CN117173185B - Method and device for detecting area of rolled plate, storage medium and computer equipment - Google Patents
Method and device for detecting area of rolled plate, storage medium and computer equipment Download PDFInfo
- Publication number
- CN117173185B CN117173185B CN202311453302.XA CN202311453302A CN117173185B CN 117173185 B CN117173185 B CN 117173185B CN 202311453302 A CN202311453302 A CN 202311453302A CN 117173185 B CN117173185 B CN 117173185B
- Authority
- CN
- China
- Prior art keywords
- image
- plate
- brightness
- detected
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 230000003044 adaptive effect Effects 0.000 claims abstract description 98
- 238000011156 evaluation Methods 0.000 claims abstract description 82
- 238000012545 processing Methods 0.000 claims abstract description 68
- 238000001514 detection method Methods 0.000 claims abstract description 60
- 239000000463 material Substances 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 17
- 238000003708 edge detection Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000005096 rolling process Methods 0.000 abstract description 20
- 238000010191 image analysis Methods 0.000 abstract description 2
- 229910000831 Steel Inorganic materials 0.000 description 22
- 239000010959 steel Substances 0.000 description 22
- 230000008569 process Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000428 dust Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010008 shearing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种轧制板材的区域检测方法及装置、存储介质、计算机设备，属于轧制图像分析技术领域，主要在于解决现有技术中采用固定阈值确定的板材区域误差大的问题，包括：获取包含轧制板材的边缘信息的待检测板材图像；评估待检测板材图像的亮度，得到亮度评估结果；若亮度评估结果不满足亮度要求，则采用图像增强处理得到满足亮度要求的目标亮度板材图像；若亮度评估结果满足亮度要求，则将待检测板材图像确定为目标亮度板材图像；提取目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；基于自适应阈值对待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定轧制板材的目标区域。
The invention discloses a method and device, storage medium and computer equipment for area detection of rolled plate. It belongs to the technical field of rolling image analysis and mainly aims to solve the problem of large area error of plate determined by fixed threshold in the prior art, including : Obtain the image of the plate to be detected that contains the edge information of the rolled plate; evaluate the brightness of the image of the plate to be detected, and obtain the brightness evaluation result; if the brightness evaluation result does not meet the brightness requirements, use image enhancement processing to obtain the target brightness plate that meets the brightness requirements. image; if the brightness evaluation result meets the brightness requirements, determine the plate image to be detected as the target brightness plate image; extract the contour line of the target brightness plate image, and determine the self-image corresponding to the plate image to be detected based on the contour pixel value Adaptive threshold; perform adaptive binarization processing on the image of the plate to be detected based on the adaptive threshold, and determine the target area of the rolling plate based on the adaptive binarization processing result.
Description
技术领域Technical field
本发明涉及轧制图像分析技术领域，特别是涉及一种轧制板材的区域检测方法及装置、存储介质、计算机设备。The present invention relates to the technical field of rolling image analysis, and in particular to a method and device for area detection of rolled plates, storage media, and computer equipment.
背景技术Background technique
随着钢铁工业的转型升级和智能化技术的快速发展，机器视觉技术由于其非接触、高效和高自动化的特点，已应用于自动剪切系统、平面形状控制技术以及镰刀弯实时监测等轧制工艺生产中。特别是在中厚板平面形状控制工艺中，通过对设置在轧机后的相机所拍摄的钢板头尾端照片进行图像处理，可以代替传统人工对头尾端切损区域的测量，提高效率和精确度，还能为后端智能分析提供大量实际数据。With the transformation and upgrading of the steel industry and the rapid development of intelligent technology, machine vision technology has been applied to automatic shearing systems, plane shape control technology, and real-time monitoring of sickle bends in rolling mills due to its non-contact, high efficiency and high automation characteristics. Process production in progress. Especially in the planar shape control process of medium and thick plates, by image processing the photos of the head and tail ends of the steel plates taken by the camera installed behind the rolling mill, it can replace the traditional manual measurement of the cut areas at the head and tail ends, improving efficiency and accuracy. , and can also provide a large amount of actual data for back-end intelligent analysis.
目前，在对轧制中的中厚板材进行图像处理时，采用人工经验设定的阈值提取钢板区域的像素点作为感兴趣区域，并剔除掉非钢板区域的像素点作为非感兴趣区域，为下一步钢板的轮廓识别打下基础。但是，在采集轧制钢板图像的过程中，由于不同道次的钢板温度不同，不同时间的车间光线明暗不同以及灰尘和电磁干扰等因素，均会使所拾取的图像受到影响。采用人工经验设定的固定阈值对所采集的所有钢板图像进行阈值处理，则无法准确提取每一张图像的钢板区域，必然会影响轮廓识别处理等后续工作。Currently, when performing image processing on rolling medium-thick plates, the threshold set by artificial experience is used to extract the pixels in the steel plate area as the area of interest, and the pixels in the non-steel plate area are eliminated as the non-interest area, as The next step is to lay the foundation for the contour recognition of steel plates. However, in the process of collecting images of rolling steel plates, factors such as different temperatures of steel plates in different passes, different light and shade in the workshop at different times, dust and electromagnetic interference, etc., will all affect the picked up images. If a fixed threshold set by manual experience is used to perform threshold processing on all collected steel plate images, the steel plate area of each image cannot be accurately extracted, which will inevitably affect subsequent work such as contour recognition processing.
发明内容Contents of the invention
有鉴于此，本发明提供一种轧制板材的区域检测方法及装置、存储介质、计算机设备，主要目的在于解决现有技术中采用固定阈值确定的板材区域误差大的问题。In view of this, the present invention provides an area detection method and device, storage medium, and computer equipment for rolled plate materials. The main purpose is to solve the problem of large error in plate area determination using fixed thresholds in the prior art.
依据本发明一个方面，提供了一种轧制板材的区域检测方法，包括：According to one aspect of the present invention, a method for area detection of rolled plates is provided, including:
获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；Obtain an image of the plate to be detected, where the image of the plate to be detected contains edge information of the rolled plate;
评估所述待检测板材图像的亮度，得到亮度评估结果；Evaluate the brightness of the image of the plate to be detected to obtain a brightness evaluation result;
若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像，并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；If the brightness evaluation result does not meet the brightness requirements, the plate image to be monitored is determined as the plate image to be enhanced, and image enhancement processing is performed on the plate image to be enhanced to obtain a target brightness plate image that meets the brightness requirements; if If the brightness evaluation result meets the brightness requirement, the plate image to be detected is directly determined as the target brightness plate image;
提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；Extract the contour line of the target brightness plate image, and determine an adaptive threshold corresponding to the plate image to be detected based on the contour pixel value;
基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域。The image of the plate material to be detected is subjected to adaptive binarization processing based on the adaptive threshold value, and the target area of the rolled plate material is determined based on the adaptive binarization processing result.
进一步的，所述评估所述待检测板材图像的亮度，得到亮度评估结果包括：Further, the evaluation of the brightness of the plate image to be detected and obtaining the brightness evaluation result includes:
计算所述待检测板材图像的所有像素点的像素平均值；Calculate the pixel average of all pixels of the plate image to be detected;
将所述像素平均值与亮度评估阈值作比较，若所述像素平均值小于所述亮度评估阈值，则将所述亮度评估结果确定为不满足亮度要求；若所述像素平均值大于等于所述亮度评估阈值，则将所述亮度评估结果确定为满足亮度要求。The pixel average value is compared with a brightness evaluation threshold. If the pixel average value is less than the brightness evaluation threshold, the brightness evaluation result is determined to not meet the brightness requirements; if the pixel average value is greater than or equal to the brightness evaluation threshold If the brightness evaluation threshold is determined, the brightness evaluation result is determined to meet the brightness requirements.
进一步的，所述评估所述待检测板材图像的亮度之前，所述方法还包括：Further, before evaluating the brightness of the plate image to be detected, the method further includes:
基于所述待检测板材图像中各个像素点的像素值对所述待检测板材图像进行去噪处理，得到去噪后图像，以使得基于所述去噪后图像进行亮度评估。The image of the plate to be detected is denoised based on the pixel value of each pixel in the image of the plate to be detected, and a denoised image is obtained, so that the brightness can be evaluated based on the denoised image.
