输送带跑偏检测方法研究

王锴; 曾祥进; 黎新; 张锐; 徐成

doi:10.13272/j.issn.1671-251x.2022050064

输送带跑偏检测方法研究

doi: 10.13272/j.issn.1671-251x.2022050064

王锴^{1, 2,},
曾祥进^{1, 2},
黎新^{1, 2},
张锐^{1, 2},
徐成^{1, 2}

1.
武汉工程大学计算机科学与工程学院, 湖北武汉　430205
2.
湖北三峡实验室, 湖北宜昌　445804

基金项目: 国家自然科学基金资助项目(61502355）；湖北省三峡实验室创新基金资助项目(SC215001)；武汉工程大学研究生教育创新基金资助项目（CX2021246）。

详细信息

作者简介:
王锴（1997—），男，山东菏泽人，硕士研究生，研究方向为图像处理和计算机视觉，E-mail：1181640871@qq.com

中图分类号: TD634
计量
- 文章访问数: 470
- HTML全文浏览量: 81
- PDF下载量: 53
- 被引次数: 0
出版历程
- 收稿日期: 2022-05-24
- 修回日期: 2023-03-15
- 网络出版日期: 2022-09-28

Research on conveyor belt deviation detection method

WANG Kai^{1, 2
,},
ZENG Xiangjin^{1, 2},
LI Xin^{1, 2},
ZHANG Rui^{1, 2},
XU Cheng^{1, 2}

1.
School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China
2.
Hubei Three Gorges Laboratory, Yichang 445804, China

摘要

摘要: 基于机器视觉的输送带跑偏检测方法检测的输送带边缘特征中包含伪边缘，现有研究难以识别伪边缘，且多场景适应性差。针对该问题，对输送带监控图像提取感兴趣区域（ROI）并进行归一化，采用较大阈值区间的Canny算法提取边缘特征点，以提高算法的场景适应性，并采用形态学滤波方法处理部分杂质及伪边缘；对于Canny算法无法检测到有效边缘的图像，对提取的ROI进行伽马变换和45，135° 方向的梯度滤波，以增强边缘特征，之后进行基于Canny算法的特征点提取和形态学滤波。以边缘点像素值关系、邻域特征、紧密性特征，以及边缘线长度、相对位置、斜率等作为约束条件，采用基于分治搜索思想的直线筛选排序算法对提取的边缘特征点进行筛选及拟合，得到输送带实时边缘。将实时边缘的像素值与未发生跑偏时边缘像素值做差，得到当前跑偏的像素值。试验结果表明，针对多种场景下的输送带监控图像，基于Canny算法和直线筛选排序的输送带跑偏检测方法检测误差小于3个像素值，百张图像检测时间为6.945 1 s，边缘计算机处理4路视频图像的CPU占有率为132%，满足现场输送带边缘检测的准确性、实时性要求。
- 带式输送机 /
- 跑偏检测 /
- 边缘检测 /
- 特征点排序 /
- 直线筛选 /
- 分治搜索
Abstract: The machine vision-based conveyor belt deviation detection methods detect conveyor belt edge features. The features contain false edges. The existing research is difficult to identify false edges and has poor adaptability to multiple scenes. To solve this problem, the region of interest (ROI) is extracted from the conveyor belt monitoring image and normalized. The Canny algorithm with a larger threshold range is used to extract edge feature points to improve the scene adaptability of the algorithm. Morphological filtering methods are used to deal with some impurities and false edges. For images where the Canny algorithm cannot detect effective edges, gamma transform and gradient filtering in the 45° and 135° directions are performed on the extracted ROI to enhance edge features. The feature point extraction and morphological filtering based on the Canny algorithm are carried out. The pixel value relationship of edge points, neighborhood features, compactness features, as well as the length, relative position, and slope of edge lines are taken as constraints. The line filtering and sorting algorithm based on the idea of divide and conquer search is used to filter and fit the extracted edge feature points to obtain a real-time edge of the conveyor belt. The pixel value of the real-time edge is subtracted from the pixel value of the edge when no deviation occurs, and the pixel value of the current deviation is obtained. The test results show that for the conveyor belt monitoring images under various scenes, the detection error of the conveyor belt deviation detection method based on the Canny algorithm and line filtering and sorting is less than three pixel values. The detection time of 100 images is 6.9451 s. The CPU occupancy of the edge computer processing four video images is 132%, which meets the accuracy and real-time requirements of on-site conveyor belt edge detection.
- belt conveyor /
- deviation detection /
- edge detection /
- sorting of feature points /
- line filtering /
- divide and conquer search

