基于双目结构光视觉的煤流量测量研究

张俊升; 王洪磊; 李佳城

doi:10.13272/j.issn.1671-251x.2022100050

基于双目结构光视觉的煤流量测量研究

doi: 10.13272/j.issn.1671-251x.2022100050

煤炭科学研究总院有限公司智能矿山研究院, 北京　100013

基金项目: 天地科技股份有限公司科技创新创业资金专项项目（2022-3-TD-ZD001）。

详细信息

作者简介:
张俊升(1995—)，男，四川巴中人，助理研究员，硕士，研究方向为智能矿山和机器视觉，E-mail：zhangjs2013s@163.com

中图分类号: TD634
计量
- 文章访问数: 211
- HTML全文浏览量: 141
- PDF下载量: 43
- 被引次数: 0
出版历程
- 收稿日期: 2022-10-18
- 修回日期: 2023-06-20
- 网络出版日期: 2023-08-03

Research on coal flow measurement based on binocular structured light vision

Intelligent Mine Research Institute, CCTEG Chinese Institute of Coal Science, Beijing 100013, China

摘要

摘要: 在常规的双目视觉系统中，常用的加速稳健特征和尺度不变特征转换匹配算法对图像质量要求高，针对煤炭这种颜色纹理比较单一的场景应用时容易失效，且需要消耗大量的计算资源，难以保证实时性；激光雷达在进行煤流量测量时，有效视场范围较小，对应的测量点数较少，扫描频率也较低，在带式输送机运行速度较快时，精度会大幅降低。针对上述问题，提出一种基于双目结构光视觉的煤流量测量方法，将线结构光引入双目视觉系统，利用线结构光的约束，将图像特征点匹配简化成左右2幅图像行之间的匹配。在保证双目系统相机光轴平行度的基础上，采用对应行匹配计算三维坐标点，提高采样频率和分辨率，进而提高煤流量测量精度，降低测量系统对光照和环境的依赖。点云获取：利用线结构光凸显煤料截面曲线，提取煤料截面中心线的图像坐标，利用双目相机获取左右煤料截面线结构光图像，建立双目结构光三维重建模型，左右图像中心线坐标构成匹配点对参与计算煤料截面三维坐标，实现点云的实时获取。煤流量计算：利用空载胶带截面点云和负载胶带截面点云，结合获取煤料点云，利用微元法对煤料三维点云进行采样，分别利用均匀网格化法和三角网格化法求取单位时间内的煤料体积，实现带式输送机煤流量测量。实验结果表明，利用均匀网格化法检测煤料体积平均相对误差为6.758%，利用三角网格化法检测煤料体积平均相对误差为2.791%，三角网格化法测量精度高于均匀网格化法。工业性试验结果表明，基于双目结构光视觉的煤流量测量方法与电子胶带秤相比，绝对误差最大值为87.855 t/h，绝对误差平均值为25.902 t/h，相对误差最大值为2.876%，平均相对误差为0.847%，满足煤矿非接触式煤流量测量使用要求。
- 带式输送机 /
- 非接触式测量 /
- 双目结构光视觉 /
- 双目相机 /
- 煤流量检测 /
- 均匀网格化 /
- 三角网格化 /
- 煤料点云
Abstract: In the conventional binocular vision system, the commonly used speeded up robust features and scale-invariant feature transform matching algorithms have high requirements for image quality. When applied to scenes with relatively single color and texture such as coal, it is prone to failure. It needs to consume a lot of computing resources, which is difficult to ensure real-time performance. When using LiDAR for coal quantity measurement, the effective field of view is relatively small. The corresponding measurement points are few and the scanning frequency is low. When the belt conveyor runs at a faster speed, the precision will be significantly reduced. In order to solve the above problems, a coal flow measurement method based on binocular structured light vision is proposed. The linear structured light is introduced into the binocular vision system. By using the constraint of linear structured light, the image feature point matching is simplified into matching between left and right image lines. On the basis of ensuring the parallelism of the optical axis of the binocular system camera, corresponding row matching is used to calculate three-dimensional coordinate points. The sampling frequency and resolution is improved. The precision of coal flow measurement is improved. The dependence of the measurement system on lighting and environment is reduced. Point cloud acquisition: It uses the line structured light to highlight the coal material section curve, and extracts the image coordinates of the coal material section center line. It uses the binocular camera to obtain the left and right coal material section line structured light images. It establishes binocular structured light 3D reconstruction model. The left and right image center line coordinates form a matching point pair to participate in the calculation of the coal material section 3D coordinates, so as to achieve real-time acquisition of point clouds. Coal flow calculation: The point cloud of coal material is obtained by combining the point cloud of no-load belt section and the point cloud of loaded belt section. The infinitesimal method is used to sample the 3D point cloud of coal material. The volume of coal material in unit time is calculated by the uniform meshing method and the triangle meshing method, respectively. The coal flow measurement of belt conveyor is realized. The experimental results show that the average relative error of coal volume measured by the uniform meshing method is 6.758%. The average relative error of coal volume measured by the triangle meshing method is 2.791%. The measurement precision of the triangle meshing method is higher than that of the uniform meshing method. The industrial test results show that compared with the electronic belt weigher, the maximum absolute error of the coal flow measurement method based on binocular structured light vision is 87.855 t/h. The average absolute error is 25.902 t/h, the maximum relative error is 2.876%, and the average relative error is 0.847%. The results meet the requirements of non-contact coal flow measurement in coal mines.
- belt conveyor /
- non contact measurement /
- binocular structured light vision /
- binocular camera /
- coal flow detection /
- uniform meshing /
- triangle meshing /
- coal point cloud

