixel value in the second pixel array.

[0129] It can be understood that the total number of pixels refers to the total number of pixel values in the first pixel array or the second pixel array, and the total number of pixels of the first pixel array and the total number of pixels of the second pixel array are equal.

[0130] S3, receiving the image storage instruction by using the image storage unit, storing the recyclable steel collection image into the image storage unit and generating an image processing instruction.

[0131] S4, receiving the image processing instruction by using the image processing unit and executing the processing instruction analysis to obtain an instruction analysis result.

[0132] The processing instruction analysis refers to an action of analyzing the image processing instruction, and the instruction analysis result refers to a conclusion obtained after the processing instruction analysis. It can be known from the instruction analysis result whether the recycled steel collection image is directly input into the first image processing unit or the recycled steel collection image is first input into the second image processing unit, and the recycled steel collection image is input into the first image processing unit after the running load of the first image processing unit is less than the running load threshold. The running load refers to the load of the first image processing unit when it is working, and the running load threshold refers to the maximum load that the first image processing unit can bear when it is working.

[0133] In detail, the receiving the image processing instruction by the image processing unit and performing processing instruction analysis to obtain an instruction analysis result include:

[0134] The image processing unit includes a first image processing unit and a second image processing unit.

[0135] The processing instruction analysis is as follows:

[0136] The running load of the first image processing unit is calculated, and it is judged whether the running load is less than a preset running load threshold;

[0137] If the running load is less than the running load threshold, the instruction analysis result is determined as inputting the recycled steel collection image into the first image processing unit;

[0138] If the running load is equal to or greater than the running load threshold, the instruction analysis result is determined as inputting the recycled steel collection image into the second image processing unit, and after the running load is less than the running load threshold, the recycled steel collection image is input into the first image collection unit.

[0139] In detail, the calculation of the running load of the first image processing unit includes:

[0140] The cpu usage, memory usage, bandwidth usage and IO rate of the first image processing unit are obtained;

[0141] The cpu load weight, memory load weight, bandwidth load weight and IO load weight of the first image processing unit are obtained;

[0142] The running load of the first image processing unit is calculated based on the cpu usage, memory usage, bandwidth usage, IO rate, cpu load weight, memory load weight, bandwidth load weight and IO load weight:

[0143] H = p1 x R1 + p2 x R2 + p3 x R3 + p4 x R4

[0144] Wherein, H refers to the running load of the first image processing unit, p1 refers to the cpu load weight, R1 refers to the cpu usage, p2 refers to the memory load weight, R2 refers to the memory usage, p3 refers to the bandwidth load weight, R3 refers to the bandwidth usage, p4 refers to the IO load weight, and R4 refers to the IO rate.

[0145] The cpu usage refers to the usage degree of the cpu when the first image processing unit is working, the memory usage refers to the usage degree of the memory when the first image processing unit is working, the bandwidth usage refers to the proportion of the actually used bandwidth to the maximum bandwidth when the first image processing unit is working, for example, assuming that the maximum bandwidth of the first image processing unit is 100 / Mbps and the actually used bandwidth is 40 / Mbps, then the bandwidth usage is 40%, the IO rate refers to the speed of the first image processing unit when performing data read / write operation, the cpu load weight refers to the influence degree of the cpu usage on the running load, the memory load weight refers to the influence degree of the memory usage on the running load, the bandwidth load weight refers to the influence degree of the bandwidth usage on the running load, and the IO load weight refers to the influence degree of the IO rate on the running load.

[0146] S5, based on the instruction analysis result and the image processing unit, the image preprocessing is performed on the recycled steel collection image to obtain a preprocessed image, wherein the image preprocessing is median filtering and binarization.

[0147] The preprocessed image refers to the image obtained after the recycled steel collection image is subjected to median filtering and binarization processing, which is a prior art and will not be described here.

[0148] S6, a fuzzy marking method is used to perform fuzzy marking on the preprocessed image to obtain a fuzzy boundary set.

[0149] The fuzzy marking method is eight-connected, and the fuzzy marking method is used to mark the preprocessed image to obtain a plurality of connected regions, and a unique label is assigned to each connected region to distinguish the connected regions, the fuzzy boundary set is a set formed by the plurality of connected regions, and the eight-connected is a prior art and will not be described here.

[0150] S7, fuzzy boundaries are sequentially extracted from the fuzzy boundary set.

[0151] The fuzzy boundary refers to the connected region obtained after marking by the fuzzy marking method, and each connected region is a fuzzy boundary.

[0152] S8, whether the fuzzy boundary is a preset defect boundary is judged by using a preset defect threshold.

[0153] The explainable defect threshold value is a standard value for judging whether the fuzzy boundary is a defect boundary, and the defect boundary refers to a fuzzy boundary with an area greater than or equal to the defect threshold value.

[0154] In detail, the step of judging whether the fuzzy boundary is a defect boundary by using the preset defect threshold value comprises the following steps.

