基于YOLOv5s−SDE的带式输送机煤矸目标检测

张磊; 王浩盛; 雷伟强; 王斌; 林建功

doi:10.13272/j.issn.1671-251x.2022080043

基于YOLOv5s−SDE的带式输送机煤矸目标检测

doi: 10.13272/j.issn.1671-251x.2022080043

山西大同大学煤炭工程学院, 山西大同　037003

基金项目: 山西省研究生教育创新项目（2021Y739）；2022年大同市科技计划重点研发（高新技术领域）项目（2022005）；山西大同大学2022年度校级揭榜招标项目（2021ZBZX3）；山西大同大学2021年度产学研专项研究项目（2021CXZ2）；山西大同大学研究生教育创新项目（21CX02，21CX37）。

详细信息

作者简介:
张磊(1984—)，男，山西大同人，副教授，主要从事智能采矿、煤矿地质等方面的研究工作，E-mail：dtblack84@163.com

中图分类号: TD634
计量
- 文章访问数: 238
- HTML全文浏览量: 80
- PDF下载量: 53
- 被引次数: 0
出版历程
- 收稿日期: 2022-08-15
- 修回日期: 2023-04-10
- 网络出版日期: 2023-04-27

Coal gangue target detection of belt conveyor based on YOLOv5s-SDE

School of Coal Engineering, Shanxi Datong University, Datong 037003, China

摘要

摘要: 传统的煤矸图像检测方法需要人工提取图像特征，准确率不高，实用性不强。现有基于改进YOLO的煤矸目标检测方法在速度和精度方面有所提升，但仍不能很好地满足选煤厂带式输送机实时智能煤矸分选需求。针对该问题，在YOLOv5s模型基础上进行改进，构建了YOLOv5s−SDE模型，提出了基于YOLOv5s−SDE的带式输送机煤矸目标检测方法。YOLOv5s−SDE模型通过在主干网络中添加压缩和激励（SE）模块，以增强有用特征，抑制无用特征，改善小目标煤矸检测效果；利用深度可分离卷积替换普通卷积，以减少参数量和计算量；将边界框回归损失函数CIoU替换为EIoU，提高了模型的收敛速度和检测精度。消融实验结果表明：YOLOv5s−SDE模型对煤矸图像的检测准确率达87.9%，平均精度均值（mAP）达92.5%，检测速度达59.9帧/s，可有效检测煤和矸石，满足实时检测需求；与YOLOv5s模型相比，YOLOv5s−SDE模型的准确率下降2.3%，mAP提升1.3%，参数量减少22.2%，计算量下降24.1%，检测速度提升6.4%。同类改进模型对比实验结果表明，YOLOv5s−STA与YOLOv5s−Ghost模型的检测精度明显偏低，YOLOv5s−SDE模型与YOLOv5s模型及YOLOv5s−CBAM模型的检测效果整体相近，但在运动模糊和低照度情况下，YOLOv5s−SDE模型整体检测效果更优。
- 煤矸目标检测 /
- 实时智能煤矸分选 /
- 深度学习 /
- YOLOv5s /
- 注意力机制 /
- 深度可分离卷积 /
- 损失函数
Abstract: Traditional coal gangue image detection methods require manual extraction of image features. The methods have low accuracy and practicality. The existing coal gangue target detection methods based on improved YOLO have improved in speed and precision, but they still cannot meet the real-time intelligent coal gangue sorting needs of belt conveyors in coal preparation plants. In order to solve the above problems, an improvement is made to the YOLOv5s model, and a YOLOv5s-SDE model was constructed. A method for coal gangue target detection of belt conveyors based on YOLOv5s-SDE is proposed. The YOLOv5s-SDE model enhances useful features, suppresses useless features, and improves the detection effect of small target coal gangue by adding squeeze-and-excitation (SE) module to the backbone network. The model replaces ordinary convolutions with depthwise separable convolutions to reduce parameter and computational complexity. The loss function of the bounding box regression CIoU is replaced by the EIoU. This improves the convergence speed and detection precision of the model. The results of the ablation experiment show that the YOLOv5s-SDE model has a detection accuracy of 87.9% for coal gangue images, a mean average precision (mAP) of 92.5%, and a detection speed of 59.9 frames/s. It can effectively detect coal and gangue, meeting real-time detection requirements. Compared with the YOLOv5s model, the accuracy of the YOLOv5s-SDE model decreases by 2.3%, the mAP increases by 1.3%, the number of parameters decreases by 22.2%, the calculation amount decreases by 24.1%, and the detection speed increases by 6.4%. The comparative experimental results of similar improved models show that the detection precision of YOLOv5s-STA model and YOLOv5s-Ghost model is significantly lower. The detection performance of the YOLOv5s-SDE model, YOLOv5s model and YOLOv5s-CBAM model is generally similar. But in the case of motion blur and low lightning, the overall detection performance of the YOLOv5s-SDE model is better.
- coal gangue target detection /
- real-time intelligent coal gangue sorting /
- deep learning /
- YOLOv5s /
- attention mechanism /
- depthwise separable convolution /
- loss function