进一步的，所述提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值包括：Further, extracting the contour line of the target brightness plate image and determining an adaptive threshold corresponding to the plate image to be detected based on the contour pixel value includes:
通过Canny边缘检测算法对所述目标亮度板材图像的所述边缘信息进行筛选处理，得到包含所述边缘信息的目标像素点；Use the Canny edge detection algorithm to filter the edge information of the target brightness plate image to obtain target pixels containing the edge information;
对所述目标像素点进行连续性检测，并基于连续性检测结果确定包含所述目标像素点最多且连续的轮廓线；Perform continuity detection on the target pixel points, and determine the most continuous contour line containing the target pixel points based on the continuity detection results;
获取所述轮廓线上所有像素点的轮廓线坐标值，并基于所述轮廓线坐标值从所述待检测板材图像中确定轮廓线像素值，并基于所述轮廓线像素值确定与所述待检测板材图像相对应的所述自适应阈值。Obtain the contour coordinate values of all pixel points on the contour line, determine the contour pixel value from the plate image to be detected based on the contour line coordinate value, and determine the contour line pixel value based on the contour line pixel value and the to-be-detected plate image. The adaptive threshold corresponding to the plate image is detected.
进一步的，所述对所述目标像素点进行连续性检测，并基于连续性检测结果确定包含所述目标像素点最多且连续的轮廓线包括：Further, the step of performing continuity detection on the target pixel points, and determining the most continuous contour lines containing the target pixel points based on the continuity detection results includes:
设置连续性检测区域，并任意获取一个所述目标像素点为所述连续性检测区域的中心像素点；Set a continuity detection area, and arbitrarily obtain one of the target pixels as the center pixel of the continuity detection area;
在所述中心像素点四周剩余区域内进行检测，若剩余区域内包含其余目标像素点，则将所述其余目标像素点和所述中心像素点确认为连续像素点；Detection is performed in the remaining area around the central pixel, and if the remaining area contains other target pixels, then the remaining target pixels and the central pixel are confirmed as continuous pixels;
基于所述连续像素点确定多条待确定轮廓线，并将包含像素点数量最多的所述待确定轮廓线确定为所述目标亮度板材图像的轮廓线。A plurality of contour lines to be determined are determined based on the continuous pixel points, and the contour line to be determined containing the largest number of pixel points is determined as the contour line of the target brightness plate image.
进一步的，所述基于所述轮廓线坐标值从所述待检测板材图像中确定轮廓线像素值，并基于所述轮廓线像素值确定所述自适应阈值包括：Further, determining the contour pixel value from the plate image to be detected based on the contour coordinate value, and determining the adaptive threshold based on the contour pixel value includes:
从所述待检测板材图像中确定与所述轮廓线坐标值相对应的轮廓线像素点，并将所述轮廓线像素点上的像素值确定为所述轮廓线像素值；Determine the contour pixel point corresponding to the contour line coordinate value from the plate material image to be detected, and determine the pixel value on the contour line pixel point as the contour line pixel value;
从所述轮廓线像素值中随机获取一个目标轮廓线像素值，并将所述目标轮廓线像素值确定为所述自适应阈值；或，Randomly obtain a target contour pixel value from the contour pixel value, and determine the target contour pixel value as the adaptive threshold; or,
对所有所述轮廓线像素值进行求平均，得到平均轮廓线像素值；并将所述平均轮廓线像素值确定为所述自适应阈值。All the contour pixel values are averaged to obtain an average contour pixel value; and the average contour pixel value is determined as the adaptive threshold.
进一步的，所述基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域包括：Further, the step of performing adaptive binarization processing on the image of the plate to be detected based on the adaptive threshold, and determining the target area of the rolled plate based on the adaptive binarization processing result includes:
获取所述待检测板材图像中的所有待处理像素值与所述自适应阈值进行比较；Obtain all pixel values to be processed in the plate image to be detected and compare them with the adaptive threshold;
若所述待处理像素值小于所述自适应阈值，则将对应的所述待处理像素值确定为0；If the pixel value to be processed is less than the adaptive threshold, the corresponding pixel value to be processed is determined to be 0;
若所述待处理像素值大于等于所述自适应阈值，则将对应的所述待处理像素值确定为255；If the pixel value to be processed is greater than or equal to the adaptive threshold, then the corresponding pixel value to be processed is determined to be 255;
将所述待检测板材图像中被所述自适应二值化处理后得到的白色区域确定为所述轧制板材的目标区域。The white area obtained by the adaptive binarization process in the image of the plate to be detected is determined as the target area of the rolled plate.
依据本发明另一个方面，提供了一种轧制板材的区域检测装置，包括：According to another aspect of the present invention, an area detection device for rolled plates is provided, including:
获取模块，用于获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；An acquisition module, used to acquire an image of the plate to be detected, where the image of the plate to be detected contains edge information of the rolled plate;
亮度评估模块，用于评估所述待检测板材图像的亮度，得到亮度评估结果；A brightness evaluation module, used to evaluate the brightness of the plate image to be detected and obtain a brightness evaluation result;
增强处理模块，用于若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像，并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；An enhancement processing module, configured to determine the image of the plate to be monitored as the image of the plate to be enhanced if the brightness evaluation result does not meet the brightness requirements, and perform image enhancement processing on the image of the plate to be enhanced to obtain an image that meets the brightness requirements. Target brightness plate image; if the brightness evaluation result meets the brightness requirement, then directly determine the plate image to be detected as the target brightness plate image;
阈值确定模块，用于提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；A threshold determination module configured to extract the contour line of the target brightness plate image, and determine an adaptive threshold corresponding to the plate image to be detected based on the contour pixel value;
区域确定模块，用于基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域。An area determination module, configured to perform adaptive binarization processing on the plate image to be detected based on the adaptive threshold, and determine the target area of the rolled plate based on the adaptive binarization processing result.
进一步的，所述亮度评估模块还用于：Further, the brightness evaluation module is also used to:
计算所述待检测板材图像的所有像素点的像素平均值；Calculate the pixel average of all pixels of the plate image to be detected;
将所述像素平均值与亮度评估阈值作比较，若所述像素平均值小于所述亮度评估阈值，则将亮度评估结果确定为不满足亮度要求；若所述像素平均值大于等于所述亮度评估阈值，则将所述亮度评估结果确定为满足亮度要求。Compare the pixel average value with a brightness evaluation threshold. If the pixel average value is less than the brightness evaluation threshold, the brightness evaluation result is determined to not meet the brightness requirements; if the pixel average value is greater than or equal to the brightness evaluation threshold threshold, the brightness evaluation result is determined to meet the brightness requirements.
进一步的，所述装置还包括去噪模块，用于基于所述待检测板材图像中各个像素点的像素值对所述待检测板材图像进行去噪处理，得到去噪后图像，以使得基于所述去噪后图像进行亮度评估。Further, the device further includes a denoising module for denoising the image of the plate to be detected based on the pixel value of each pixel point in the image of the plate to be detected, to obtain a denoised image, so that based on the The brightness of the denoised image was evaluated.
进一步的，所述阈值确定模块，包括：Further, the threshold determination module includes:
信息筛选单元， 用于通过Canny边缘检测算法对所述目标亮度板材图像的所述边缘信息进行筛选处理，得到包含所述边缘信息的目标像素点；An information screening unit, configured to screen the edge information of the target brightness plate image through a Canny edge detection algorithm to obtain target pixels containing the edge information;
连续性检测单元，用于对所述目标像素点进行连续性检测，并基于连续性检测结果确定包含所述目标像素点最多且连续的轮廓线；A continuity detection unit, configured to perform continuity detection on the target pixel points, and determine the most continuous contour lines containing the target pixel points based on the continuity detection results;
阈值确定单元，用于获取所述轮廓线上所有像素点的轮廓线坐标值，并基于所述轮廓线坐标值从所述待检测板材图像中确定轮廓线像素值，并基于所述轮廓线像素值确定与所述待检测板材图像相对应的所述自适应阈值。A threshold determination unit configured to obtain the contour coordinate values of all pixel points on the contour line, and determine the contour pixel value from the plate image to be detected based on the contour line coordinate value, and determine the contour line pixel value based on the contour line pixel The value determines the adaptive threshold corresponding to the plate image to be detected.