[0155] Obtaining the total amount of fuzzy boundary pixels of the fuzzy boundary and the pixel equivalent of the fuzzy boundary;

[0156] Calculating the fuzzy boundary area of the fuzzy boundary based on the total amount of fuzzy boundary pixels of the fuzzy boundary and the pixel equivalent of the fuzzy boundary:

[0157] M = S x Z

[0158] Wherein, M refers to the fuzzy boundary area, S refers to the total amount of fuzzy boundary pixels, and Z refers to the pixel equivalent.

[0159] Judging whether the fuzzy boundary area is less than the defect threshold value;

[0160] If the fuzzy boundary area is less than the defect threshold value, it is determined that the fuzzy boundary is not a defect boundary.

[0161] If the fuzzy boundary area is not less than the defect threshold value, it is determined that the fuzzy boundary is a defect boundary.

[0162] Explainable, the total amount of fuzzy boundary pixels refers to the total number of pixels in the fuzzy boundary, the pixel equivalent refers to the actual physical size represented by one pixel in a digital image, and the fuzzy boundary area refers to the area of the fuzzy boundary.

[0163] If the fuzzy boundary is not a defect boundary, return to the step of extracting the fuzzy boundary in the fuzzy boundary set in sequence.

[0164] If the fuzzy boundary is a defect boundary, perform S9, and judge the defect type of the defect boundary based on the preset defect standard, wherein the defect type comprises a crack defect, a hole defect, and a rust defect.

[0165] Explainable, the defect type refers to various types of defect boundaries, including cracks, holes, and rust, the crack defect refers to a defect with a crack type, the hole defect refers to a defect with a hole type, and the rust defect refers to a defect with a rust type.

[0166] In detail, the step of judging the defect type of the defect boundary based on the preset defect standard comprises the following steps.

[0167] Obtaining the defect boundary area of the defect boundary, and judging whether the defect boundary area is less than a preset crack area threshold value;

[0168] if the defect boundary area is less than the crack area threshold, confirming that the defect type of the defect boundary is a crack defect;

[0169] if the defect boundary area is not less than the crack area threshold, calculating the defect boundary roundness of the defect boundary;

[0170] The calculation method is as follows:

[0171] Obtaining the defect pixel points of the defect boundary, the total amount of defect pixel points, the horizontal coordinates and the vertical coordinates of the defect pixel points;

[0172] Calculating the defect boundary circumference by using a preset dist function, the defect pixel points of the defect boundary, the total amount of defect pixel points, the horizontal coordinates and the vertical coordinates of the defect pixel points:

[0173]

[0174] wherein X represents the defect boundary circumference, E represents the total amount of defect pixel points, dist represents the dist function, x τ represents the horizontal coordinate of the τth defect pixel point, y τ represents the vertical coordinate of the τth defect pixel point, x τ+1 represents the horizontal coordinate of the τ+1th defect pixel point, y τ+1 represents the vertical coordinate of the τ+1th defect pixel point;

[0175] Calculating the defect boundary roundness:

[0176]

[0177] wherein Y represents the defect boundary roundness, A represents the defect boundary area, X represents the defect boundary circumference, and π represents the circular constant;

[0178] Judging whether the defect boundary roundness of the defect boundary is less than a preset hole roundness threshold;

[0179] if the defect boundary roundness of the defect boundary is not less than the hole roundness threshold, confirming that the defect type of the defect boundary is a hole defect;

[0180] if the defect boundary roundness of the defect boundary is less than the hole roundness threshold, confirming that the defect type of the defect boundary is a rust defect.

[0181] Understandably, the defect boundary area refers to the area of ​​the defect boundary; the crack area threshold is the value used to determine whether the defect type of the defect boundary is a crack defect; when the defect boundary area is less than the crack area threshold, the defect type of the defect boundary is considered to be a crack defect; the defect boundary roundness refers to the regularity of the shape of the defect boundary, used to measure how close the defect boundary is to a circle; the total number of defect pixels refers to the total number of pixels within the defect boundary; defect pixels refer to the pixels within the defect boundary; the defect boundary perimeter refers to the perimeter of the defect boundary; and the hole roundness threshold is the value used to determine whether the defect type of the defect boundary is a hole defect.

[0182] S10. Calculate the defect score of the defect boundary based on the defect type.

[0183] Explainable, the defect score indicates the severity of the defect; the higher the defect score, the more serious the defect and the lower its recycling value.

[0184] Specifically, the calculation of the defect score based on the defect type for the defect boundary includes:

[0185] If the defect type is a crack defect, then obtain the crack area, crack depth and crack length of the crack defect;

[0186] Substituting the crack area, crack depth, and crack length into preset crack area, crack depth, and crack length standards, respectively, yields crack area scores, crack depth scores, and crack length scores. The crack area standard is defined as (0, 5] cm. 2 : 2 points, (5, 10] cm 2 : 6 points, (10, +∞) cm 2 The crack depth standard is: (0, 0.5] mm: 2 points, (0.5, 1.5] mm: 6 points, (1.5, +∞) mm: 10 points; the crack length standard is: (0, 2] cm: 2 points, (2, 6] cm: 6 points, (6, +∞) cm: 10 points.

[0187] The defect score for a crack defect is calculated using the crack area score, crack depth score, and crack length score.

[0188] U1 = b1 + b2 + b3

[0189] Among them, U1 refers to the defect score of the defect type being crack, b1 refers to the crack area score, b2 refers to the crack depth score, and b3 refers to the crack length score.

