改进YOLOv8的矿用传输带异物检测方法

doi:10.3778/j.issn.1002-8331.2410-0425

摘要/Abstract

摘要： 目前矿井下输送带图像存在昏暗环境清晰度差、图像噪点等问题，现有检测算法模型存在复杂度高、漏检和错检、精度不足等问题。基于上述问题，提出一种改进YOLOv8模型。使用轻量级ShuffleNetv2作为头部网络减少模型参数量，并构建多尺度组合注意力机制（multi-scale composite attention module，MSCAM）来增强特征提取能力，以降低漏检率和错检率；针对现有模型对长条状异物准确率低的问题，在C2f模块中使用动态可变形卷积（DDConv）的思想，使模型更容易提取长条状异物结构特征；使用具有角度损失的SIoU新型损失函数，提升模型训练能力和推理性能。在MTBID数据集进行验证，实验结果表明：改进模型的mAP@0.5可达0.893，mAP@0.5：0.95可达0.663，参数量相较于YOLOv8n减少了27.6%。

关键词: 目标检测, YOLOv8n, ShuffleNetv2, 异物识别, 轻量化

Abstract: At present, there are some problems such as poor clarity in dark environment, image noise, high complexity of existing detection algorithm model, missing and wrong detection, and insufficient accuracy. Based on the above problems, an improved YOLOv8 model is proposed. Firstly, lightweight ShuffleNetv2 is used as the header network to reduce the number of model parameters, and multi-scale composite attention module (MSCAM) is constructed to enhance the feature extraction capability to reduce the miss and error detection rates. Secondly, in view of the low accuracy of existing models for long foreign bodies, the idea of dynamic deformable convolution (DDConv) is used in C2f module to make it easier to extract the structural features of long foreign bodies. Finally, the new SIoU loss function with angle loss is used to improve the training ability and inference performance of the model. The MTBID dataset is verified. The experimental results show that: mAP@0.5 and mAP@0.5：0.95 of the improved model can reach 0.893, 0.663, and the number of parameters is reduced by 27.6% compared with YOLOv8n.

Key words: target detection, YOLOv8n, ShuffleNetv2, foreign body recognition, light weight

杨迪, 赵培培, 孙奥然, 张君逸, 肖涛. 改进YOLOv8的矿用传输带异物检测方法[J]. 计算机工程与应用, 2025, 61(19): 311-319.

YANG Di, ZHAO Peipei, SUN Aoran, ZHANG Junyi, XIAO Tao. Improving YOLOv8 Method for Coal Mine Conveyor Belt Foreign Body Detection[J]. Computer Engineering and Applications, 2025, 61(19): 311-319.

