Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (21): 248-255.DOI: 10.3778/j.issn.1002-8331.2105-0025

Previous Articles     Next Articles

Ore Conveyor Belt Sundries Detection Based on Improved YOLOv3

BO Jingwen, ZHANG Chuntang, FAN Chunling, LI Haiju   

  1. College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, Shandong 266100, China
  • Online:2021-11-01 Published:2021-11-04



  1. 青岛科技大学 自动化与电子工程学院,山东 青岛 266100


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



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