HTML全文

图 1 YOLOv5s−SDE结构

Figure 1. YOLOv5s -SDE structure

下载: 全尺寸图片幻灯片

图 2 SE模块

Figure 2. Squeeze-and-excitation module

下载: 全尺寸图片幻灯片

图 3 深度可分离卷积结构

Figure 3. Structure of depthwise separable convolution

下载: 全尺寸图片幻灯片

图 4 数据集样本

Figure 4. Dataset samples

下载: 全尺寸图片幻灯片

图 5 目标检测模型训练结果

Figure 5. Training results of target detection models

下载: 全尺寸图片幻灯片

图 6 不同改进YOLOv5s模型检测效果对比

Figure 6. Comparison of detection effects of different improved YOLOv5s models

下载: 全尺寸图片幻灯片

表 1 消融实验结果

Table 1. Ablation experiment results

网络模型	SE模块	深度可分离卷积	EIoU	准确率/%	mAP/%	参数量/10⁵个	每秒浮点运算次数/10⁸	速度/（帧·s⁻¹）
YOLOv5s	×	×	×	90.2	91.2	70.2	15.8	56.3
优化模型1	√	×	×	92.8	91.0	70.2	16.0	54.4
优化模型2	×	√	×	85.6	85.8	54.6	12.0	62.1
优化模型3	×	×	√	91.9	92.1	70.2	15.8	56.0
YOLOv5s−SDE	√	√	√	87.9	92.5	54.6	12.0	59.9

下载: 导出CSV

表 2 不同改进YOLOv5s模型对比实验结果

Table 2. Comparative experimental results of different improved YOLOv5s models

模型	准确率/%	mAP/%	参数量/ 10⁵个	每秒浮点运算次数/10⁸	速度/ （帧·s⁻¹）
YOLOv5s	90.2	91.2	70.2	15.8	56.3
YOLOv5s−Ghost	84.2	89.3	62.4	14.0	54.9
YOLOv5s−CBAM	90.7	91.8	72.1	16.0	55.4
YOLOv5s−STA	83.1	84.8	55.2	20.6	75.2
YOLOv5s−SDE	87.9	92.5	54.6	12.0	59.9

下载: 导出CSV

参考文献(21)