[0190] If the defect type is a hole defect, then obtain the hole diameter, hole depth, and hole roundness of the hole defect;

[0191] The hole diameter, hole depth and hole roundness are substituted into preset hole diameter standard, hole depth standard and hole roundness standard to obtain hole diameter score, hole depth score and hole roundness score, wherein the hole diameter standard is: (0, 0.5] cm: 2 points, (0.5, 4] cm: 6 points, (4, +∞) cm: 10 points, the hole depth standard is: (0, 0.5] mm: 2 points, (0.5, 3] mm: 6 points, (3, +∞) mm: 10 points, and the hole roundness standard is: (0, 0.5]: 10 points, (0.5, 0.8], 6 points, (0.8, 1.0): 2 points;

[0192] The hole diameter score, hole depth score and hole roundness score are used to calculate the defect score of the defect of the hole defect type:

[0193] U2=g1+g2+g3

[0194] Wherein U2 refers to the defect score of the defect of the hole defect type, g1 refers to the hole diameter score, g2 refers to the hole depth score, and g3 refers to the hole roundness score.

[0195] If the defect type is a rust defect, the rust area, rust depth and texture complexity of the rust defect are obtained, wherein the texture complexity includes: smooth, rough and extremely rough.

[0196] The rust area, rust depth and texture complexity are substituted into preset rust area standard, rust depth standard and texture complexity standard to obtain rust area score, rust depth score and texture complexity score, wherein the rust area standard is: (0, 5] cm 2 : 2 points, (5, 10] cm 2 : 6 points, (10, +∞) cm 2 : 10 points, the rust depth standard is: (0, 1] mm: 2 points, (1, 4] mm: 6 points, (4, +∞) mm: 10 points, and the texture complexity standard is: smooth: 2 points, rough: 6 points, and extremely rough: 10 points.

[0197] The rust area score, rust depth score and texture complexity score are used to calculate the defect score of the defect of the rust defect type:

[0198] U3=k1+k2+k3

[0199] Wherein U3 refers to the defect score of the defect of the rust defect type, k1 refers to the rust area score, k2 refers to the rust depth score, and k3 refers to the texture complexity score.

[0200] It can be understood that the crack area refers to the area of the crack defect, the crack depth refers to the depth of the crack defect, the crack length refers to the length of the crack defect, the crack area standard refers to the standard for scoring the crack area, the crack depth standard refers to the standard for scoring the crack depth, the crack length standard refers to the standard for scoring the crack length, the crack area score refers to the score obtained by scoring the crack area using the crack area standard, the crack depth score refers to the score obtained by scoring the crack depth using the crack depth standard, and the crack length score refers to the score obtained by scoring the crack length using the crack length standard.

[0201] It can be understood that the hole diameter refers to the diameter of the hole defect, the hole depth refers to the depth of the hole defect, the hole roundness refers to the roundness of the hole defect, the hole diameter standard refers to the standard for scoring the hole diameter, the hole depth standard refers to the standard for scoring the hole depth, the hole roundness standard refers to the standard for scoring the hole roundness, the hole diameter score refers to the score obtained by scoring the hole diameter using the hole diameter standard, the hole depth score refers to the score obtained by scoring the hole depth using the hole depth standard, and the hole roundness score refers to the score obtained by scoring the hole roundness using the hole roundness standard.

[0202] It can be understood that the rust area refers to the area of the rust defect, the rust depth refers to the depth of the rust defect, the texture complexity refers to the roughness of the surface texture of the rust defect, the rust area standard refers to the standard for scoring the rust area, the rust depth standard refers to the standard for scoring the rust depth, the texture complexity standard refers to the standard for scoring the texture complexity, the rust area score refers to the score obtained by scoring the rust area using the rust area standard, the rust depth score refers to the score obtained by scoring the rust area using the rust depth standard, and the texture complexity score refers to the score obtained by scoring the texture complexity using the texture complexity standard.

[0203] S11, determine whether the fuzzy boundary is extracted.

[0204] If the fuzzy boundary extraction is not complete, return to the step of sequentially extracting the fuzzy boundary in the fuzzy boundary set.

[0205] If the fuzzy boundary extraction is complete, perform S12, aggregate the defect scores to obtain a defect score set, and calculate a comprehensive defect score based on the defect score set.

[0206] It can be understood that the defect score set refers to a collection of defect scores of all defect boundaries, and the comprehensive defect score refers to a score calculated based on the defect scores of all defect boundaries for comprehensive evaluation of the scrap recycling steel.

[0207] In detail, the calculation of the comprehensive defect score based on the defect score set comprises:

[0208] The defect score set is divided into a crack score set, a hole score set and a rust score set based on the defect category, and the crack score set, the hole score set and the rust score set are used to obtain a crack score number, a hole score number, a rust score number, a crack score, a hole score and a rust score;

[0209] A crack score weight, a hole score weight and a rust score weight are obtained, and a comprehensive defect score is calculated based on the crack score number, the hole score number, the rust score number, the crack score, the hole score, the rust score, the crack score weight, the hole score weight and the rust score weight:

[0210]

[0211] Wherein, U4 refers to the comprehensive defect score, l1 refers to the crack score weight, f refers to the crack score number, h α refers to the alpha-th crack score, l2 refers to the hole score weight, t refers to the hole score number, c β refers to the beta-th hole score, l3 refers to the rust score weight, o refers to the rust score number, j γ refers to the gamma-th rust score.