进一步的，所述连续性检测单元，还用于：Further, the continuity detection unit is also used for:
设置连续性检测区域，并任意获取一个所述目标像素点为所述连续性检测区域的中心像素点；Set a continuity detection area, and arbitrarily obtain one of the target pixels as the center pixel of the continuity detection area;
在所述中心像素点四周剩余区域内进行检测，若剩余区域内包含其余目标像素点，则将所述其余目标像素点和所述中心像素点确认为连续像素点；Detection is performed in the remaining area around the central pixel, and if the remaining area contains other target pixels, then the remaining target pixels and the central pixel are confirmed as continuous pixels;
基于所述连续像素点确定多条待确定轮廓线，并将包含像素点数量最多的所述待确定轮廓线确定为所述目标亮度板材图像的轮廓线。A plurality of contour lines to be determined are determined based on the continuous pixel points, and the contour line to be determined containing the largest number of pixel points is determined as the contour line of the target brightness plate image.
进一步的，所述阈值确定单元，还用于：Further, the threshold determination unit is also used to:
从所述待检测板材图像中确定与所述轮廓线坐标值相对应的轮廓线像素点，并将所述轮廓线像素点上的像素值确定为所述轮廓线像素值；Determine the contour pixel point corresponding to the contour line coordinate value from the plate material image to be detected, and determine the pixel value on the contour line pixel point as the contour line pixel value;
从所述轮廓线像素值中随机获取一个目标轮廓线像素值，并将所述目标轮廓线像素值确定为所述自适应阈值；或，Randomly obtain a target contour pixel value from the contour pixel value, and determine the target contour pixel value as the adaptive threshold; or,
对所有所述轮廓线像素值进行求平均，得到平均轮廓线像素值；并将所述平均轮廓线像素值确定为所述自适应阈值。All the contour pixel values are averaged to obtain an average contour pixel value; and the average contour pixel value is determined as the adaptive threshold.
进一步的，所述区域确定模块，还用于：Further, the area determination module is also used to:
获取所述待检测板材图像中的所有待处理像素值与所述自适应阈值进行比较；Obtain all pixel values to be processed in the plate image to be detected and compare them with the adaptive threshold;
若所述待处理像素值小于所述自适应阈值，则将对应的所述待处理像素值确定为0；If the pixel value to be processed is less than the adaptive threshold, the corresponding pixel value to be processed is determined to be 0;
若所述待处理像素值大于等于所述自适应阈值，则将对应的所述待处理像素值确定为255；If the pixel value to be processed is greater than or equal to the adaptive threshold, then the corresponding pixel value to be processed is determined to be 255;
将所述待检测板材图像中被所述自适应二值化处理后得到的白色区域确定为所述轧制板材的目标区域。The white area obtained by the adaptive binarization process in the image of the plate to be detected is determined as the target area of the rolled plate.
依据本发明的又一方面，提供了一种存储介质，所述存储介质中存储有至少一可执行指令，所述可执行指令使处理器执行如上述轧制板材的区域检测方法对应的操作。According to another aspect of the present invention, a storage medium is provided, and at least one executable instruction is stored in the storage medium. The executable instruction causes the processor to perform operations corresponding to the above-mentioned area detection method for rolled plate materials.
依据本发明另一个方面，提供了一种计算机设备，包括处理器、存储器、通信接口和通信总线，所述处理器、所述存储器和所述通信接口通过所述通信总线完成相互间的通信；According to another aspect of the present invention, a computer device is provided, including a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus;
所述存储器用于存放至少一可执行指令，所述可执行指令使所述处理器执行如上述轧制板材的区域检测方法对应的操作。The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the above-mentioned area detection method for rolled plate materials.
借由上述技术方案，本发明实施例提供的技术方案至少具有下列优点：Through the above technical solutions, the technical solutions provided by the embodiments of the present invention have at least the following advantages:
本发明提供了一种轧制板材的区域检测方法及装置、存储介质、计算机设备，与现有技术相比，本发明通过获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；评估所述待检测板材图像的亮度，得到亮度评估结果；若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像；并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域，实现了对不同亮度轧制板材图像的区域检测。本发明采用自适应阈值进行区域划分，避免了固定阈值划分区域时导致的无法划分或者误差大的问题，提高了轧制板材区域划分的自动化程度及可操控性。The present invention provides a method and device, storage media, and computer equipment for area detection of rolled plates. Compared with the existing technology, the present invention obtains an image of the plate to be detected, and the image of the plate to be detected includes the edge of the rolled plate. information; evaluate the brightness of the plate image to be detected, and obtain a brightness evaluation result; if the brightness evaluation result does not meet the brightness requirements, determine the plate image to be monitored as an image of the plate to be enhanced; and determine the plate image to be enhanced. The image is subjected to image enhancement processing to obtain a target brightness plate image that meets the brightness requirements; if the brightness evaluation result meets the brightness requirements, the plate image to be detected is directly determined as the target brightness plate image; the target is extracted Brighten the contour line of the plate image, and determine the adaptive threshold corresponding to the plate image to be detected based on the pixel value of the contour line; perform adaptive binarization processing on the plate image to be detected based on the adaptive threshold, and The target area of the rolling plate is determined based on the adaptive binarization processing result, thereby realizing the area detection of rolling plate images with different brightness. The present invention uses adaptive thresholds for area division, which avoids the problems of inability to divide or large errors caused by fixed thresholds for dividing areas, and improves the automation and controllability of rolling plate area division.
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。The above description is only an overview of the technical solution of the present invention. In order to have a clearer understanding of the technical means of the present invention, it can be implemented according to the content of the description, and in order to make the above and other objects, features and advantages of the present invention more obvious and understandable. , the specific embodiments of the present invention are listed below.
附图说明Description of the drawings
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本发明的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be construed as limiting the invention. Also throughout the drawings, the same reference characters are used to designate the same components. In the attached picture:
图1示出了本发明实施例提供的一种轧制板材的区域检测方法的流程示意图；Figure 1 shows a schematic flow chart of an area detection method for rolled plates provided by an embodiment of the present invention;
图2示出了本发明实施例提供的另一种轧制板材的区域检测方法的流程示意图；Figure 2 shows a schematic flow chart of another area detection method for rolled plates provided by an embodiment of the present invention;
图3示出了本发明实施例提供的三张不同轧制钢板采集的头端图像的灰度图；Figure 3 shows the grayscale images of three head-end images collected from different rolling steel plates provided by the embodiment of the present invention;
图4示出了本发明实施例提供的又一种轧制板材的区域检测方法的流程示意图；Figure 4 shows a schematic flow chart of yet another area detection method for rolled plates provided by an embodiment of the present invention;
图5示出了本发明实施例提供的经Canny边缘检测算法筛选处理得到的包含边缘信息的目标像素点示意图；Figure 5 shows a schematic diagram of target pixels containing edge information obtained through screening processing by the Canny edge detection algorithm provided by the embodiment of the present invention;
图6示出了本发明实施例提供的再一种轧制板材的区域检测方法的流程示意图；Figure 6 shows a schematic flow chart of yet another area detection method for rolled plates provided by an embodiment of the present invention;
图7示出了本发明实施例提供的经二值化处理后的图像；Figure 7 shows a binarized image provided by an embodiment of the present invention;
图8示出了本发明实施例提供的一种轧制板材的区域检测装置的结构示意图；Figure 8 shows a schematic structural diagram of an area detection device for rolled plates provided by an embodiment of the present invention;
图9示出了本发明实施例提供的一种计算机设备的结构示意图。FIG. 9 shows a schematic structural diagram of a computer device provided by an embodiment of the present invention.
具体实施方式Detailed ways
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that a thorough understanding of the disclosure will be provided, and the scope of the disclosure will be fully conveyed to those skilled in the art.
本发明实施例提供了一种轧制板材的区域检测方法，如图1所示，该方法包括：An embodiment of the present invention provides a method for area detection of rolled plates, as shown in Figure 1. The method includes:
101、获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；101. Obtain an image of the plate to be detected, where the image of the plate to be detected contains edge information of the rolled plate;
本发明实施例中，当前执行端获取待检测板材图像，其中，待检测板材图像包含轧制板材的边缘信息，如中厚钢板的头端拍摄照片包含中厚钢板的头端边缘信息，中厚钢板的尾端拍摄照片包含中厚钢板的尾端边缘信息等，本发明实施例不做具体限定。In the embodiment of the present invention, the current execution end obtains an image of the plate to be detected, where the image of the plate to be detected contains edge information of the rolled plate. For example, a photo taken of the head end of a medium-thick steel plate contains edge information of the head end of a medium-thick steel plate. The photos taken of the tail end of the steel plate include information on the tail end edge of the medium-thick steel plate, etc., which are not specifically limited in the embodiment of the present invention.
