改进YOLOv3的矿石输送带杂物检测方法

doi:10.3778/j.issn.1002-8331.2105-0025

摘要/Abstract

摘要：

针对矿石输送带上夹杂的废旧木头、钢钎、塑料导爆管等杂物会对后续选矿设备造成严重破环的问题，提出一种改进YOLOv3的矿石输送带杂物检测方法YOLO-Ore。将轻量级网络Mobilenetv2作为主干特征提取网络，利用深度可分离卷积和逆残差结构，缩减了模型容量，丰富了特征信息；将语义分割网络PSPnet中的金字塔池化模块PPM融入到特征提取过程当中，有效聚合不同尺度的上下文信息；引入注意力机制CBAM，同时在空间维度和通道维度上进行特征增强；对YOLOv3的FPN结构简化，删减参数冗余的卷积层，实现进一步的模型压缩。利用数据增广技术构建矿石杂物数据集，并对所提方法的有效性进行实验对比验证。结果表明，和原YOLOv3算法相比，所提方法YOLO-Ore能够准确快速地检测矿石输送带杂物。

关键词: 目标检测, 深度可分离卷积, 轻量级, 特征融合, 注意力机制

Abstract:

Aiming at the problem that the waste wood, steel chisel, plastic pipe and other sundries on the ore conveyor belt will cause serious damage to the subsequent mineral processing equipment, this paper proposes an improved object detection algorithm YOLO-Ore based on YOLOv3 to identify these sundries. The lightweight network Mobilenetv2 is used as the backbone feature extraction network, and the deep separable convolution and inverse residual structure are used to reduce the model capacity and enrich the feature information. The pyramid pooling module PPM in the semantic segmentation network PSPnet is integrated into the feature extraction process to effectively aggregate contextual information of different scales. The attention mechanism CBAM is used to enhance the features in the spatial and channel dimensions at the same time. The FPN structure of YOLOv3 is simplified by deleting the convolutional layer of redundant parameters to achieve further model compression. The dataset of ore sundries is constructed by the data augmentation technology, and the effectiveness of the proposed method is compared and verified by experiments. The results show that, compared with the original YOLOv3 algorithm, the proposed method YOLO-Ore can detect sundries on the ore conveyor belt accurately and quickly.

Key words: object detection, depthwise separable convolution, lightweight, feature fusion, attention mechanism

薄景文，张春堂，樊春玲，李海菊. 改进YOLOv3的矿石输送带杂物检测方法[J]. 计算机工程与应用, 2021, 57(21): 248-255.

BO Jingwen, ZHANG Chuntang, FAN Chunling, LI Haiju. Ore Conveyor Belt Sundries Detection Based on Improved YOLOv3[J]. Computer Engineering and Applications, 2021, 57(21): 248-255.

参考文献

[1] 李伟山，卫晨，王琳.改进的Faster RCNN煤矿井下行人检测算法[J].计算机工程与应用，2019，55（4）：200-207.
LI W S，WEI C，WANG L.Improved faster RCNN approach for pedestrian detection in underground coal mine[J].Computer Engineering and Applications，2019，55（4）：200-207.
[2] WEI X，ZHANG H，LIU S，et al.Pedestrian detection in underground mines via parallel feature transfer network[J].Pattern Recognition，2020，103：107195.
[3] 张春堂，管利聪.基于SSD-MobileNet的矿工安保穿戴设备检测系统[J].工矿自动化，2019，45（6）：96-100.
ZHANG C T，GUAN L C.Target detection system of miner security wearing equipment based on SSD-MobileNet[J].Industry and Mine Automation，2019，45（6）：96-100.
[4] 李现国，李斌，刘宗鹏，等.井下视频行人检测方法[J].工矿自动化，2020，46（2）：54-58.
LI X G，LI B，LIU Z P，et al.Underground video pedestrian detection method[J].Industry and Mine Automation，2020，46（2）：54-58.
[5] 吕鹏飞，何敏，陈晓晶，等.智慧矿山发展与展望[J].工矿自动化，2018，44（9）：84-88.
LYU P F，HE M，CHEN X J，et al.Development and prospect of wisdom mine[J].Industry and Mine Automation，2018，44（9）：84-88.
[6] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[7] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1440-1448.
[8] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，39（6）：1137-1149.
[9] HE K，GKIOXARI G，DOLLáR P，et al.Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2961-2969.
[10] LIU W，ANGUELOV D，ERHAN D，et al.Ssd：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[11] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[12] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[13] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[14] SANDLER M，HOWARD A，ZHU M，et al.Mobilenetv2：Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：4510-4520.
[15] ZHAO H，SHI J，QI X，et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2881-2890.
[16] WOO S，PARK J，LEE J Y，et al.Cbam：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：3-19.
[17] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[18] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[19] ZHOU X，WANG D，KR?HENBüHL P.Objects as points[J].arXiv：1904.07850，2019.
[20] ZHAO Q，SHENG T，WANG Y，et al.M2det：a single-shot object detector based on multi-level feature pyramid network[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019，33（1）：9259-9266.
[21] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.Yolov4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.