基于改进YOLOv5s模型的煤矸目标检测

沈科; 季亮; 张袁浩; 邹盛

doi:10.13272/j.issn.1671-251x.17838

基于改进YOLOv5s模型的煤矸目标检测

doi: 10.13272/j.issn.1671-251x.17838

沈科^1,2,
季亮^1,2,
张袁浩^1,2,
邹盛^1,2

1. 中煤科工集团常州研究院有限公司, 江苏常州 213015;
2. 天地(常州)自动化股份有限公司, 江苏常州 213015

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（2020-TD-ZD010）。

详细信息

作者简介:
沈科(1982-),男,江苏常州人,工程师,主要从事机器视觉、深度学习算法及软件的研发工作,E-mail:1123540889@qq.com.

中图分类号: TD67
计量
- 文章访问数: 198
- HTML全文浏览量: 16
- PDF下载量: 51
- 被引次数: 0
出版历程
- 收稿日期: 2021-08-31
- 修回日期: 2021-11-16
- 刊出日期: 2021-11-20

Research on coal and gangue detection algorithm based on improved YOLOv5s model

SHEN Ke^1,2,
JI Liang^1,2,
ZHANG Yuanhao^1,2,
ZOU Sheng^1,2

1. CCTEG Changzhou Research Institute, Changzhou 213015, China;
2. Tiandi(Changzhou)Automation Co., Ltd., Changzhou 213015, China

摘要

摘要: 针对现有基于深度学习的煤矸目标检测方法存在检测速度慢且检测精度较低等问题，提出了一种改进YOLOv5s模型，并将其应用于煤矸目标检测中。改进YOLOv5s模型在YOLOv5s模型Backbone区域嵌入自校正卷积(SCConv)作为特征提取网络，可更好地融合多尺度特征信息；由于煤块和矸石的尺寸相对整张图像过小，对YOLOv5s模型Neck区域进行适当精简，将适合检测较大尺寸对象的19×19特征图分支删除，从而降低模型复杂度并提高检测实时性；对通过K-means算法聚类得到的锚框进行线性缩放，提高模型检测精度。基于改进YOLOv5s模型的煤矸目标检测实验表明，相较于YOLOv5s模型，改进YOLOv5s模型能准确检测出相应的煤块和矸石，且改进YOLOv5s模型大小降低了1.57 MB，帧速率增加了2.1帧/s，平均精度均值提高了1.7%，表明改进YOLOv5s模型检测精度和检测速度均有提升。
- 煤矸分选 /
- 煤矸识别 /
- 煤矸目标检测 /
- YOLOv5s /
- 自校正卷积
Abstract: In order to solve the problems of slow detection speed and low detection precision of the existing deep learning-based coal and gangue target detection methods, an improved YOLOv5s model is proposed and applied to coal and gangue target detection.The YOLOv5s model is improved by embedding self-calibrated convolutions(SCConv)in the Backbone area of YOLOv5s model as the characteristic extraction network, which can better fuse multi-scale characteristic information.Because the size of coal and gangue is too small compared with the whole image, the Neck area of YOLOv5s model is appropriately simplified, and the 19×19 characteristic map branches suitable for detecting larger size objects are deleted, thus reducing model complexity and improving the real-time detection performance.The anchor box obtained by clustering with K-means algorithm is linearly scaled to improve the model detection precision.The experiment of coal and gangue target detection based on improved YOLOv5s model shows that compared with YOLOv5s model, the improved YOLOv5s model can detect the corresponding coal and gangue accurately.The size of improved YOLOv5s model is reduced by 1.57 MB, the frame rate is increased by 2.1 frames/s, and the average precision is improved by 1.7%, indicating that the improved YOLOv5s model has improved both detection precision and detection speed.
- coal and gangue separation /
- coal and gangue identification /
- coal and gangue target detection /
- YOLOv5s /
- self-calibrated convolutions

HTML全文

参考文献(15)

[1]	孙超,姜琳,袁广玉.“十四五”期间我国煤炭供需趋势分析[J].煤炭工程,2021,53(5):193-196. SUN Chao,JIANG Lin,YUAN Guangyu.Trend analysis of China's coal supply and demand during the 14th Five-Year Plan[J].Coal Engineering,2021,53(5):193-196.
[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(1):1-9.
[3]	MOHANTA K S,MEIKAPB C.Influence of medium particle size on the separation performance of an air dense medium fluidized bed separator for coal cleaning[J].Journal of the Southern African Institute of Mining and Metallurgy,2015,115(8):761-766.
[4]	李建平,郑克洪,杜长龙.煤和矸石的冲击破碎粒度分布特征[J].煤炭学报,2013,38(增刊1):54-58. LI Jianping,ZHENG Kehong,DU Changlong.The distribution discipline of impact crushed on coal and gangue[J].Journal of China Coal Society,2013,38(S1):54-58.
[5]	曹现刚,李莹,王鹏,等.煤矸石识别方法研究现状与展望[J].工矿自动化,2020,46(1):38-43. CAO Xiangang,LI Ying,WANG Peng,et al.Research status of coal-gangue identification method and its prospect[J].Industry and Mine Automation,2020,46(1):38-43.
[6]	刘富强,钱建生,王新红,等.基于图像处理与识别技术的煤矿矸石自动分选[J].煤炭学报,2000,25(5):534-537. LIU Fuqiang,QIAN Jiansheng,WANG Xinhong,et al.Automatic separation of waste rock in coal mine based on image procession and recognition[J].Journal of China Coal Society,2000,25(5):534-537.
[7]	刘丽,赵凌君,郭承玉,等.图像纹理分类方法研究进展和展望[J].自动化学报,2018,44(4):584-607. LIU Li,ZHAO Lingjun,GUO Chengyu,et al.Texture classification:state-of-the-art methods and prospects[J].Acta Automatica Sinica,2018,44(4):584-607.
[8]	ZHANG Ning,DONAHUE J,GIRSHICK R,et al.Part-based R-CNNs for fine-grained category detection[C]//European Conference on Computer Vision(ECCV),Zurich,2014:834-849.
[9]	LIU Wei,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector[C]//European Conference on Computer Vision(ECCV),Amsterdam,2016:21-37.
[10]	REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Conference on Computer Vision and Pattern Recognition(CVPR),Las Vegas,2016:779-788.
[11]	王中举,毛馨凯,孙江.基于视频解析的智能煤矸分选技术研究[J].工矿自动化,2021,47(增刊1):122-125. WANG Zhongju,MAO Xinkai,SUN Jiang.Research on intelligent coal-gangue separation technology based on video analysis[J].Industry and Mine Automation,2021,47(S1):122-125.
[12]	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.
[13]	DU Shuangjiang,ZHANG Pin,ZHANG Baofu,et al.Weak and occluded vehicle detection in complex infrared environment based on improved YOLOv4[J].IEEE Access,2021,9:25671-25680.
[14]	JI Weizhen,LIU Deer,MENG Yifei,et al.Exploring the solutions via Retinex enhancements for fruit recognition impacts of outdoor sunlight:a case study of navel oranges[J].Evolutionary Intelligence,2021:1-37.
[15]	LIU Jiangjiang,HOU Qibin,CHENG Mingming,et al.Improving convolutional networks with self-calibrated convolutions[C]//Conference on Computer Vision and Pattern Recognition(CVPR),Seattle,2020:10093-10102.