102、评估所述待检测板材图像的亮度，得到亮度评估结果；102. Evaluate the brightness of the image of the plate to be detected, and obtain the brightness evaluation result;
本发明实施例中，由于在轧制过程中，轧制道次数较少的钢板的实际温度较高，所采集的钢板图像较亮；轧制道次数较多的钢板的实际温度较低，所采集的钢板图像较暗。所以，当前执行端需要评估待检测板材图像的亮度，得到亮度评估结果，所述亮度评估结果包括满足亮度要求和不满足亮度要求两种。In the embodiment of the present invention, since during the rolling process, the actual temperature of the steel plate with fewer rolling passes is higher, the collected steel plate image is brighter; the actual temperature of the steel plate with more rolling passes is lower, so The collected image of the steel plate is darker. Therefore, the current execution end needs to evaluate the brightness of the image of the plate to be detected and obtain the brightness evaluation results. The brightness evaluation results include those that meet the brightness requirements and those that do not meet the brightness requirements.
103、若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像，并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；103. If the brightness evaluation result does not meet the brightness requirements, determine the plate image to be monitored as the plate image to be enhanced, and perform image enhancement processing on the plate image to be enhanced to obtain a target brightness plate image that meets the brightness requirements. ; If the brightness evaluation result meets the brightness requirement, the plate image to be detected is directly determined as the target brightness plate image;
本发明实施例中，当前执行端基于亮度评估结果确定不满足亮度要求的待检测板材图像，则需要进行图像增强处理，将不满足亮度要求的待检测板材图像确定为待增强板材图像。如果待检测板材图像的亮度满足亮度要求，则不需要进行图像增强处理，将待检测板材图像直接确定为目标亮度板材图像转至步骤104执行轮廓线提取等操作。当前执行端对待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像。本发明实施例中，图像增强处理可采用的方法包括Gamma图像增强处理，Gamma图像增强的特点是可以让较低灰度的像素点快速提高，而较高灰度的像素点则变化很小，来增大钢板区域像素值与背景区域像素值的梯度值。因此可以在不造成新干扰的情况下，对较暗的钢板图像进行明显提升。In the embodiment of the present invention, if the current execution end determines that the image of the plate to be detected does not meet the brightness requirements based on the brightness evaluation result, image enhancement processing needs to be performed to determine the image of the plate to be detected that does not meet the brightness requirements as the image of the plate to be enhanced. If the brightness of the plate image to be detected meets the brightness requirements, there is no need to perform image enhancement processing, and the image of the plate to be detected is directly determined as the target brightness plate image and the process goes to step 104 to perform operations such as contour line extraction. The current execution end performs image enhancement processing on the plate image to be enhanced, and obtains a target brightness plate image that meets the brightness requirements. In the embodiment of the present invention, the method that can be used for image enhancement processing includes Gamma image enhancement processing. The characteristic of Gamma image enhancement is that it can quickly improve the pixels of lower grayscale, while the pixels of higher grayscale will change very little. To increase the gradient value between the pixel value in the steel plate area and the pixel value in the background area. Darker steel plate images can thus be significantly improved without causing new interference.
104、提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；104. Extract the contour line of the target brightness plate image, and determine an adaptive threshold corresponding to the plate image to be detected based on the contour pixel value;
本发明实施例中，由于拍摄的待检测板材图像包括板材部分和背景部分，所以当前执行端需要根据两部分的边缘进行检测，提取目标亮度板材图像的轮廓线，再基于轮廓线确定与所述待检测板材图像相对应的自适应阈值。所述自适应阈值表征根据轮廓线的变化而变化的阈值，可以有效寻找到后期二值化处理的最优阈值，自动化程度高。In the embodiment of the present invention, since the photographed plate image to be detected includes a plate part and a background part, the current execution end needs to detect based on the edges of the two parts, extract the contour line of the target brightness plate image, and then determine the relationship between the plate image and the background part based on the contour line. Adaptive threshold corresponding to the plate image to be detected. The adaptive threshold represents a threshold that changes according to changes in the contour, and can effectively find the optimal threshold for later binarization processing, with a high degree of automation.
105、基于所述自适应阈值对所述待检测板材图像进行二值化处理，并基于二值化处理结果确定所述轧制板材的目标区域。105. Binarize the plate image to be detected based on the adaptive threshold, and determine the target area of the rolled plate based on the binarization result.
本发明实施例中，当前执行端基于与待检测板材图像相对应的自适应阈值对待检测板材图像进行二值化处理，所述二值化处理用于表征将图像中的每个像素转化为黑白两色的图像处理过程。经二值化处理后的图像更加简化，易于当前执行端进行区域检测。当前执行端基于二值化处理结果确定轧制板材的目标区域，如，当前执行端获取到黑白两色的二值化处理图像后，将黑色区域确定为背景区域，将白色区域确定为轧制板材的目标区域，本发明实施例不做具体限定。In the embodiment of the present invention, the current execution end performs binarization processing on the image of the plate to be detected based on the adaptive threshold corresponding to the image of the plate to be detected. The binary processing is used to represent each pixel in the image into black and white. Two-color image processing process. The image after binarization is more simplified and easier for the current execution end to perform area detection. The current execution end determines the target area of the rolling plate based on the binary processing result. For example, after the current execution end obtains the black and white binary processing image, it determines the black area as the background area and the white area as the rolling area. The target area of the plate is not specifically limited in the embodiment of the present invention.
进一步的，作为上述实施例具体实施方式的细化和扩展，为了快速且准确得确定出待增强板材图像，提供了另一种轧制板材的区域检测方法，该方法进一步限定了步骤“评估所述待检测板材图像的亮度，得到亮度评估结果”的内容，如图2所示，包括：Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to quickly and accurately determine the image of the plate to be enhanced, another area detection method of the rolled plate is provided, which method further defines the step of "evaluating the "Describe the brightness of the plate image to be detected and obtain the brightness evaluation results", as shown in Figure 2, including:
201、计算所述待检测板材图像的所有像素点的像素平均值；201. Calculate the pixel average of all pixels of the plate image to be detected;
本发明实施例中，当前执行端获取待检测板材图像上所有像素点的像素值，再计算得到像素平均值，本发明实施例中，选取了三张不同钢板采集的头端图像。经过灰度处理后，如图3所示，其中，（a）为灰度处理后待检测板材图像P1，（b）为灰度处理后待检测板材图像P2，（c）为灰度处理后待检测板材图像P3。对其中（a）、（b）、（c）三张图像上所有像素点的像素值求平均后，得到的像素平均值如下表1所示：In the embodiment of the present invention, the current execution end obtains the pixel values of all pixels on the plate image to be detected, and then calculates the average pixel value. In the embodiment of the present invention, three head-end images collected from different steel plates are selected. After grayscale processing, as shown in Figure 3, (a) is the image of the plate to be detected after grayscale processing P1, (b) is the image of the plate to be detected after grayscale processing P2, (c) is the image of the plate to be detected after grayscale processing Image P3 of the plate to be inspected. After averaging the pixel values of all pixels in the three images (a), (b), and (c), the obtained pixel average value is shown in Table 1 below:
表1 亮度评估表Table 1 Brightness evaluation table
202、将所述像素平均值与亮度评估阈值作比较，若所述像素平均值小于所述亮度评估阈值，则将所述亮度评估结果确定为不满足亮度要求；若所述像素平均值大于等于所述亮度评估阈值，则将所述亮度评估结果确定为满足亮度要求。202. Compare the pixel average value with the brightness evaluation threshold. If the pixel average value is less than the brightness evaluation threshold, determine the brightness evaluation result as not meeting the brightness requirements; if the pixel average value is greater than or equal to If the brightness evaluation threshold is determined, the brightness evaluation result is determined to meet the brightness requirements.