HTML全文

图 1 输送带跑偏检测流程

Figure 1. Flow of conveyor belt deviation detection

下载: 全尺寸图片幻灯片

图 2 输送带图像预处理结果

Figure 2. Pretreatment results of conveyor belt image

下载: 全尺寸图片幻灯片

图 3 输送带图像暗处理效果

Figure 3. Processing effect of conveyor belt image in dark environment

下载: 全尺寸图片幻灯片

图 4 直线筛选排序算法流程

Figure 4. Flow of line filtering and sorting algorithm

下载: 全尺寸图片幻灯片

图 5 直线筛选排序算法处理效果

Figure 5. Process effect of line filtering and sorting algorithm

下载: 全尺寸图片幻灯片

图 6 邻域点结构

Figure 6. Neighborhood point structure

下载: 全尺寸图片幻灯片

图 7 实际检测出的边缘点

Figure 7. Actual detected edge pointss

下载: 全尺寸图片幻灯片

图 8 分治搜索流程

Figure 8. Flow of divide and conquer search

下载: 全尺寸图片幻灯片

图 9 输送带跑偏检测像素偏移值可视化

Figure 9. Pixel offset value visualization of conveyor belt deviation detection

下载: 全尺寸图片幻灯片

图 10 输送带跑偏检测现场试验

Figure 10. Actual operating effect diagram

下载: 全尺寸图片幻灯片

表 1 输送带跑偏检测结果

Table 1. Conveyor belt deviation detection results

场景	检测正确数/张		检测准确率/%		漏检数/张	漏检率/%
场景	左边缘	右边缘	左边缘	右边缘	漏检数/张	漏检率/%
1	3 578	3 572	99.38	99.22	0	0
2	3 569	3 600	99.13	100	0	0
3	3 563	3 493	99.44	97.48	17	0.47
4	3 334	3 421	95.33	97.82	103	2.86
5	3 497	3 506	97.92	98.17	29	0.81
6	3 200	2 752	96.56	83.04	286	7.94

下载: 导出CSV

表 2 输送带跑偏检测算法运行时间

Table 2. Running time of conveyor belt deviation detection algorithm

图像数/张	1	10	100	1 000
时间/s	0.073 9	0.712 5	6.945 1	69.478 6

下载: 导出CSV

表 3 边缘计算机处理视频流的CPU占有率

Table 3. CPU occupancy of edge computer processing video flow

视频流/路	1	2	3	4
CPU占有率/%	52	81	106	132

下载: 导出CSV

表 4 输送带跑偏检测像素偏移值

Table 4. Pixel offset value of conveyor belt deviation detection

场景	实际像素偏移值		检测像素偏移值		像素差
场景	左边缘	右边缘	左边缘	右边缘	左边缘	右边缘
1	10	15	10	15	0	0
2	2	3	2	3	0	0
3	22	22	23	22	1	0
4	−30	−29	−32	−29	2	0
5	−18	−20	−19	−21	1	1
6	−20	−21	−19	−23	1	2

下载: 导出CSV

参考文献(21)

