Design of foreign object recognition and positioning system for sorting robot of coal mine belt conveyor
-
摘要: 机器视觉已在煤矿带式输送机分拣机器人目标检测与识别方面具有一定的理论基础，但目前煤矿带式输送机分拣机器人目标识别主要针对煤矸石识别，对造成输送带穿透、撕裂等的异物目标识别的研究较少，且在目标异物精确定位方面的研究也较少。针对上述问题，设计了一种基于机器视觉的煤矿带式输送机分拣机器人异物识别与定位系统，可对输送带上存在的不同类型和不同形状的异物进行识别与定位。采用双目视觉实时获取输送带上异物图像信息，并对图像进行预处理，基于Canny算子进行图像信息增强，通过灰度拉伸方法改进图像边缘信息，突出煤矿带式输送机上异物的边缘特征；利用形态学方法提取异物形状特征，建立异物图像特征样本库，通过图像特征匹配的方式解算出异物存在区域，实现异物类型的检测、分类与识别；在异物类型成功识别的基础上，以目标异物边缘特征值为基础，建立目标异物的感兴趣区域（ROI），构建相机、输送带与目标异物坐标转换关系，利用多目标质心快速计算方法求取目标异物质心坐标，实现对目标异物的定位。系统样机实验结果表明：煤矿带式输送机分拣机器人异物识别与定位系统异物识别率不受尺寸、材质和颜色等因素影响，能够实现输送带目标异物图像的采集、处理、特征提取、识别和位置定位，识别率为92.5 %以上，目标异物位置定位平均误差为3%左右。Abstract: Machine vision has a certain theoretical basis in target detection and recognition for sorting robot of coal mine belt conveyor. But current target recognition of sorting robot of coal mine belt conveyor is mainly aimed at coal-gangue recognition. There are few kinds of research on the recognition of foreign object targets causing conveyor belt penetration and tearing, and also few kinds of research on the precise positioning of target foreign object. In order to solve the above problems, a foreign object recognition and positioning system based on machine vision for sorting robots of coal mine belt conveyor is designed. The system can recognize and position different types and shapes of foreign objects on the conveyor belt. The image information of the foreign objects on the conveyor belt in real-time is obtained by adopting binocular vision, and the image is preprocessed. Image information is enhanced based on the Canny operator. The gray stretching method is used to improve image edge information to highlight the edge features of foreign objects on coal mine belt conveyor. The morphological method is used to extract foreign object shape features, and establish foreign object image feature sample library. The image feature matching method is used to solve the existing area of foreign objects to realize the detection, classification and recognition of foreign objects. On the basis of the successful recognition of foreign object type, the region of interest (ROI) of the target foreign object is established based on the edge feature value of the target foreign object. The coordinate conversion relationship is built between the camera, conveyor belt and target foreign object. The fast multi-target centroid calculation method is used to obtain the centroid coordinate of the target foreign object, so as to realize the positioning of the target foreign object. The experimental result of the system prototype shows that the foreign object recognition rate of foreign object recognition and positioning system for sorting robot of coal mine belt conveyor is not affected by the size, material, color and other factors, the system can realize the image acquisition, process, feature extraction, recognition and positioning of the target foreign object of coal mine conveyor belt. The recognition rate is above 92.5%, and the average error of the target foreign object positioning is about 3%.