[1]	张强,张润鑫,刘峻铭,等. 煤矿智能化开采煤岩识别技术综述[J]. 煤炭科学技术,2022,50(2):1-26. ZHANG Qiang,ZHANG Runxin,LIU Junming,et al. Review on coal and rock identification technology for intelligent mining in coal mines[J]. Coal Science and Technology,2022,50(2):1-26.
[2]	ZHANG Ningbo, LIU Changyou. Radiation characteristics of natural gamma-ray from coal and gangue for recognition in top coal caving[J]. Scientific Reports, 2018, 8. DOI: 10.1038/s41598-017-18625-y.
[3]	王闰泽,郎利影,席思星. 用于智能煤矸分选机器人的改进型VGG网络煤矸识别模型[J]. 煤炭技术,2022,41(1):237-241. WANG Runze,LANG Liying,XI Sixing. Improved VGG network coal gangue recognition model for intelligent coal gangue sorting robot[J]. Coal Technology,2022,41(1):237-241.
[4]	司垒,谭超,朱嘉皓,等. 基于X射线图像和激光点云的煤矸识别方法[J]. 仪器仪表学报,2022,43(9):193-205. SI Lei,TAN Chao,ZHU Jiahao,et al. A coal-gangue recognition method based on X-ray image and laser point cloud[J]. Chinese Journal of Scientific Instrument,2022,43(9):193-205.
[5]	桂方俊,李尧. 基于CBA−YOLO模型的煤矸石检测[J]. 工矿自动化,2022,48(6):128-133. GUI Fangjun,LI Yao. Coal gangue detection based on CBA-YOLO model[J]. Journal of Mine Automation,2022,48(6):128-133.
[6]	王家臣,李良晖,杨胜利. 不同照度下煤矸图像灰度及纹理特征提取的实验研究[J]. 煤炭学报,2018,43(11):3051-3061. WANG Jiachen,LI Lianghui,YANG Shengli. Experimental study on gray and texture features extraction of coal and gangue image under different illuminance[J]. Journal of China Coal Society,2018,43(11):3051-3061.
[7]	鲁恒润,王卫东,徐志强,等. 基于机器视觉的煤矸特征提取与分类研究[J]. 煤炭工程,2018,50(8):137-140. LU Hengrun,WANG Weidong,XU Zhiqiang,et al. Extraction and classification of coal and gangue image features based on machine vision[J]. Coal Engineering,2018,50(8):137-140.
[8]	单鹏飞,孙浩强,来兴平,等. 基于改进Faster R−CNN的综放煤矸混合放出状态识别方法[J]. 煤炭学报,2022,47(3):1382-1394. SHAN Pengfei,SUN Haoqiang,LAI Xingping,et al. Identification method on mixed and release state of coal-gangue masses of fully mechanized caving based on improved Faster R-CNN[J]. Journal of China Coal Society,2022,47(3):1382-1394.
[9]	郝帅,张旭,马旭,等. 基于CBAM−YOLOv5的煤矿输送带异物检测[J]. 煤炭学报,2022,47(11):4147-4156. HAO Shuai,ZHANG Xu,MA Xu,et al. Foreign object detection in coal mine conveyor belt based on CBAM-YOLOv5[J]. Journal of China Coal Society,2022,47(11):4147-4156.
[10]	雷世威,肖兴美,张明. 基于改进YOLOv3的煤矸识别方法研究[J]. 矿业安全与环保,2021,48(3):50-55. LEI Shiwei,XIAO Xingmei,ZHANG Ming. Research on coal and gangue identification method based on improved YOLOv3[J]. Mining Safety & Environmental Protection,2021,48(3):50-55.
[11]	来文豪,周孟然,胡锋,等. 基于多光谱成像和改进YOLO v4的煤矸石检测[J]. 光学学报,2020,40(24):72-80. LAI Wenhao,ZHOU Mengran,HU Feng,et al. Coal gangue detection based on multi-spectral imaging and improved YOLO v4[J]. Acta Optica Sinica,2020,40(24):72-80.
[12]	李永上,马荣贵,张美月. 改进YOLOv5s+DeepSORT的监控视频车流量统计[J]. 计算机工程与应用,2022,58(5):271-279. LI Yongshang,MA Ronggui,ZHANG Meiyue. Traffic monitoring video vehicle volume statistics method based on improved YOLOv5s+DeepSORT[J]. Computer Engineering and Applications,2022,58(5):271-279.
[13]	沈科,季亮,张袁浩,等. 基于改进YOLOv5s模型的煤矸目标检测[J]. 工矿自动化,2021,47(11):107-111,118. SHEN Ke,JI Liang,ZHANG Yuanhao,et al. Research on coal and gangue detection algorithm based on improved YOLOv5s model[J]. Industry and Mine Automation,2021,47(11):107-111,118.
[14]	徐涛,马克,刘才华. 基于深度学习的行人多目标跟踪方法[J]. 吉林大学学报(工学版),2021,51(1):27-38. XU Tao,MA Ke,LIU Caihua. Multi object pedestrian tracking based on deep learning[J]. Journal of Jilin University(Engineering and Technology Edition),2021,51(1):27-38.
[15]	杜京义,史志芒,郝乐,等. 轻量化煤矸目标检测方法研究[J]. 工矿自动化,2021,47(11):119-125. DU Jingyi,SHI Zhimang,HAO Le,et al. Research on lightweight coal and gangue target detection method[J]. Industry and Mine Automation,2021,47(11):119-125.
[16]	宋晓茹,杨佳,高嵩,等. 基于注意力机制与多尺度特征融合的行人重识别方法[J]. 科学技术与工程,2022,22(4):1526-1533. SONG Xiaoru,YANG Jia,GAO Song,et al. Person re-identification method based on attention mechanism and multi-scale feature fusion[J]. Science Technology and Engineering,2022,22(4):1526-1533.
[17]	张璐,李道亮,曹新凯,等. 基于深度可分离卷积网络的粘连鱼体识别方法[J]. 农业工程学报,2021,37(17):160-167. ZHANG Lu,LI Daoliang,CAO Xinkai,et al. Recognition method for adhesive fish based on depthwise separable convolution network[J]. Transactions of the Chinese Society of Agricultural Engineering,2021,37(17):160-167.
[18]	杨永波,李栋. 改进YOLOv5的轻量级安全帽佩戴检测算法[J]. 计算机工程与应用,2022,58(9):201-207. doi: 10.3778/j.issn.1002-8331.2111-0346 YANG Yongbo,LI Dong. Lightweight helmet wearing detection algorithm of improved YOLOv5[J]. Computer Engineering and Applications,2022,58(9):201-207. doi: 10.3778/j.issn.1002-8331.2111-0346
[19]	刘普壮. 基于改进YOLO算法的煤矸识别方法与实验研究[D]. 淮南: 安徽理工大学, 2022. LIU Puzhuang. Research on coal and gangue recognition method and experiment based on improved YOLO algorithm[D]. Huainan: Anhui University of Science and Technology, 2022.
[20]	何雨,田军委,张震,等. YOLOv5目标检测的轻量化研究[J]. 计算机工程与应用,2023,59(1):92-99. HE Yu,TIAN Junwei,ZHANG Zhen,et al. Lightweight research of YOLOv5 target detection[J]. Computer Engineering and Applications,2023,59(1):92-99.
[21]	ZHANG Yifan,REN Weiqiang,ZHANG Zhang,et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing,2022,506:146-157. doi: 10.1016/j.neucom.2022.07.042