[0212] The crack score set refers to a set of defect scores in which all defect categories in the defect score set are crack defects, the hole score set refers to a set of defect scores in which all defect categories in the defect score set are hole defects, the rust score set refers to a set of defect scores in which all defect categories in the defect score set are rust defects, the crack score number refers to the number of crack scores in the crack score set, the crack score refers to a defect score in which the defect category is a crack defect, the hole score number refers to the number of hole scores in the hole score set, the hole score refers to a defect score in which the defect category is a hole defect, the rust score number refers to the number of rust scores in the rust score set, the rust score refers to a defect score in which the defect category is a rust defect, the crack score weight refers to the influence degree of the rust score on the comprehensive defect score, the hole score weight refers to the influence degree of the hole score on the comprehensive defect score, and the rust score weight refers to the influence degree of the rust score on the comprehensive defect score.

[0213] S13, based on the preset score level and the comprehensive defect score, the waste and old recycling steel is evaluated and graded to obtain a graded recycling steel.

[0214] The score grade is: (0, 3] points: excellent grade, (3, 6] points: good grade, (6, 10] points: damage grade. The comprehensive defect score is substituted into the corresponding score grade to obtain graded recycling steel. The excellent grade of waste recycling steel has no obvious structural defects and can continue to be used. The good grade of waste recycling steel has slight defects and can be normally used after recycling and repairing. The damaged grade of waste recycling steel has serious defects and structural integrity is damaged and cannot be used continuously.

[0215] The present application solves the problems in the background art by combining score grade and comprehensive defect score to perform multi-step processing on the image of waste recycling steel, realizing automatic detection and evaluation of waste recycling steel. First, the image acquisition unit is used to perform automatic image acquisition on waste recycling steel. Automatic image acquisition can quickly and continuously acquire images of waste recycling steel, reducing the waste of manual work and ensuring that the real state of the surface of waste recycling steel can be captured in time, providing accurate image information for subsequent processing and improving the efficiency of overall detection and evaluation. Second, median filtering and binary preprocessing are performed on the collected image of recycling steel. Median filtering and binary processing can effectively remove background noise and highlight important features, making defects easier to observe in the image and making fuzzy marking and defect recognition more efficient, improving the accuracy and efficiency of detection. Then, fuzzy marking is performed on the preprocessed image using fuzzy marking method to obtain fuzzy boundary set. The fuzzy boundary set can help to more accurately define the defect area, improving the efficiency and accuracy of defect recognition. Further, fuzzy boundaries are extracted in the fuzzy boundary set, and whether the extracted fuzzy boundary is a defect boundary is judged using a defect threshold. When it is a defect boundary, the defect type of the defect boundary is judged based on the defect standard. Judging the defect type of the defect boundary can reduce subjective judgment and improve the reliability of subsequent defect score calculation. Then, the defect score of the defect boundary is calculated based on the defect type, and each defect is scored to quantify the severity of the defect, making the evaluation result more intuitive. Not only does it provide a data basis for evaluation grading, but it also reduces the error of human judgment. Then, when the fuzzy boundary extraction is completed, the defect scores are summarized to obtain a defect score set, and a comprehensive defect score is calculated based on the defect score set. Calculating the comprehensive defect score based on the defect score can make the quality status of waste recycling steel more clear and explicit, improving the evaluation efficiency. Finally, the waste recycling steel is evaluated and graded based on the score grade and the comprehensive defect score. According to the comprehensive defect score and the score grade, effective grading is performed to quickly evaluate the quality of waste recycling steel. This standardized evaluation process simplifies the operation process and makes the evaluation of waste recycling steel more efficient. Therefore, the present application can improve the detection and evaluation efficiency of waste recycling steel.

[0216] As Figure 2As shown is a functional module diagram of an automatic detection and evaluation system of waste recycled steel provided by an embodiment of the present application.

[0217] The automatic detection and evaluation system 100 of waste recycled steel can be installed in an electronic device. According to the functions to be implemented, the automatic detection and evaluation system 100 of waste recycled steel can include an image acquisition module 101, an image preprocessing module 102, a defect boundary judgment module 103, and a recycled steel grading module 104. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0218] The image acquisition module 101 is configured to receive a detection instruction, and start a pre-constructed image detection unit based on the detection instruction. The image detection unit includes an image acquisition unit, an image storage unit, and an image processing unit. The image acquisition unit is configured to perform automatic image acquisition on a pre-set waste recycled steel, obtain a recycled steel acquisition image, and generate an image storage instruction.

[0219] The image preprocessing module 102 is configured to receive the image storage instruction by using the image storage unit, store the recycled steel acquisition image in the image storage unit, and generate an image processing instruction. The image processing unit is configured to receive the image processing instruction and execute processing instruction analysis to obtain an instruction analysis result. Based on the instruction analysis result and the image processing unit, the recycled steel acquisition image is subjected to image preprocessing to obtain a preprocessed image. The image preprocessing includes median filtering and binarization.