[1]	张波. 皮带运输机皮带跑偏原因及处理措施[J]. 科技创新与应用,2019(20):125-126. ZHANG Bo. Causes and treatment measures of belt deviation of belt conveyors[J]. Technology Innovation and Application,2019(20):125-126.
[2]	陈赟. 我国工业自动化行业产业链技术水平和差距分析及发展对策[J]. 科学发展,2022(10):30-36. CHEN Yun. Analysis of the current situation of China's industrial automation industry development and countermeasure suggestions[J]. Scientific Development,2022(10):30-36.
[3]	胡康. 皮带运输机皮带跑偏成因及解决办法[J]. 价值工程,2021,40(12):114-116. HU Kang. Causes and solutions of belt deviation of belt conveyor[J]. Value Engineering,2021,40(12):114-116.
[4]	杨京东,杜贤羿,李大伟,等. 基于矢量控制的带式输送机PMSM调制研究[J]. 山西煤炭,2022,42(4):107-115. YANG Jingdong,DU Xianyi,LI Dawei,et al. PMSM modulation study of belt conveyor based on vector control[J]. Shanxi Coal,2022,42(4):107-115.
[5]	薛金国. 带式输送机跑偏机理分析与纠偏方法研究[J]. 当代化工研究,2021(11):51-52. XUE Jinguo. Analysis of belt conveyor deviation mechanism and research on deviation correction method[J]. Modern Chemical Research,2021(11):51-52.
[6]	高文兵. 煤矿带式输送机常见故障分析及处理措施探究[J]. 机械管理开发,2022,37(11):323-324,327. GAO Wenbing. Analysis of common faults of coal mine belt conveyor and investigation of handling measures[J]. Mechanical Management and Development,2022,37(11):323-324,327.
[7]	杨林顺,董志勇. 基于图像处理的输送带跑偏故障在线检测技术研究[J]. 煤炭工程,2020,52(10):116-120. YANG Linshun,DONG Zhiyong. On-line detection of conveyor belt deviation fault based on image processing[J]. Coal Engineering,2020,52(10):116-120.
[8]	邹廷彪. 带式输送机皮带跑偏研究及液压自动纠偏装置设计[J]. 自动化应用,2015(11):16-17,42. ZOU Tingbiao. Research on belt deviation of belt conveyor and design of hydraulic automatic deviation correction device[J]. Automation Application,2015(11):16-17,42.
[9]	张菲菲, 崔亚辉, 于琛, 等.基于机器学习的钻井工况识别技术现状及发展[J/OL].长江大学学报(自然科学版):1-13[2022-03-17]. https://doi.org/10.16772/j.cnki.1673-1409.20230302.001. ZHANG Feifei, CUI Yahui, YU Chen,et al. Recent developments and future trends of drilling status recognition technology based on machine learning[J/OL]. Journal of Yangtze University(Natural Science Edition):1-13[2022-03-17]. https://doi.org/10.16772/j.cnki.1673-1409.20230302.001.
[10]	王文清,田柏林,冯海明,等. 基于激光测距矿用带式输送机多参数检测方法研究[J]. 煤炭科学技术,2020,48(8):131-138. WANG Wenqing,TIAN Bailin,FENG Haiming,et al. Research on multi-parameters detection method of mine belt conveyor based on laser ranging[J]. Coal Science and Technology,2020,48(8):131-138.
[11]	董锴文,孙彦景,陈岩,等. 矿山生产作业场景视频结构化分析关键技术[J]. 煤炭学报,2021,46(11):3724-3735. DONG Kaiwen,SUN Yanjing,CHEN Yan,et al. Key technology of video structured analysis in mine production operation scenario[J]. Journal of China Coal Society,2021,46(11):3724-3735.
[12]	常娜. 图像处理中的边缘检测算法研究综述[J]. 中国科技信息,2011(4):130-131,149. CHANG Na. A review of edge detection algorithms in image processing[J]. China Science and Technology Information,2011(4):130-131,149.
[13]	ZHANG Mengchao, SHI Hao, YU Yan, et al. A computer vision based conveyor deviation detection system[J]. Applied Sciences, 2020, 10（7）: 2402.
[14]	徐欢,李振璧,姜媛媛,等. 基于OpenCV的输送带跑偏自动检测算法研究[J]. 工矿自动化,2014,40(9):48-52. XU Huan,LI Zhenbi,JIANG Yuanyuan,et al. Research of automatic detection algorithm of conveying belt deviation based on OpenCV[J]. Industry and Mine Automation,2014,40(9):48-52.
[15]	王星,白尚旺,潘理虎,等. 基于计算机视觉的带式输送机跑偏监测[J]. 煤矿安全,2017,48(5):130-133. WANG Xing,BAI Shangwang,PAN Lihu,et al. Deviation monitoring of belt conveyor based on computer vision[J]. Safety in Coal Mines,2017,48(5):130-133.
[16]	谭恒,张红娟,靳宝全,等. 基于机器视觉的煤矿带式输送机跑偏检测方法[J]. 煤炭技术,2021,40(5):152-156. TAN Heng,ZHANG Hongjuan,JIN Baoquan,et al. Method for detecting deviation of coal mine belt conveyor based on machine vision[J]. Coal Technology,2021,40(5):152-156.
[17]	林俊,党伟超,潘理虎,等. 基于计算机视觉的井下输送带跑偏检测方法[J]. 煤矿机械,2019,40(10):169-171. LIN Jun,DANG Weichao,PAN Lihu,et al. Deviation monitoring method of underground conveyor belt based on computer vision[J]. Coal Mine Machinery,2019,40(10):169-171.
[18]	LIU Yi, MIAO Changyun, LI Xianguo, et al. Research on deviation detection of belt conveyor based on inspection robot and deep learning[J]. Complexity, 2021（3）: 1- 15.
[19]	吴丽. 基于机器视觉的煤炭带式输送机的智能监控方法[J]. 煤炭技术,2022,41(7):202-205. WU Li. Intelligent monitoring method of coal belt conveyor based on machine vision[J]. Coal Technology,2022,41(7):202-205.
[20]	刘涛. 煤矿井下带式输送机智能控制系统研究[J]. 现代工业经济和信息化,2022,12(11):323-324. LIU Tao. Research on intelligent control system of underground belt conveyor in a coal mine[J]. Modern Industrial Economy and Informationization,2022,12(11):323-324.
[21]	王春华. 机器视觉的带式输送机监控系统中输送带积水检测研究[D]. 天津: 天津工业大学, 2019. WANG Chunhua. Research on detection of water accumulation in conveyor belt monitoring system for machine vision[D]. Tianjin: Tianjin Polytechnic University, 2019.