-
图 1 煤矿带式输送机分拣机器人系统样机
Figure 1. Prototype of sorting robot system of coal mine belt conveyor
图 2 煤矿带式输送机分拣机器人异物识别与定位系统界面
Figure 2. Interface of foreign object recognition and positioning system for sorting robot of coal mine belt conveyor
图 3 煤矿带式输送机分拣机器人异物识别和定位方法架构
Figure 3. Architecture of foreign object recognition and positioning method for sorting robots of coal mine belt conveyor
图 8 目标异物坐标信息、目标异物类别信息、输送带实时图像和目标识别提取图像等系统程序
Figure 8. System programs such as target foreign object coordinate information, target foreign object category information, real-time image of conveyor belt and target recognition and extraction image
图 9 煤矿带式输送机分拣机器人异物识别与定位实验
Figure 9. Foreign object recognition and positioning experiment of sorting robot of coal mine belt conveyor
表 1 输送带上的异物类别
Table 1. Types of foreign objects on conveyor belt
序号 异物 序号 异物 序号 异物 1 木 8 铁背板 15 道钉/道木 2 （半）圆木 9 竹芭/塑芭 16 道夹板 3 锚杆/锚索 10 工字钢头 17 风带条 4 铁丝 11 钻头/杆 18 钢丝绳 5 编织袋 12 输送带头/卡 19 塑料瓶/袋 6 棉纱 13 脚线 20 盖板 7 螺栓、螺帽 14 雷管 21 水/水煤 
下载: 导出CSV
表 2 实验平台主要性能参数
Table 2. Main performance parameters of the experimental platform
序号 核心部件 主要参数 1 双目视觉 视角：对角线视角为121°；水平方向视角为105°；
垂直方向视角为58°焦距/mm： 2.45 深度工作距离/m： 0.32~7 同步精度/ms： ＜0.01 帧率/（帧·s−1）： 60 分辨率： 2 560×720 像素尺寸/μm： 3.75×3.75 2 机械臂 最大伸展距离/mm： 320 重复定位精度/mm： 0.2 抓取范围/mm： 310 抓取效率/%： ＞95 3 输送带 长度/mm： 600 速度/(mm·s−1)： 120
下载: 导出CSV
表 3 异物图像识别结果
Table 3. Foreign object image recognition results
样本类别 样本数 正确识别样本数 识别率/% 杆状异物 30 28 93.33
下载: 导出CSV
表 4 不同长度的杆状目标异物图像识别结果
Table 4. Rod-shaped target foreign object image recognition results for different lengths
长度/cm 实验次数 成功识别次数 识别率/% 3 40 39 97.5 5 40 37 92.5 7 40 38 95.0
下载: 导出CSV
表 5 不同直径的杆状目标异物图像识别结果
Table 5. Rod-shaped target foreign object image recognition results for different diameters
直径/mm 实验次数 成功识别次数 识别率/% 15 40 38 95.0 10 40 37 92.5 5 40 38 95.0
下载: 导出CSV
表 6 目标异物质心位置坐标解算实验结果
Table 6. Experimental results for solving the coordinates of the target foreign object's centre of mass position
目标异物 x0/mm ${x}_{0}'$/mm 相对误差/% y0/mm ${y}_{0}'$/mm 相对误差/% 1 60 59.784 9 0.36 63 62.928 3 0.11 2 58 57.016 9 1.70 50 51.235 7 2.47 3 48 46.269 7 3.60 65 63.852 8 1.76 4 55 52.932 5 3.76 59 56.740 9 3.83 5 50 46.337 7 7.32 61 61.080 3 0.13 6 56 56.598 0 1.07 61 61.858 5 1.41 7 50 48.676 0 2.65 64 63.497 5 0.79 8 58 59.072 5 1.85 54 55.921 9 3.56 9 48 46.701 1 2.71 55 54.869 2 0.24 10 43 40.729 2 5.28 53 50.847 2 4.06 11 44 45.499 7 3.41 59 57.838 9 1.97 12 58 59.908 9 3.29 62 63.018 7 1.64 13 43 44.003 9 2.33 59 62.768 5 6.39 14 47 48.606 1 3.42 54 57.232 8 5.99 15 49 48.010 2 2.02 65 61.735 9 5.02 16 53 52.759 7 0.45 58 55.509 9 4.29 17 59 57.437 4 2.65 57 54.312 7 4.71 18 59 58.117 0 1.50 57 59.562 6 4.50 19 47 45.203 4 3.82 55 51.423 4 6.50 20 42 41.205 4 1.89 58 55.304 4 4.65
下载: 导出CSV
-