[0220] The defect boundary judgment module 103 is configured to perform fuzzy labeling on the preprocessed image by using a pre-set fuzzy labeling method to obtain a fuzzy boundary set. The fuzzy boundaries in the fuzzy boundary set are extracted in sequence. A pre-set defect threshold is used to judge whether the fuzzy boundary is a pre-set defect boundary. If the fuzzy boundary is not a defect boundary, the step of extracting the fuzzy boundary in the fuzzy boundary set is returned. If the fuzzy boundary is a defect boundary, a pre-set defect standard is used to judge the defect type of the defect boundary. The defect type includes crack defects, hole defects, and rust defects.

[0221] The recycling steel grading module 104 is configured to calculate a defect score of the defect boundary based on the defect category, determine whether the fuzzy boundary extraction is completed, return to the step of sequentially extracting the fuzzy boundary from the fuzzy boundary set if the fuzzy boundary extraction is not completed, aggregate the defect scores to obtain a defect score set if the fuzzy boundary extraction is completed, calculate a comprehensive defect score based on the defect score set, and evaluate and grade the waste recycling steel based on a preset score level and the comprehensive defect score.

[0222] In detail, the modules in the automatic detection and evaluation system 100 for waste recycling steel in the embodiments of the present application use the same technical means as the automatic detection and evaluation method for waste recycling steel in the Figure 1 above, and can produce the same technical effects, which will not be described here.

[0223] As shown in Figure 3 , it is a structural schematic diagram of an electronic device for implementing the automatic detection and evaluation method for waste recycling steel according to an embodiment of the present application.

[0224] The electronic device 1 can include a processor 10, a memory 11 and a bus 12, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as an automatic detection and evaluation method for waste recycling steel program.

[0225] The memory 11 includes at least one type of readable storage medium, such as a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Further, the memory 11 includes an internal storage unit of the electronic device 1 and also includes an external storage device. The memory 11 can be used not only to store application software and various data installed on the electronic device 1, such as the code of the automatic detection and evaluation method for waste recycling steel program, but also to temporarily store data that has been output or will be output.

[0226] The processor 10 can be composed of integrated circuits in some embodiments, for example, can be composed of a single packaged integrated circuit, or can be composed of multiple packaged integrated circuits with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, etc. The processor 10 is the control core of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as the automatic detection and evaluation method of waste recycling steel), and calls data stored in the memory 11, to perform various functions and process data of the electronic device 1.

[0227] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11, the at least one processor 10, etc.

[0228] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0229] For example, although not shown, the electronic device 1 can also include a power supply (such as a battery) for powering various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so as to realize functions such as charge management, discharge management, and power consumption management through the power management device. The power supply can also include one or more direct current or alternating current power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0230] Further, the electronic device 1 can also include a network interface, which can optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is usually used to establish a communication connection between the electronic device 1 and other electronic devices.

[0231] Optionally, the electronic device 1 can also include a user interface, which can be a display, an input unit such as a keyboard, and optionally a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. Among them, the display can also be appropriately called a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display the visualized user interface.

[0232] The program of the automatic detection and evaluation method of waste recycling steel stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which can realize the following functions when running in the processor 10:

[0233] Receiving a detection instruction, based on the detection instruction, starting a pre-constructed image detection unit, wherein the image detection unit includes an image acquisition unit, an image storage unit and an image processing unit;

[0234] Using the image acquisition unit to perform automatic image acquisition on the preset waste recycling steel, obtaining the recycling steel acquisition image and generating an image storage instruction;

[0235] Using the image storage unit to receive the image storage instruction, storing the recycling steel acquisition image in the image storage unit and generating an image processing instruction;

[0236] Using the image processing unit to receive the image processing instruction and executing the processing instruction analysis, obtaining the instruction analysis result;

[0237] Based on the instruction analysis result and the image processing unit, performing image preprocessing on the recycling steel acquisition image to obtain a preprocessed image, wherein the image preprocessing is median filtering and binarization;

[0238] Using a preset fuzzy labeling method to perform fuzzy labeling on the preprocessed image to obtain a fuzzy boundary set;

[0239] Extracting fuzzy boundaries in the fuzzy boundary set in sequence;

[0240] Using a preset defect threshold to determine whether the fuzzy boundary is a preset defect boundary;

[0241] If the fuzzy boundary is not a defect boundary, return to the step of extracting fuzzy boundaries in the fuzzy boundary set in sequence;

[0242] If the fuzzy boundary is a defect boundary, the defect type of the defect boundary is determined based on a preset defect standard, wherein the defect type includes: crack defects, hole defects and corrosion defects.

[0243] Calculate the defect score for the defect boundary based on the defect type;

[0244] Determine whether the fuzzy boundary has been completely extracted;

[0245] If the extraction of the fuzzy boundaries is not completed, return to the steps described above for sequentially extracting fuzzy boundaries from the fuzzy boundary set.

[0246] Once the fuzzy boundaries have been extracted, the defect scores are summarized to obtain a defect score set, and a comprehensive defect score is calculated based on the defect score set.