本发明实施例中，当前执行端将像素平均值与预设的亮度评估阈值作比较，如果像素平均值小于预设的亮度评估阈值，则将对应的待检测板材图像确定为待增强板材图像，如果像素平均值大于等于预设的亮度评估阈值，则直接对待检测板材图像进行轮廓线提取等操作。如，本发明实施例中预设的亮度评估阈值为50，基于亮度评估阈值50对表1中的图例P1、P2、P3的亮度进行评估，其中，P1和P2的像素平均值大于50，则P1和P2满足亮度要求，不需要进行图像增强处理，直接进入下一个步骤提取轮廓线；P3的像素平均值小于50，则P3不满足亮度要求，需要进行图像增强处理，将待检测板材图像P3确定为待增强板材图像。In the embodiment of the present invention, the current execution end compares the pixel average value with the preset brightness evaluation threshold. If the pixel average value is less than the preset brightness evaluation threshold, the corresponding plate image to be detected is determined as the plate image to be enhanced. If the average pixel value is greater than or equal to the preset brightness evaluation threshold, operations such as contour line extraction will be directly performed on the image of the plate to be detected. For example, the preset brightness evaluation threshold in the embodiment of the present invention is 50. Based on the brightness evaluation threshold 50, the brightness of the legends P1, P2, and P3 in Table 1 is evaluated. Among them, the average pixel value of P1 and P2 is greater than 50, then P1 and P2 meet the brightness requirements and do not need to perform image enhancement processing. They go directly to the next step to extract the contour lines. If the average pixel value of P3 is less than 50, then P3 does not meet the brightness requirements and needs to perform image enhancement processing. The plate image to be detected is P3. Determine it as the plate image to be enhanced.
需要说明的是，采集的待检测板材图像在进行亮度评估时可能还受到灰尘、水渍等表面污染物的影响，从而降低对待检测板材图像亮度的评估结果。本发明实施例中在步骤评估所述待检测板材图像的亮度之前，还包括：基于待检测板材图像中各个像素点的像素值对待检测板材图像进行去噪处理，得到去噪后图像，以使得基于所述去噪后图像进行亮度评估。如，遍历待检测板材图像所有像素点的像素值，剔除掉像素值小于10的像素点等，本发明实施例不做具体限定。It should be noted that the collected image of the plate to be inspected may also be affected by surface contaminants such as dust and water stains during brightness evaluation, thereby reducing the evaluation results of the brightness of the image of the plate to be inspected. In the embodiment of the present invention, before the step of evaluating the brightness of the image of the plate to be detected, it also includes: performing denoising processing on the image of the plate to be detected based on the pixel values of each pixel in the image of the plate to be detected, to obtain a denoised image, so that Brightness evaluation is performed based on the denoised image. For example, the pixel values of all pixels in the plate image to be detected are traversed, and pixels with a pixel value less than 10 are eliminated, etc. The embodiments of the present invention are not specifically limited.
进一步的，作为上述实施例具体实施方式的细化和扩展，为了针对不同的图像设置不同的阈值，提高板材区域划分的准确性，提供了另一种轧制板材的区域检测方法，该方法进一步限定了步骤“提取所述目标亮度板材图像的轮廓线，并基于所述轮廓线确定与所述待检测板材图像相对应的自适应阈值”的内容，如图4所示，包括：Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to set different thresholds for different images and improve the accuracy of plate area division, another area detection method for rolled plate is provided, which method further The content of the step "extracting the contour line of the target brightness plate image, and determining the adaptive threshold corresponding to the plate image to be detected based on the contour line" is defined, as shown in Figure 4, including:
301、通过Canny边缘检测算法对所述目标亮度板材图像的所述边缘信息进行筛选处理，得到包含所述边缘信息的目标像素点；301. Use the Canny edge detection algorithm to filter the edge information of the target brightness plate image to obtain target pixels containing the edge information;
本发明实施例中，当前执行端通过Canny边缘检测算法对目标亮度板材图像的所述边缘信息进行筛选处理，得到包含所述边缘信息的目标像素点。其中，Canny边缘检测算法分为以下五个步骤：1.高斯滤波；2.计算图像的梯度大小和梯度方向；3.非极大值抑制；4. 双阈值筛选边缘；5.连接边缘。本发明实施例中，采用Canny边缘检测算法对P1、P2和经图像增强处理后的P3进行边缘检测，Canny边缘检测的双阈值设置为67和32，得到的检测结果如图5所示，其中，（a）为采用Canny边缘检测算法进行边缘信息筛选后的P1，（b）为采用Canny边缘检测算法进行边缘信息筛选后的P2，（c）为采用Canny边缘检测算法进行边缘信息筛选后的P3，本发明实施例不做具体限定。图5中呈白色的亮点为通过Canny边缘检测算法筛选处理得到的包含边缘信息的目标像素点。In the embodiment of the present invention, the current execution end uses the Canny edge detection algorithm to filter the edge information of the target brightness plate image to obtain the target pixels containing the edge information. Among them, the Canny edge detection algorithm is divided into the following five steps: 1. Gaussian filtering; 2. Calculating the gradient size and gradient direction of the image; 3. Non-maximum suppression; 4. Double threshold filtering edges; 5. Connecting edges. In the embodiment of the present invention, the Canny edge detection algorithm is used to perform edge detection on P1, P2 and P3 after image enhancement processing. The dual thresholds of Canny edge detection are set to 67 and 32. The obtained detection results are shown in Figure 5, where , (a) is P1 after filtering edge information using Canny edge detection algorithm, (b) is P2 after filtering edge information using Canny edge detection algorithm, (c) is P2 after filtering edge information using Canny edge detection algorithm P3, the embodiment of the present invention is not specifically limited. The white bright spots in Figure 5 are target pixels containing edge information obtained through the Canny edge detection algorithm.
302、对所述目标像素点进行连续性检测，并基于连续性检测结果确定包含所述目标像素点最多且连续的轮廓线；302. Perform continuity detection on the target pixel points, and determine the continuous contour line containing the most target pixel points based on the continuity detection results;
本发明实施例中，当前执行端对目标像素点进行连续性检测，首先设置连续性检测区域，如将以九宫格形式的9个像素点区域设置为连续性检测区域，当前执行端任意获取一个目标像素点为连续性检测区域的中心像素点；然后，在中心像素点四周剩余区域内进行检测，若剩余区域内包含其余目标像素点，则将其余目标像素点和中心像素点确认为连续像素点；通过上述方法遍历所有的像素点，再基于连续像素点确定多条待确定轮廓线，但是这些并不都是钢板的轮廓线，当前执行端还需要将包含像素点数量最多的待确定轮廓线确定为目标亮度板材图像的轮廓线。In the embodiment of the present invention, the current execution end performs continuity detection on the target pixel points. First, the continuity detection area is set. For example, 9 pixel areas in the form of a nine-square grid are set as the continuity detection area. The current execution end arbitrarily acquires a target. The pixel is the center pixel of the continuity detection area; then, the remaining area around the central pixel is detected. If the remaining area contains other target pixels, the remaining target pixels and the central pixel are confirmed as continuous pixels. ; Traverse all pixels through the above method, and then determine multiple contours to be determined based on consecutive pixels. However, these are not all contours of the steel plate. The current execution end also needs to determine the contour line with the largest number of pixels. Determine the contour line of the plate image as the target brightness.
303、获取所述轮廓线上所有像素点的基于所述轮廓线坐标值从所述待检测板材图像中确定轮廓线像素值，并基于所述轮廓线像素值确定与所述待检测板材图像相对应的所述自适应阈值。303. Obtain the contour pixel values of all pixel points on the contour line based on the contour line coordinate values, determine the contour line pixel values from the plate material image to be detected, and determine the contour line pixel values corresponding to the plate material image to be detected based on the contour line pixel values. The corresponding adaptive threshold.