[1] 刘峰. 对煤矿智能化发展的认识和思考[J]. 中国煤炭工业,2020(8):5-9. doi: 10.3969/j.issn.1673-9612.2020.08.002LIU Feng. Understanding and thinking on intelligent development of coal mine[J]. China Coal Industry,2020(8):5-9. doi: 10.3969/j.issn.1673-9612.2020.08.002 [2] 葛世荣. 煤矿机器人现状及发展方向[J]. 中国煤炭,2019,45(7):18-27. doi: 10.3969/j.issn.1006-530X.2019.07.004GE Shirong. Present situation and development direction of coal mine robots[J]. China Coal,2019,45(7):18-27. doi: 10.3969/j.issn.1006-530X.2019.07.004 [3] 文灵,谢元媛. 利用机器视觉远程监测煤矿带式输送机故障[J]. 能源与环保,2022,44(7):201-205.WEN Ling,XIE Yuanyuan. Remote monitoring of faults of coal mine belt conveyor by machine vision[J]. China Energy and Environmental Protection,2022,44(7):201-205. [4] 刘莉莉,苗长云. 基于机器视觉的带式输送机带速检测方法的研究[J]. 仪表技术与传感器,2020(7):118-121,126. doi: 10.3969/j.issn.1002-1841.2020.07.024LIU Lili,MIAO Changyun. Research on belt conveyor speed detection based on machine vision[J]. Instrument Technique and Sensor,2020(7):118-121,126. doi: 10.3969/j.issn.1002-1841.2020.07.024 [5] 杨春雨,顾振,张鑫,等. 基于深度学习的带式输送机煤流量双目视觉测量[J]. 仪器仪表学报,2021,41(8):164-174. doi: 10.19650/j.cnki.cjsi.J2107842YANG Chunyu,GU Zhen,ZHANG Xin,et al. Binocular vision measurement of coal flow of belt conveyors based on deep learning[J]. Chinese Journal of Scientific Instrument,2021,41(8):164-174. doi: 10.19650/j.cnki.cjsi.J2107842 [6] 陈晓晶. 井工煤矿运输系统智能化技术现状及发展趋势[J]. 工矿自动化,2022,48(6):6-14, 35. doi: 10.13272/j.issn.1671-251x.17933CHEN Xiaojing. Current status and development trend of intelligent technology of underground coal mine transportation system[J]. Journal of Mine Automation,2022,48(6):6-14, 35. doi: 10.13272/j.issn.1671-251x.17933 [7] 王志星,乔铁柱. 带式输送机胶带纵向撕裂双目视觉在线检测系统研究与设计[J]. 中国煤炭,2018,44(4):87-90, 105. doi: 10.3969/j.issn.1006-530X.2018.04.016WANG Zhixing,QIAO Tiezhu. Study and design on binocular vision online monitoring system of conveyor belt longitudinal tearing[J]. China Coal,2018,44(4):87-90, 105. doi: 10.3969/j.issn.1006-530X.2018.04.016 [8] 王燕,郭潇樯,刘新华. 带式输送机大块异物视觉检测系统设计[J]. 机械科学与技术,2021,40(12):1939-1943. doi: 10.13433/j.cnki.1003-8728.20200284WANG Yan,GUO Xiaoqiang,LIU Xinhua. Design of visual detection system for large foreign body in belt conveyor[J]. Mechanical Science and Technology for Aerospace Engineering,2021,40(12):1939-1943. doi: 10.13433/j.cnki.1003-8728.20200284 [9] 苗长云,陈雯. 基于机器视觉和支持向量机的带式输送机矸石检测方法[J]. 天津工业大学学报,2022,41(1):60-65. doi: 10.3969/j.issn.1671-024x.2022.01.010MIAO Changyun,CHEN Wen. A method for detecting gangue of belt conveyor based on machine vision and support vector machine[J]. Journal of Tiangong University,2022,41(1):60-65. doi: 10.3969/j.issn.1671-024x.2022.01.010 [10] 杜京义,陈瑞,郝乐,等. 煤矿带式输送机异物检测[J]. 