[0247] The scrap recycled steel is evaluated and graded based on the preset rating levels and the comprehensive defect rating to obtain graded recycled steel.

[0248] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0249] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0250] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0251] Upon receiving a detection command, a pre-constructed image detection unit is activated based on the detection command. The image detection unit includes an image acquisition unit, an image storage unit, and an image processing unit.

[0252] The image acquisition unit is used to perform automated image acquisition on the preset scrap steel to obtain the image of the recycled steel and generate an image storage instruction.

[0253] The image storage unit receives the image storage instruction, stores the image of the recycled steel into the image storage unit, and generates an image processing instruction.

[0254] receiving the image processing instruction by the image processing unit and performing processing instruction analysis to obtain an instruction analysis result;

[0255] performing image preprocessing on the recycled steel collection image based on the instruction analysis result and the image processing unit to obtain a preprocessed image, wherein the image preprocessing is median filtering and binarization;

[0256] performing fuzzy marking on the preprocessed image using a preset fuzzy marking method to obtain a fuzzy boundary set;

[0257] extracting fuzzy boundaries in the fuzzy boundary set in sequence;

[0258] judging whether the fuzzy boundary is a preset defect boundary using a preset defect threshold;

[0259] if the fuzzy boundary is not a defect boundary, returning to the step of extracting fuzzy boundaries in the fuzzy boundary set in sequence;

[0260] if the fuzzy boundary is a defect boundary, judging a defect type of the defect boundary based on a preset defect standard, wherein the defect type includes a crack defect, a hole defect and a rust defect;

[0261] calculating a defect score of the defect boundary based on the defect type;

[0262] judging whether the fuzzy boundary extraction is completed;

[0263] if the fuzzy boundary extraction is not completed, returning to the step of extracting fuzzy boundaries in the fuzzy boundary set in sequence;

[0264] if the fuzzy boundary extraction is completed, summarizing the defect scores to obtain a defect score set, and calculating a comprehensive defect score based on the defect score set;

[0265] performing evaluation and grading on the waste recycled steel based on a preset score level and the comprehensive defect score to obtain graded recycled steel.

[0266] In several embodiments provided in the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the above-described system embodiments are only illustrative, and actual implementation can have another division way.

[0267] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs.

[0268] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0269] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be realized in other specific forms without departing from the spirit or essential characteristics of the present application.

[0270] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An automated detection and evaluation method for recycled scrap steel, characterized in that, The method comprises: receiving a detection instruction, and starting a pre-constructed image detection unit based on the detection instruction, wherein the image detection unit comprises an image acquisition unit, an image storage unit, and an image processing unit; using the image acquisition unit to perform automatic image acquisition on a preset waste recycling steel to obtain a recycling steel acquisition image and generate an image storage instruction; using the image storage unit to receive the image storage instruction, store the recycling steel acquisition image in the image storage unit, and generate an image processing instruction; using the image processing unit to receive the image processing instruction and perform processing instruction analysis to obtain an instruction analysis result; performing image preprocessing on the recycling steel acquisition image based on the instruction analysis result and the image processing unit to obtain a preprocessed image, wherein the image preprocessing comprises median filtering and binarization; using a preset fuzzy marking method to perform fuzzy marking on the preprocessed image to obtain a fuzzy boundary set; extracting fuzzy boundaries in the fuzzy boundary set in sequence; using a preset defect threshold to determine whether the fuzzy boundary is a preset defect boundary; if the fuzzy boundary is not a defect boundary, returning to the step of extracting fuzzy boundaries in the fuzzy boundary set in sequence; if the fuzzy boundary is a defect boundary, determining a defect type of the defect boundary based on a preset defect standard, wherein the defect type comprises a crack defect, a hole defect, and a rust defect; calculating a defect score of the defect boundary based on the defect type; determining whether the fuzzy boundary extraction is complete; if the fuzzy boundary extraction is not complete, returning to the step of extracting fuzzy boundaries in the fuzzy boundary set in sequence; if the fuzzy boundary extraction is complete, summarizing the defect scores to obtain a defect score set, and calculating a comprehensive defect score based on the defect score set; based on a preset score level and the comprehensive defect score, evaluating and grading the waste recycling steel to obtain a graded recycling steel.

2. The method of automated inspection and evaluation of scrap recycled steel of claim 1, wherein, The method comprises: using the image acquisition unit to perform 3s of continuous shooting on the waste recycling steel based on a shooting frequency of 5 pictures / s to obtain a recycling steel image set; based on the recycling steel image set, selecting two images with the highest clarity to obtain a first representative image and a second representative image; obtaining a first pixel value set of the first representative image and a second pixel value set of the second representative image; expanding the first pixel value set and the second pixel value set into one-dimensional arrays to obtain a first pixel array and a second pixel array; based on the first pixel array and the second pixel array, calculating an image similarity of the first representative image and the second representative image; determining whether the image similarity is greater than a preset similarity threshold; if the image similarity is greater than the similarity threshold, randomly selecting one of the first representative image and the second representative image as a recycling steel acquisition image, and generating an image storage instruction based on the recycling steel acquisition image; If the image similarity is not greater than a similarity threshold, the first representative image and the second representative image are taken as a recycled steel collection image, and an image storage instruction is generated based on the recycled steel collection image.

3. The method of automated inspection and evaluation of scrap recycled steel of claim 2, wherein, The image similarity of the first representative image and the second representative image is calculated based on the first pixel array and the second pixel array, including: The total number of pixels is obtained based on the first pixel array and the second pixel array, wherein the total number of pixels is the total number of pixels of the first pixel array or the total number of pixels of the second pixel array, and the total number of pixels of the first pixel array and the total number of pixels of the second pixel array are equal; The image similarity of the first representative image and the second representative image is calculated using the total number of pixels, the first pixel array and the second pixel array: ； wherein, refers to an image similarity, refers to a total number of pixels, refers to a first pixel value in the first pixel array, refers to a second pixel value in the second pixel array, refers to a second pixel value in the second pixel array, refers to a second pixel value in the second pixel array.

4. The method of automated inspection and evaluation of scrap recycled steel of claim 1, wherein, The image processing unit receives the image processing instruction and performs processing instruction analysis to obtain an instruction analysis result, including: The image processing unit includes a first image processing unit and a second image processing unit; The processing instruction analysis is as follows: The running load of the first image processing unit is calculated, and it is determined whether the running load is less than a preset running load threshold; If the running load is less than the running load threshold, the instruction analysis result is determined as inputting the recycled steel collection image into the first image processing unit; If the running load is equal to or greater than the running load threshold, the instruction analysis result is determined as inputting the recycled steel collection image into the second image processing unit, and after waiting for the running load to be less than the running load threshold, the recycled steel collection image is input into the first image collection unit.

5. The automated detection and evaluation method of scrap recycled steel as claimed in claim 4, wherein, The running load of the first image processing unit is calculated, including: The CPU usage, memory usage, bandwidth usage and IO rate of the first image processing unit are obtained; The CPU load weight, memory load weight, bandwidth load weight and IO load weight of the first image processing unit are obtained; The running load of the first image processing unit is calculated based on the CPU usage, memory usage, bandwidth usage, IO rate, CPU load weight, memory load weight, bandwidth load weight and IO load weight: ； wherein, refers to the running load of the first image processing unit, refers to the cpu load weight, refers to the cpu usage rate, refers to the memory load weight, refers to the memory usage amount, refers to the bandwidth load weight, refers to the bandwidth usage rate, refers to the IO load weight, refers to the IO rate.

6. The automated detection and evaluation method of scrap recycled steel as claimed in claim 1, wherein, The determination of whether the fuzzy boundary is a defect boundary based on a preset defect threshold includes: The total amount of fuzzy boundary pixel points of the fuzzy boundary and the pixel equivalent of the fuzzy boundary are obtained; The fuzzy boundary area of the fuzzy boundary is calculated based on the total amount of fuzzy boundary pixel points of the fuzzy boundary and the pixel equivalent of the fuzzy boundary: ； wherein, refers to the fuzzy boundary area, refers to the total amount of fuzzy boundary pixel points, refers to the pixel equivalent; It is determined whether the fuzzy boundary area is less than the defect threshold; If the fuzzy boundary area is less than the defect threshold, it is determined that the fuzzy boundary is not a defect boundary; If the fuzzy boundary area is not less than the defect threshold, it is determined that the fuzzy boundary is a defect boundary.

7. The automated detection and evaluation method of scrap recycled steel as claimed in claim 1, wherein, The determination of the defect type of the defect boundary based on a preset defect standard includes: The defect boundary area of the defect boundary is obtained, and it is determined whether the defect boundary area is less than a preset crack area threshold; If the defect boundary area is less than the crack area threshold, it is determined that the defect type of the defect boundary is a crack defect; If the defect boundary area is not less than the crack area threshold, a defect boundary roundness of the defect boundary is calculated; The calculation is as follows: A defect pixel point of the defect boundary, a total amount of defect pixel points, an abscissa of the defect pixel point, and an ordinate of the defect pixel point are obtained; using a preset calculating the defect boundary perimeter using the preset function, the defect pixel points of the defect boundary, the total amount of defect pixel points, the horizontal coordinates and the vertical coordinates of the defect pixel points ； wherein, refers to the defect boundary perimeter, refers to the total number of defect pixels, refers to a function, refers to the horizontal coordinate of the th defect pixel, refers to the vertical coordinate of the th defect pixel, refers to the horizontal coordinate of the th defect pixel, refers to the vertical coordinate of the th defect pixel; The defect boundary roundness is calculated as follows: ； wherein, refers to defect boundary circularity, refers to defect boundary area, refers to defect boundary perimeter, refers to pi; It is judged whether the defect boundary roundness of the defect boundary is less than a preset hole roundness threshold; If the defect boundary roundness of the defect boundary is not less than the hole roundness threshold, it is confirmed that the defect type of the defect boundary is a hole defect; If the defect boundary roundness of the defect boundary is less than the hole roundness threshold, it is confirmed that the defect type of the defect boundary is a rust defect.