本发明实施例中，当前执行端获取轮廓线上所有像素点的轮廓线坐标值，由于图像增强处理后的目标亮度板材图像与原待检测板材图像各个像素点的坐标没有发生变化，则可以通过轮廓线的坐标值确定待检测板材图像中轮廓线的对应坐标。再从待检测板材图像中确定与轮廓线坐标值相对应的轮廓线像素点，并将轮廓线像素点上的像素值确定为轮廓线像素值。当前执行端再基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值，如从轮廓线像素值中随机获取一个目标轮廓线像素值，并将目标轮廓线像素值确定为相应图像的自适应阈值；或，对所有轮廓线像素值进行求平均，得到平均轮廓线像素值，并将平均轮廓线像素值确定为相应待检测板材图像的自适应阈值。本发明实施例中，将从待检测板材图像P1、待检测板材图像P2、待检测板材图像P3提取的轮廓线像素值中随机获取的一个目标轮廓线像素值确定为自适应阈值，如表2所示：In the embodiment of the present invention, the current execution end obtains the contour coordinate values of all pixel points on the contour line. Since the coordinates of each pixel point of the target brightness plate image after image enhancement processing and the original plate image to be detected have not changed, it can be obtained by The coordinate value of the contour line determines the corresponding coordinates of the contour line in the plate image to be detected. Then the contour pixel points corresponding to the contour line coordinate values are determined from the image of the plate to be detected, and the pixel values on the contour line pixel points are determined as the contour line pixel values. The current execution end then determines the adaptive threshold corresponding to the plate image to be detected based on the contour pixel value, such as randomly obtaining a target contour pixel value from the contour pixel value, and determining the target contour pixel value as the corresponding The adaptive threshold of the image; or, average all contour pixel values to obtain the average contour pixel value, and determine the average contour pixel value as the adaptive threshold of the corresponding plate image to be detected. In the embodiment of the present invention, a target contour pixel value randomly obtained from the contour pixel values extracted from the plate image P1, the plate image P2, and the plate image P3 is determined as the adaptive threshold, as shown in Table 2 Shown:
表2 自适应阈值Table 2 Adaptive threshold
如表2所示，每张待检测板材图像都对应一个自适应阈值，由于阈值不再固定，从而对每张待检测板材图像而言，确定的自适应阈值是最优的。As shown in Table 2, each plate image to be detected corresponds to an adaptive threshold. Since the threshold is no longer fixed, the determined adaptive threshold is optimal for each plate image to be detected.
进一步的，作为上述实施例具体实施方式的细化和扩展，为了使区域边缘更加的明确，便于后期进行自动剪切处理或计算切损率等操作，提供了另一种轧制板材的区域检测方法，该方法进一步限定了步骤“基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域”的内容，如图6所示，包括：Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to make the area edges clearer and facilitate later operations such as automatic shearing processing or calculation of cut loss rate, another area detection of rolled plates is provided. Method, which further defines the step of "performing adaptive binarization processing on the plate image to be detected based on the adaptive threshold, and determining the target area of the rolled plate based on the adaptive binarization processing result." The content, as shown in Figure 6, includes:
401、获取所述待检测板材图像中的所有待处理像素值与所述自适应阈值进行比较；401. Obtain all pixel values to be processed in the plate image to be detected and compare them with the adaptive threshold;
402、若所述待处理像素值小于所述自适应阈值，则将对应的所述待处理像素值确定为0；402. If the pixel value to be processed is less than the adaptive threshold, determine the corresponding pixel value to be processed as 0;
403、若所述待处理像素值大于等于所述自适应阈值，则将对应的所述待处理像素值确定为255；403. If the pixel value to be processed is greater than or equal to the adaptive threshold, determine the corresponding pixel value to be processed as 255;
404、将所述待检测板材图像中被所述自适应二值化处理后得到的白色区域确定为所述轧制板材的目标区域。404. Determine the white area obtained by the adaptive binarization process in the image of the plate to be detected as the target area of the rolled plate.
本本发明实施例中，当前执行端获取待检测板材图像中所有待处理像素值，并将获取的待处理像素值与自适应阈值进行比较。如果待处理像素值小于自适应阈值，则将对应的所述待处理像素值确定为0（即二值化处理成黑色）；如果待处理像素值大于等于自适应阈值，则将对应的待处理像素值确定为255（即二值化处理成白色）。本发明实施例中，对待检测板材图像P1、待检测板材图像P2、待检测板材图像P3进行二值化处理后的图像如图7所示。在二值化处理完成后，当前执行端将待检测板材图像中被自适应二值化处理后得到的白色区域确定为轧制板材的目标区域。In the embodiment of the present invention, the current execution end obtains all pixel values to be processed in the image of the plate to be detected, and compares the obtained pixel values to be processed with the adaptive threshold. If the pixel value to be processed is less than the adaptive threshold, the corresponding pixel value to be processed is determined to be 0 (that is, binarized into black); if the pixel value to be processed is greater than or equal to the adaptive threshold, the corresponding pixel value to be processed is The pixel value is determined to be 255 (that is, binarized to white). In the embodiment of the present invention, the images of the plate material to be detected P1, the plate material image P2 to be detected, and the plate material image P3 to be detected are binarized as shown in Figure 7. After the binarization process is completed, the current execution end determines the white area obtained by the adaptive binarization process in the image of the plate to be detected as the target area of the rolling plate.
本发明实施例提供了一种轧制板材的区域检测方法，与现有技术相比，本发明通过获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；评估所述待检测板材图像的亮度，得到亮度评估结果；若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像；并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域，实现了对不同亮度轧制板材图像的区域检测。本发明采用自适应阈值进行区域划分，避免了固定阈值划分区域时导致的无法划分或者误差大的问题，提高了轧制板材区域划分的自动化程度及可操控性。Embodiments of the present invention provide a method for area detection of rolled plates. Compared with the existing technology, the present invention obtains an image of the plate to be detected, and the image of the plate to be detected contains edge information of the rolled plate; and evaluates the image of the plate to be detected. Detect the brightness of the plate image to obtain the brightness evaluation result; if the brightness evaluation result does not meet the brightness requirements, determine the plate image to be monitored as the plate image to be enhanced; and perform image enhancement processing on the plate image to be enhanced, Obtain a target brightness plate image that meets the brightness requirements; if the brightness evaluation result meets the brightness requirements, directly determine the plate image to be detected as the target brightness plate image; extract the contour line of the target brightness plate image , and determine the adaptive threshold corresponding to the plate image to be detected based on the contour pixel value; perform adaptive binarization processing on the plate image to be detected based on the adaptive threshold, and perform adaptive binarization based on the adaptive threshold The processing result determines the target area of the rolled plate, realizing area detection of images of rolled plates with different brightness. The present invention uses adaptive thresholds for area division, which avoids the problems of inability to divide or large errors caused by fixed thresholds for dividing areas, and improves the automation and controllability of rolling plate area division.
作为对上述图1所示方法的实现，本发明实施例提供了一种轧制板材的区域检测装置，如图8所示，该装置包括：As an implementation of the method shown in Figure 1 above, an embodiment of the present invention provides an area detection device for rolled plates, as shown in Figure 8, the device includes:
获取模块51，用于获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；The acquisition module 51 is used to acquire an image of the plate to be detected, where the image of the plate to be detected contains edge information of the rolled plate;
亮度评估模块52，用于评估所述待检测板材图像的亮度，得到亮度评估结果；The brightness evaluation module 52 is used to evaluate the brightness of the plate image to be detected and obtain the brightness evaluation result;
增强处理模块53，用于若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像，并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；The enhancement processing module 53 is used to determine the plate image to be monitored as the plate image to be enhanced if the brightness evaluation result does not meet the brightness requirements, and perform image enhancement processing on the plate image to be enhanced to obtain a result that meets the brightness requirements. The target brightness plate image; if the brightness evaluation result meets the brightness requirement, then the plate image to be detected is directly determined as the target brightness plate image;
阈值确定模块54，用于提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；A threshold determination module 54, configured to extract the contour line of the target brightness plate image, and determine an adaptive threshold corresponding to the plate image to be detected based on the contour pixel value;
区域确定模块55，用于基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域。The area determination module 55 is configured to perform adaptive binarization processing on the plate image to be detected based on the adaptive threshold, and determine the target area of the rolling plate based on the adaptive binarization processing result.