工矿自动化,2021,47(8):77-83. doi: 10.13272/j.issn.1671-251x.2021040026DU Jingyi,CHEN Rui,HAO Le,et al. Coal mine belt conveyor foreign object detection[J]. Industry and Mine Automation,2021,47(8):77-83. doi: 10.13272/j.issn.1671-251x.2021040026 [11] 胡璟皓,高妍,张红娟,等. 基于深度学习的带式输送机非煤异物识别方法[J]. 工矿自动化,2021,47(6):57-62,90.HU Jinghao,GAO Yan,ZHANG Hongjuan,et al. Research on the identification method of non-coal foreign object of belt conveyor based on deep learning[J]. Industry and Mine Automation,2021,47(6):57-62,90. [12] 吴守鹏,丁恩杰,俞啸. 基于改进FPN的输送带异物识别方法[J]. 煤矿安全,2019,50(12):127-130.WU Shoupeng,DING Enjie,YU Xiao. Foreign body identification of belt based on improved FPN[J]. Safety in Coal Mines,2019,50(12):127-130. [13] 马宏伟,孙那新,张烨,等. 煤矸石分拣机器人动态目标稳定抓取轨迹规划[J]. 工矿自动化,2022,48(4):20-30. doi: 10.13272/j.issn.1671-251x.2021110050MA Hongwei,SUN Naxin,ZHANG Ye,et al. Track planning of coal gangue sorting robot for dynamic target stable grasping[J]. Journal of Mine Automation,2022,48(4):20-30. doi: 10.13272/j.issn.1671-251x.2021110050 [14] 曹现刚,刘思颖,王鹏,等. 面向煤矸分拣机器人的煤矸识别定位系统研究[J]. 煤炭科学技术,2022,50(1):237-246. doi: 10.3969/j.issn.0253-2336.2022.1.mtkxjs202201024CAO Xiangang,LIU Siying,WANG Peng,et al. Research on coal gangue identification and positioning system based on coal-gangue sorting robot[J]. Coal Science and Technology,2022,50(1):237-246. doi: 10.3969/j.issn.0253-2336.2022.1.mtkxjs202201024 [15] 王鹏,曹现刚,夏晶,等. 基于机器视觉的多机械臂煤矸石分拣机器人系统研究[J]. 工矿自动化,2019,45(9):47-53. doi: 10.13272/j.issn.1671-251x.17442WANG Peng,CAO Xiangang,XIA Jing,et al. Research on multi-manipulator coal and gangue sorting robot system based on machine vision[J]. Industry and Mine Automation,2019,45(9):47-53. doi: 10.13272/j.issn.1671-251x.17442 [16] MATTONE R,CAMPAGIORNI G,GALATI F,et al. Sorting of items on a moving conveyor belt-part 1:a technique for detecting and classifying objects[J]. Robotics and Computer-Integrated Manufacturing,2000,16(2/3):73-80. [17] FEIERABEND A. Application of NIR measurement technique for the identification and sorting of mineral rocks[J]. Gesellschaft Fuer Bergbau,Metallurgie,Rohstoff-und UmwelttechnikSchriftenreihe,2010(122):33. [18] 石康,叶宏,胡安灿,等. 一种基于LabVIEW的机器视觉标定和校正方法[J]. 激光与光电子学进展,2014,51(10):127-136.SHI Kang. YE Hong,HU Ancan,et al. A new method for machine vision calibration and rectification based on LabVIEW[J]. Laser & Optoelectronics Progress,2014,51(10):127-136. [19] 涂波,刘璐,刘一会,等. 一种扩展小孔成像模型的鱼眼相机矫正与标定方法[J]. 自动化学报,2014,40(4):653-659.TU Bo,LIU Lu,LIU Yihui,et al. A calibration method for fish-eye cameras based on pinhole model[J]. Acta Automatica Sinica,2014,40(4):653-659. [20] 李海,王若璞,陈勇,等. 图像全站仪星点质心快速提取方法研究[J]. 测绘科学技术学报,2019,36(5):482-486.LI Hai,WANG Ruopu,CHEN Yong,et al. Fast star centroid extraction method for image total station[J]. Journal of Geomatics Science and Technology,2019,36(5):482-486. -
点击查看大图
计量
- 文章访问数: 1250
- HTML全文浏览量: 79
- PDF下载量: 78
- 被引次数: 0