8. The automated detection and evaluation method of scrap recycled steel as claimed in claim 1, wherein, The defect score of the defect boundary based on the defect type comprises: If the defect type is a crack defect, a crack area, a crack depth, and a crack length of the crack defect are obtained; The crack area, crack depth and crack length are substituted into preset crack area standards, crack depth standards and crack length standards respectively to obtain crack area scores, crack depth scores and crack length scores, wherein the crack area standards are: : 2 points, : 6 points, : 10 points, the crack depth standards are: : 2 points, : 6 points, : 10 points, and the crack length standards are: : 2 points, : 6 points, : 10 points. The defect score of the defect type being a crack defect is calculated by using the crack area score, the crack depth score, and the crack length score: ； wherein, defect score indicating a defect type is a crack defect, crack area score, crack depth score, crack length score; If the defect type is a hole defect, a hole diameter, a hole depth, and a hole roundness of the hole defect are obtained; The hole diameter, hole depth and hole roundness are substituted into preset hole diameter standard, hole depth standard and hole roundness standard to obtain hole diameter score, hole depth score and hole roundness score, wherein the hole diameter standard is: : 2 points, : 6 points, : 10 points, the hole depth standard is: : 2 points, : 6 points, : 10 points, and the hole roundness standard is: : 10 points, : 6 points, : 2 points. The defect score of the defect type being a hole defect is calculated by using the hole diameter score, the hole depth score, and the hole roundness score: ； wherein, a defect score indicating a defect type is a hole defect, a hole diameter score, a hole depth score, a hole roundness score; If the defect type is a rust defect, a rust area, a rust depth, and a texture complexity of the rust defect are obtained, wherein the texture complexity comprises smooth, rough, and extremely rough; The rust area, rust depth and texture complexity are substituted into preset rust area standards, rust depth standards and texture complexity standards to obtain rust area scores, rust depth scores and texture complexity scores, wherein the rust area standards are: : 2 points, : 6 points, : 10 points, the rust depth standards are: : 2 points, : 6 points, : 10 points, and the texture complexity standards are: smooth: 2 points, rough: 6 points, and extremely rough: 10 points. The defect score of the defect type being a rust defect is calculated by using the rust area score, the rust depth score, and the texture complexity score: ； wherein, a defect score indicating a type of defect is a rust defect, a rust area score, a rust depth score, a texture complexity score.

9. The automated detection and evaluation method of scrap recycled steel as claimed in claim 1, wherein, The comprehensive defect score is calculated based on the defect score set, comprising: The defect score set is divided into a crack score set, a hole score set, and a rust score set based on the defect type, and a crack score number, a hole score number, a rust score number, a crack score, a hole score, and a rust score are obtained by using the crack score set, the hole score set, and the rust score set; A crack score weight, a hole score weight, and a rust score weight are obtained, and the comprehensive defect score is calculated based on the crack score number, the hole score number, the rust score number, the crack score, the hole score, the rust score, the crack score weight, the hole score weight, and the rust score weight: ； wherein, refers to the comprehensive defect score, refers to the crack score weight, refers to the crack score number, refers to the th crack score, refers to the hole score weight, refers to the hole score number, refers to the th hole score, refers to the rust score weight, refers to the rust score number, refers to the th rust score.

10. An automated detection and evaluation system for scrap recycled steel, characterized in that, The system comprises: An image acquisition module is configured to receive a detection instruction, and start a pre-constructed image detection unit based on the detection instruction, wherein the image detection unit comprises an image acquisition unit, an image storage unit, and an image processing unit, and the image acquisition unit is configured to perform automatic image acquisition on a pre-set waste recycling steel to obtain a recycling steel acquisition image and generate an image storage instruction; An image preprocessing module is configured to receive the image storage instruction by using the image storage unit, store the recycling steel acquisition image in the image storage unit, and generate an image processing instruction, receive the image processing instruction by using the image processing unit, and perform processing instruction analysis to obtain an instruction analysis result, perform image preprocessing on the recycling steel acquisition image based on the instruction analysis result and the image processing unit, and obtain a preprocessed image, wherein the image preprocessing comprises median filtering and binarization. The defect boundary judgment module is configured to perform fuzzy marking on the preprocessed image by using a preset fuzzy marking method to obtain a fuzzy boundary set, sequentially extract fuzzy boundaries in the fuzzy boundary set, determine whether the fuzzy boundaries are preset defect boundaries by using a preset defect threshold, return to the step of sequentially extracting fuzzy boundaries in the fuzzy boundary set if the fuzzy boundaries are not defect boundaries, and determine a defect type of the defect boundaries based on a preset defect standard if the fuzzy boundaries are defect boundaries, wherein the defect type includes a crack defect, a hole defect, and a rust defect. The recycled steel grading module is configured to calculate defect scores of the defect boundaries based on the defect type, determine whether the fuzzy boundaries are extracted completely, return to the step of sequentially extracting fuzzy boundaries in the fuzzy boundary set if the fuzzy boundaries are not extracted completely, aggregate the defect scores to obtain a defect score set if the fuzzy boundaries are extracted completely, calculate a comprehensive defect score based on the defect score set, and evaluate and grade the waste recycled steel based on a preset score level and the comprehensive defect score.

Images