进一步的，所述亮度评估模块52还用于：Further, the brightness evaluation module 52 is also used to:
计算所述待检测板材图像的所有像素点的像素平均值；Calculate the pixel average of all pixels of the plate image to be detected;
将所述像素平均值与亮度评估阈值作比较，若所述像素平均值小于所述亮度评估阈值，则将所述亮度评估结果确定为不满足亮度要求；若所述像素平均值大于等于所述亮度评估阈值，则将所述亮度评估结果确定为满足亮度要求。The pixel average value is compared with a brightness evaluation threshold. If the pixel average value is less than the brightness evaluation threshold, the brightness evaluation result is determined to not meet the brightness requirements; if the pixel average value is greater than or equal to the brightness evaluation threshold If the brightness evaluation threshold is determined, the brightness evaluation result is determined to meet the brightness requirements.
进一步的，所述装置还包括去噪模块，用于基于所述待检测板材图像中各个像素点的像素值对所述待检测板材图像进行去噪处理，得到去噪后图像，以使得基于所述去噪后图像进行亮度评估。Further, the device further includes a denoising module for denoising the image of the plate to be detected based on the pixel value of each pixel point in the image of the plate to be detected, to obtain a denoised image, so that based on the The brightness of the denoised image was evaluated.
进一步的，所述阈值确定模块54，包括：Further, the threshold determination module 54 includes:
信息筛选单元， 用于通过Canny边缘检测算法对所述目标亮度板材图像的所述边缘信息进行筛选处理，得到包含所述边缘信息的目标像素点；An information screening unit, configured to screen the edge information of the target brightness plate image through a Canny edge detection algorithm to obtain target pixels containing the edge information;
连续性检测单元，用于对所述目标像素点进行连续性检测，并基于连续性检测结果确定包含所述目标像素点最多且连续的轮廓线；A continuity detection unit, configured to perform continuity detection on the target pixel points, and determine the most continuous contour lines containing the target pixel points based on the continuity detection results;
阈值确定单元，用于获取所述轮廓线上所有像素点的轮廓线坐标值，并基于所述轮廓线坐标值从所述待检测板材图像中确定轮廓线像素值，并基于所述轮廓线像素值确定与所述待检测板材图像相对应的所述自适应阈值。A threshold determination unit configured to obtain the contour coordinate values of all pixel points on the contour line, and determine the contour pixel value from the plate image to be detected based on the contour line coordinate value, and determine the contour line pixel value based on the contour line pixel The value determines the adaptive threshold corresponding to the plate image to be detected.
进一步的，所述连续性检测单元，还用于：Further, the continuity detection unit is also used for:
设置连续性检测区域，并任意获取一个所述目标像素点为所述连续性检测区域的中心像素点；Set a continuity detection area, and arbitrarily obtain one of the target pixels as the center pixel of the continuity detection area;
在所述中心像素点四周剩余区域内进行检测，若剩余区域内包含其余目标像素点，则将所述其余目标像素点和所述中心像素点确认为连续像素点；Detection is performed in the remaining area around the central pixel, and if the remaining area contains other target pixels, then the remaining target pixels and the central pixel are confirmed as continuous pixels;
基于所述连续像素点确定多条待确定轮廓线，并将包含像素点数量最多的所述待确定轮廓线确定为所述目标亮度板材图像的轮廓线。A plurality of contour lines to be determined are determined based on the continuous pixel points, and the contour line to be determined containing the largest number of pixel points is determined as the contour line of the target brightness plate image.
进一步的，所述阈值确定单元，还用于：Further, the threshold determination unit is also used to:
从所述待检测板材图像中确定与所述轮廓线坐标值相对应的轮廓线像素点，并将所述轮廓线像素点上的像素值确定为所述轮廓线像素值；Determine the contour pixel point corresponding to the contour line coordinate value from the plate material image to be detected, and determine the pixel value on the contour line pixel point as the contour line pixel value;
从所述轮廓线像素值中随机获取一个目标轮廓线像素值，并将所述目标轮廓线像素值确定为所述自适应阈值；或，Randomly obtain a target contour pixel value from the contour pixel value, and determine the target contour pixel value as the adaptive threshold; or,
对所有所述轮廓线像素值进行求平均，得到平均轮廓线像素值；并将所述平均轮廓线像素值确定为所述自适应阈值。All the contour pixel values are averaged to obtain an average contour pixel value; and the average contour pixel value is determined as the adaptive threshold.
进一步的，所述区域确定模块55，还用于：Further, the area determination module 55 is also used to:
获取所述待检测板材图像中的所有待处理像素值与所述自适应阈值进行比较；Obtain all pixel values to be processed in the plate image to be detected and compare them with the adaptive threshold;
若所述待处理像素值小于所述自适应阈值，则将对应的所述待处理像素值确定为0；If the pixel value to be processed is less than the adaptive threshold, the corresponding pixel value to be processed is determined to be 0;
若所述待处理像素值大于等于所述自适应阈值，则将对应的所述待处理像素值确定为255；If the pixel value to be processed is greater than or equal to the adaptive threshold, then the corresponding pixel value to be processed is determined to be 255;
将所述待检测板材图像中被所述自适应二值化处理后得到的白色区域确定为所述轧制板材的目标区域。The white area obtained by the adaptive binarization process in the image of the plate to be detected is determined as the target area of the rolled plate.
本发明实施例提供了一种轧制板材的区域检测装置，与现有技术相比，本发明通过获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；评估所述待检测板材图像的亮度，得到亮度评估结果；若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像；并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域，实现了对不同亮度轧制板材图像的区域检测。本发明采用自适应阈值进行区域划分，避免了固定阈值划分区域时导致的无法划分或者误差大的问题，提高了轧制板材区域划分的自动化程度及可操控性。Embodiments of the present invention provide an area detection device for rolled plates. Compared with the existing technology, the present invention obtains an image of a plate to be detected, and the image of the plate to be detected contains edge information of a rolled plate; and evaluates the image of the plate to be detected. Detect the brightness of the plate image to obtain the brightness evaluation result; if the brightness evaluation result does not meet the brightness requirements, determine the plate image to be monitored as the plate image to be enhanced; and perform image enhancement processing on the plate image to be enhanced, Obtain a target brightness plate image that meets the brightness requirements; if the brightness evaluation result meets the brightness requirements, directly determine the plate image to be detected as the target brightness plate image; extract the contour line of the target brightness plate image , and determine the adaptive threshold corresponding to the plate image to be detected based on the contour pixel value; perform adaptive binarization processing on the plate image to be detected based on the adaptive threshold, and perform adaptive binarization based on the adaptive threshold The processing result determines the target area of the rolled plate, realizing area detection of images of rolled plates with different brightness. The present invention uses adaptive thresholds for area division, which avoids the problems of inability to divide or large errors caused by fixed thresholds for dividing areas, and improves the automation and controllability of rolling plate area division.
根据本发明一个实施例提供了一种存储介质，所述存储介质存储有至少一可执行指令，该计算机可执行指令可执行上述任意方法实施例中的轧制板材的区域检测方法。According to an embodiment of the present invention, a storage medium is provided. The storage medium stores at least one executable instruction. The computer executable instruction can execute the area detection method for rolled plate in any of the above method embodiments.
图9示出了根据本发明一个实施例提供的一种计算机设备的结构示意图，本发明具体实施例并不对计算机设备的具体实现做限定。Figure 9 shows a schematic structural diagram of a computer device according to an embodiment of the present invention. The specific embodiment of the present invention does not limit the specific implementation of the computer device.
如图9所示，该计算机设备可以包括：处理器(processor)602、通信接口(Communications Interface)604、存储器(memory)606、以及通信总线608。As shown in Figure 9, the computer device may include: a processor (processor) 602, a communications interface (Communications Interface) 604, a memory (memory) 606, and a communication bus 608.
其中：处理器602、通信接口604、以及存储器606通过通信总线608完成相互间的通信。Among them: the processor 602, the communication interface 604, and the memory 606 complete communication with each other through the communication bus 608.
通信接口604，用于与其它设备比如客户端或其它服务器等的网元通信。The communication interface 604 is used to communicate with network elements of other devices such as clients or other servers.
处理器602，用于执行程序610，具体可以执行上述轧制板材的区域检测方法的相关步骤。The processor 602 is configured to execute the program 610. Specifically, it can execute the relevant steps of the above-mentioned area detection method for rolled plate materials.
具体地，程序610可以包括程序代码，该程序代码包括计算机操作指令。Specifically, program 610 may include program code including computer operating instructions.