HTML全文

图 1 双目视觉模型

Figure 1. Binocular visual model

下载: 全尺寸图片幻灯片

图 2 双目煤流量测量系统布置

Figure 2. Arrangement of the binocular coal flow measurement system

下载: 全尺寸图片幻灯片

图 3 双目结构光图像

Figure 3. Binocular structured light image

下载: 全尺寸图片幻灯片

图 4 煤料点云合成原理

Figure 4. Synthesis principle of coal point cloud

下载: 全尺寸图片幻灯片

图 5 煤流量计算原理

Figure 5. Calculation principle of coal flow

下载: 全尺寸图片幻灯片

图 6 点云均匀网格化

Figure 6. Point cloud uniform meshing

下载: 全尺寸图片幻灯片

图 7 点云三角网格化

Figure 7. Point cloud triangle meshing

下载: 全尺寸图片幻灯片

图 8 煤流量测量试验平台

Figure 8. Coal flow measurement and test platform

下载: 全尺寸图片幻灯片

图 9 空载胶带与负载胶带表面点云

Figure 9. Point cloud on the surface of no-load belt and load belt

下载: 全尺寸图片幻灯片

图 10 选煤厂煤流测量试验

Figure 10. Coal flow measurement test of coal washing plant

下载: 全尺寸图片幻灯片

图 11 双目煤流量测量系统软件界面

Figure 11. Software interface of the binocular coal flow measurement system

下载: 全尺寸图片幻灯片

图 12 电子胶带秤软件界面

Figure 12. Software interface of electronic belt scale

下载: 全尺寸图片幻灯片

图 13 本文方法与电子胶带秤检测结果

Figure 13. Test results of this method and electronic belt weigher

下载: 全尺寸图片幻灯片

图 14 本文方法相对电子胶带秤绝对误差

Figure 14. Absolute error of this method relative to electronic belt weigher

下载: 全尺寸图片幻灯片

图 15 本文方法相对电子胶带秤相对误差

Figure 15. Relative error of this method relative to electronic belt weigher

下载: 全尺寸图片幻灯片

表 1 煤料体积测量结果

Table 1. Measurement results of coal material volume

标准体积/cm³	均匀网格化/cm³	三角网格化/cm³	均匀网格化相对误差/%	三角网格化相对误差/%
250	228.667	252.142	8.533	0.857
500	478.458	521.172	4.908	4.234
750	695.941	764.505	7.208	1.934
1 000	1 091.213	965.941	9.121	3.406
1 250	1 321.048	1 275.572	5.684	2.046
1 500	1 423.624	1 564.014	5.092	4.268
平均相对误差/%			6.758	2.791

下载: 导出CSV

表 2 检测参数设置

Table 2. Test parameter settings

参数名称	设置数值
曝光时间/μs	1 000
增益	2
像素数	2 048×256
堆煤密度/（t·m⁻³）	0.90

下载: 导出CSV

参考文献(20)

[1]	方原柏. 皮带秤系统试验装置发展四十年回顾[J]. 衡器,2021,50(8):42-51. doi: 10.3969/j.issn.1003-5729.2021.08.011 FANG Yuanbai. Review of 40 years development of belt weigher system test sevice[J]. Weighing Instrument,2021,50(8):42-51. doi: 10.3969/j.issn.1003-5729.2021.08.011
[2]	王占飞,王耀. 煤矿井下煤流运输系统智能调速研究与应用[J]. 煤炭科学技术,2022,50(增刊1):283-288. WANG Zhanfei,WANG Yao. Research and application of intelligent speed regulation of coal flow transportation system in coal mine[J]. Coal Science and Technology,2022,50(S1):283-288.
[3]	李瑶,王义涵. 带式输送机煤流量自适应检测方法[J]. 工矿自动化,2020,46(6):98-102. LI Yao,WANG Yihan. Adaptive coal flow detection method of belt conveyor[J]. Industry and Mine Automation,2020,46(6):98-102.
[4]	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. YANG 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.
[5]	胡而已. 基于激光扫描的综放工作面放煤量智能监测技术[J]. 煤炭科学技术,2022,50(2):244-251. doi: 10.13199/j.cnki.cst.2021-0105 HU Eryi. Intelligent monitoring technology of coal caving in fully-mechanized caving face based on laser scanning[J]. Coal Science and Technology,2022,50(2):244-251. doi: 10.13199/j.cnki.cst.2021-0105
[6]	MOLNAR V,LIPOVCOVA K. Design of clamping structure for material flow monitor of pipe conveyors[J]. Open Engineering,2019,9(1):586-592. doi: 10.1515/eng-2019-0068
[7]	代伟, 赵杰, 杨春雨, 等. 基于双目视觉深度感知的带式输送机煤量检测方法[J]煤炭学报, 2017, 42（增刊2）: 547-555. DAI Wei, ZHAO Jie, YANG Chunyu, et al. Detection method of coal quantity in belt conveyor based on binocular vision depth perception[J]. Journal of China Coal Society, 2017, 42（S2）: 547-555.
[8]	王才东,刘丰阳,李志航,等. 基于双目视觉特征点匹配的图像拼接方法研究[J]. 激光与光电子学进展,2021,58(12):357-365. WANG Caidong,LIU Fengyang,LI Zhihang,et al. Research on image mosaic method based on binocular vision feature point matching[J]. Laser & Optoelectronics Progress,2021,58(12):357-365.
[9]	罗久飞,邱广,张毅,等. 基于自适应双阈值的SURF双目视觉匹配算法研究[J]. 仪器仪表学报,2020,41(3):240-247. LUO Jiufei,QIU Guang,ZHANG Yi,et al. Research on speeded up robust feature binocular vision matching algorithm based on adaptive double threshold[J]. Chinese Journal of Scientific Instrument,2020,41(3):240-247.
[10]	姜玉峰,张立亚,李标,等. 基于单线激光雷达的带式输送机煤流量检测研究[J]. 煤矿机械,2022,43(8):151-153. JIANG Yufeng,ZHANG Liya,LI Biao,et al. Study on coal flow detection of belt conveyor based on single-line LiDAR[J]. Coal Mine Machinery,2022,43(8):151-153.
[11]	FEI Yu, FU Qiang, ZHUANG Ying, et al. Binocular vision pose estimation based on PSOPF[J]. Journal of Physics: Conference Series, 2019, 1302（3）. DOI: 10.1088/1742-6596/1302/3/032051.
[12]	WANG Song,HU Yanzhu. Binocular visual positioning under inhomogeneous,transforming and fluctuating media[J]. Traitement du Signal,2018,35(3/4):253-276.
[13]	ZHANG Zhengyou. A flexible new technique for camera calibration[J]. IEEE Transaactions on Pattern Analysis and Machie Intelligence,2000,22(11):1330-1334. doi: 10.1109/34.888718
[14]	曾超,王少军,卢红,等. 线结构光光条中心提取算法[J]. 中国图象图形学报,2019,24(10):1772-1780. ZENG Chao,WANG Shaojun,LU Hong,et al. Center extraction algorithm of line structured light stripe[J]. Journal of Image and Graphics,2019,24(10):1772-1780.
[15]	卢红阳,刘且根,熊娇娇,等. 基于最大加权投影求解的彩色图像灰度化对比度保留算法[J]. 自动化学报,2017,43(5):843-854. LU Hongyang,LIU Qiegen,XIONG Jiaojiao,et al. Maximum weighted projection solver for contrast preserving decolorization[J]. Acta Automatica Sinica,2017,43(5):843-854.
[16]	HERMOSILIA P,RITSCHEL T,VAZQUEZ P,et al. Monte carlo convolution for learning on non-uniformly sampled point clouds[J]. ACM Transactions on Graphics(TOG),2018,37(6):1-12.
[17]	PEREIRA F I,LUFT J A,IIHA G,et al. A novel resection-intersection algorithm with fast triangulation applied to monocular visual odometry[J]. IEEE Transactions on Intelligent Transportation Systems,2018,19(11):3584-3593. doi: 10.1109/TITS.2018.2853579
[18]	ZHANG Yuyan,GUO Quanli,WANG Zhenchun,et al. Quantitative evaluation for small surface damage based on iterative difference and triangulation of 3D point cloud[J]. Measurement Science and Technology,2018,29(3):035601-035608. doi: 10.1088/1361-6501/aa99fb
[19]	MATTHIJS E,PARLIER H,VEGTER G,et al. Minimal delaunay triangulations of hyperbolic surfaces[J]. Discrete & Computational Geometry,2022,69(2):1-25.
[20]	李铁军,王学文,李博,等. 基于离散元法的煤颗粒模型参数优化[J]. 中国粉体技术,2018,24(5):6-12. LI Tiejun,WANG Xuewen,LI Bo,et al. Optimization method for coal particle model parameters based on discrete element method[J]. China Powder Science and Technology,2018,24(5):6-12.