参考文献

[1] 卢慧颖. 动力澎湃韧性十足[N]. 中国煤炭报, 2024-06-04(3).
LU H Y. Full of power and toughness[N]. China Coal Daily, 2024-06-04(3).
[2] 田冬艳, 丁苏凡, 郭星歌. 基于图像处理的煤矸识别方法[J]. 煤炭技术, 2022, 41(3): 201-204.
TIAN D Y, DING S F, GUO X G. Coal and gangue identification method based on image processing[J]. Coal Technology, 2022, 41(3): 201-204.
[3] 王学立, 赵辰燃, 李青, 等. 基于多模态的输送带撕裂大模型算法设计[J]. 煤矿安全, 2023, 54(9): 202-207.
WANG X L, ZHAO C R, LI Q, et al. Algorithm design of large model of belt tearing based on multi-modality[J]. Safety in Coal Mines, 2023, 54(9): 202-207.
[4] 郭永存, 何磊, 刘普壮, 等. 煤矸双能X射线图像多维度分析识别方法[J]. 煤炭学报, 2021, 46(1): 300-309.
GUO Y C, HE L, LIU P Z, et al. Multi-dimensional analysis and recognition method of coal and gangue dual-energy X-ray images[J]. Journal of China Coal Society, 2021, 46(1): 300-309.
[5] 王锐, 桂志国, 刘祎, 等. 基于X射线和结构光相机的煤矸石分拣方法研究[J]. 中北大学学报 (自然科学版), 2021, 42(2): 123-128.
WANG R, GUI Z G, LIU Y, et al. Research on coal gangue sorting method based on X-ray and structured light camera[J]. Journal of North University of China (Natural Science Edition), 2021, 42(2): 123-128.
[6] 王言, 邢冀川, 王遥志. 基于激光雷达的双通道伪彩图像煤矸识别方法[J]. 激光与光电子学进展, 2024, 61(4): 532-541.
WANG Y, XING J C, WANG Y Z. Coal and gangue recognition method based on dual-channel pseudocolor image by lidar[J]. Laser & Optoelectronics Progress, 2024, 61(4): 532-541.
[7] 卢才武, 闫雪颂, 刘力, 等. 一种改进的无锚框式金属矿带式输送机异物检测方法[J]. 采矿技术, 2022, 22(1): 150-154.
LU C W, YAN X S, LIU L, et al. An improved method for detecting foreign bodies in metal mine belt conveyor without anchor frame[J]. Mining Technology, 2022, 22(1): 150-154.
[8] 程德强, 徐进洋, 寇旗旗, 等. 融合残差信息轻量级网络的运煤皮带异物分类[J]. 煤炭学报, 2022, 47(3): 1361-1369.
CHENG D Q, XU J Y, KOU Q Q, et al. Lightweight network based on residual information for foreign body classification on coal conveyor belt[J]. Journal of China Coal Society, 2022, 47(3): 1361-1369.
[9] 朱名乾, 刘宾. 基于改进PSO-KMeans煤炭异物筛选算法研究[J]. 舰船电子工程, 2024, 44(2): 35-39.
ZHU M Q, LIU B. Research on foreign matter screening algorithm in coal based on improved PSO-KMeans[J]. Ship Electronic Engineering, 2024, 44(2): 35-39.
[10] 吕志强. 复杂环境下煤矿皮带运输异物图像识别研究[D]. 徐州: 中国矿业大学, 2020.
LYU Z Q. Research on image recognition of foreign bodies in the process of coal mine belt transportation in complex environment[D]. Xuzhou: China University of Mining and Technology, 2020.
[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.
HU J H, GAO Y, ZHANG H J, 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.
[12] 于志强. 基于机器视觉的异物识别系统在输送机保护中的应用[J]. 煤矿安全, 2024, 55(5): 251-256.
YU Z Q. Application of foreign object recognition system based on machine vision in conveyor protection[J]. Safety in Coal Mines, 2024, 55(5): 251-256.
[13] 毛清华, 李世坤, 胡鑫, 等. 基于改进YOLOv7的煤矿带式输送机异物识别[J]. 工矿自动化, 2022, 48(12): 26-32.
MAO Q H, LI S K, HU X, et al. Foreign object recognition of belt conveyor in coal mine based on improved YOLOv7[J]. Journal of Mine Automation, 2022, 48(12): 26-32.
[14] 陈彪, 卢兆林, 代伟, 等. 基于轻量化HPG-YOLOX-S模型的煤矸石图像精准识别[J]. 工矿自动化, 2022, 48(11): 33-38.
CHEN B, LU Z L, DAI W, et al. Accurate recognition of coal-gangue image based on lightweight HPG-YOLOX-S model[J]. Journal of Mine Automation, 2022, 48(11): 33-38.
[15] QI Y L, HE Y T, QI X M, et al. Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 6047-6056.
[16] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[J]. arXiv:2205.12740, 2022.
[17] MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer, 2018: 122-138.
[18] 高涵, 赵培培, 于正, 等. 基于特征增强与Transformer的煤矿输送带异物检测[J]. 煤炭科学技术, 2024, 52(7): 199-208.
GAO H, ZHAO P P, YU Z, et al. Coal mine conveyor belt foreign object detection based on feature enhancement and Transformer[J]. Coal Science and Technology, 2024, 52(7): 199-208.
[19] 唐俊, 李敬兆, 石晴, 等. 基于Faster-YOLOv7的带式输送机异物实时检测[J]. 工矿自动化, 2023, 49(11): 46-52.
TANG J, LI J Z, SHI Q, et al. Real time detection of foreign objects in belt conveyors based on Faster-YOLOv7[J]. Journal of Mine Automation, 2023, 49(11): 46-52.
[20] 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 S, ZHANG X, MA X, 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.
[21] 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.
DU J Y, CHEN R, HAO L, et al. Coal mine belt conveyor foreign object detection[J]. Industry and Mine Automation, 2021, 47(8): 77-83.
[22] 郑荣添, 陈泽同, 管孝汉, 等. 基于深度学习的无人机河道巡检异物监测技术研究[J/OL]. 水力发电学报: 1-11[2024-11-20]. https://link.cnki.net/urlid/11.2241.TV.20241112.0941.
002.
ZHENG R T, CHEN Z T, GUAN X H, et al. Research on monitoring technology of foreign bodies in river by UAV based on deep learning[J]. Journal of Hydroelectric Engineering: 1-11[2024-11-20]. https://link.cnki.net/urlid/11.2241.
TV.20241112.0941.002.
[23] 易磊, 黄哲玮, 易雅雯. 改进YOLOv8的输电线路异物检测方法[J]. 电子测量技术, 2024, 47(15): 125-134.
YI L, HUANG Z W, YI Y W. Improved YOLOv8 foreign object detection method for transmission lines[J]. Electronic Measurement Technology, 2024, 47(15): 125-134.