处理器602可能是中央处理器CPU，或者是特定集成电路ASIC（ApplicationSpecific Integrated Circuit），或者是被配置成实施本发明实施例的一个或多个集成电路。计算机设备包括的一个或多个处理器，可以是同一类型的处理器，如一个或多个CPU；也可以是不同类型的处理器，如一个或多个CPU以及一个或多个ASIC。The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the computer device may be the same type of processor, such as one or more CPUs; or they may be different types of processors, such as one or more CPUs and one or more ASICs.
存储器606，用于存放程序610。存储器606可能包含高速RAM存储器，也可能还包括非易失性存储器（non-volatile memory），例如至少一个磁盘存储器。Memory 606 is used to store program 610. The memory 606 may include high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
程序610具体可以用于使得处理器602执行以下操作：The program 610 may be specifically used to cause the processor 602 to perform the following operations:
获取待检测板材图像，所述待检测板材图像包含轧制板材的边缘信息；Obtain an image of the plate to be detected, where the image of the plate to be detected contains edge information of the rolled plate;
评估所述待检测板材图像的亮度，得到亮度评估结果；Evaluate the brightness of the image of the plate to be detected to obtain a brightness evaluation result;
若所述亮度评估结果不满足亮度要求，则将所述待监测板材图像确定为待增强板材图像，并对所述待增强板材图像进行图像增强处理，得到满足亮度要求的目标亮度板材图像；若所述亮度评估结果满足所述亮度要求，则将所述待检测板材图像直接确定为所述目标亮度板材图像；If the brightness evaluation result does not meet the brightness requirements, the plate image to be monitored is determined as the plate image to be enhanced, and image enhancement processing is performed on the plate image to be enhanced to obtain a target brightness plate image that meets the brightness requirements; if If the brightness evaluation result meets the brightness requirement, the plate image to be detected is directly determined as the target brightness plate image;
提取所述目标亮度板材图像的轮廓线，并基于轮廓线像素值确定与所述待检测板材图像相对应的自适应阈值；Extract the contour line of the target brightness plate image, and determine an adaptive threshold corresponding to the plate image to be detected based on the contour pixel value;
基于所述自适应阈值对所述待检测板材图像进行自适应二值化处理，并基于自适应二值化处理结果确定所述轧制板材的目标区域。The image of the plate material to be detected is subjected to adaptive binarization processing based on the adaptive threshold value, and the target area of the rolled plate material is determined based on the adaptive binarization processing result.
显然，本领域的技术人员应该明白，上述的本发明的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件结合。Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented using general-purpose computing devices. They can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices. , optionally, they may be implemented in program code executable by a computing device, such that they may be stored in a storage device for execution by the computing device, and in some cases, may be in a sequence different from that herein. The steps shown or described are performed either individually as individual integrated circuit modules, or as multiple modules or steps among them as a single integrated circuit module. As such, the invention is not limited to any specific combination of hardware and software.
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包括在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311453302.XA CN117173185B (en) | 2023-11-03 | 2023-11-03 | Method and device for detecting area of rolled plate, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311453302.XA CN117173185B (en) | 2023-11-03 | 2023-11-03 | Method and device for detecting area of rolled plate, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117173185A CN117173185A (en) | 2023-12-05 |
| CN117173185B true CN117173185B (en) | 2024-01-19 |
Family
ID=88938015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311453302.XA Active CN117173185B (en) | 2023-11-03 | 2023-11-03 | Method and device for detecting area of rolled plate, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117173185B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385753A (en) * | 2011-11-17 | 2012-03-21 | 江苏大学 | Illumination-classification-based adaptive image segmentation method |
| CN102541063A (en) * | 2012-03-26 | 2012-07-04 | 重庆邮电大学 | Line tracking control method and line tracking control device for micro intelligent automobiles |
| CN112419207A (en) * | 2020-11-17 | 2021-02-26 | 苏宁金融科技(南京)有限公司 | Image correction method, device and system |
| CN113688811A (en) * | 2021-10-26 | 2021-11-23 | 北京美摄网络科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| WO2023029467A1 (en) * | 2021-08-31 | 2023-03-09 | 上海商汤智能科技有限公司 | Method and apparatus for vehicle light detection, electronic device, and storage medium |
| WO2023179122A1 (en) * | 2022-03-23 | 2023-09-28 | 广东利元亨智能装备股份有限公司 | Defect detection method and apparatus, electronic device, and readable storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2293247B1 (en) * | 2009-07-29 | 2012-09-05 | Harman Becker Automotive Systems GmbH | Edge detection with adaptive threshold |
| KR101929560B1 (en) * | 2013-01-29 | 2019-03-14 | 삼성전자주식회사 | Method and apparatus for detecting edge in image |
| CN104077773A (en) * | 2014-06-23 | 2014-10-01 | 北京京东方视讯科技有限公司 | Image edge detection method, and image target identification method and device |
| CN112330688A (en) * | 2020-11-02 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Image processing method and device based on artificial intelligence and computer equipment |
-
2023
- 2023-11-03 CN CN202311453302.XA patent/CN117173185B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385753A (en) * | 2011-11-17 | 2012-03-21 | 江苏大学 | Illumination-classification-based adaptive image segmentation method |
| CN102541063A (en) * | 2012-03-26 | 2012-07-04 | 重庆邮电大学 | Line tracking control method and line tracking control device for micro intelligent automobiles |
| CN112419207A (en) * | 2020-11-17 | 2021-02-26 | 苏宁金融科技(南京)有限公司 | Image correction method, device and system |
| WO2023029467A1 (en) * | 2021-08-31 | 2023-03-09 | 上海商汤智能科技有限公司 | Method and apparatus for vehicle light detection, electronic device, and storage medium |
| CN113688811A (en) * | 2021-10-26 | 2021-11-23 | 北京美摄网络科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| WO2023179122A1 (en) * | 2022-03-23 | 2023-09-28 | 广东利元亨智能装备股份有限公司 | Defect detection method and apparatus, electronic device, and readable storage medium |
Non-Patent Citations (5)
| Title |
|---|
| Object detection in underwater image by detecting edges using adaptive thresholding;Akshita Saini etc.;IEEE Xplore;全文 * |
| 中厚板轧制过程高精度智能化控制系统的研发进展与应用;矫志杰等;轧钢;第39卷(第06期);全文 * |
| 基于目标边缘的图像二值化方法研究;郑浩等;计量技术(第04期);全文 * |
| 基于视觉的卡钳毛刺检测和定位方法研究;韩进宇;吴超群;;数字制造科学(第04期);全文 * |
| 视频序列中运动目标检测算法;胡晓辉;关山;;计算机工程与应用(第16期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117173185A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113646801B (en) | Defect detection method, device and computer readable storage medium for defect image | |
| CN109242853B (en) | An intelligent detection method for PCB defects based on image processing | |
| CN110321933B (en) | Fault identification method and device based on deep learning | |
| CN111598897B (en) | Infrared image segmentation method based on Otsu and improved Bernsen | |
| CN115908415B (en) | Edge-based defect detection method, device, equipment and storage medium | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN113971681B (en) | A belt conveyor edge detection method in complex environment | |
| CN113766209A (en) | Camera offset processing method and device | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN117152165B (en) | Photosensitive chip defect detection method and device, storage medium and electronic equipment | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN112529853A (en) | Method and device for detecting damage of netting of underwater aquaculture net cage | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN107993219A (en) | A kind of deck of boat detection method of surface flaw based on machine vision | |
| CN113516619B (en) | Product surface flaw identification method based on image processing technology | |
| CN113012157A (en) | Visual detection method and system for equipment defects | |
| CN118275449A (en) | Copper strip surface defect detection method, device and equipment | |
| CN115587966A (en) | A method and system for detecting whether parts are missing or not under the condition of uneven illumination | |
| CN116843687A (en) | Communication optical cable surface flaw detection method and device | |
| CN113284154A (en) | Steel coil end face image segmentation method and device and electronic equipment | |
| CN110738656B (en) | Definition evaluation method of certificate photo, storage medium and processor | |
| CN117173185B (en) | Method and device for detecting area of rolled plate, storage medium and computer equipment | |
| CN117911419A (en) | Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment | |
| CN116342589B (en) | Cross-field scratch defect continuity detection method and system | |
| CN108416790A (en) | A detection method for workpiece breakage rate |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |