Detection of coal and gangue based on improved YOLOv5.1 which embedded scSE module. (January 2022)

• Record Type: Journal Article
• Authors: Yan, Pengcheng; Sun, Quansheng; Yin, Nini; Hua, Lili; Shang, Songhang; Zhang, Chaoyin
• Is Part Of: Measurement. Volume 188(2022)
• Publication Date: 2022-01
• Subjects: YOLOv5 -- Separation of coal-gangue -- Multispectral imagig -- Target detection; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.110530
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: The highlights of this paper are as follows: Our team use YOLOv5 algorithm to analyze the spectral images of coal gangue, and we have improved the algorithm based on YOLOv5 algorithm. It improves the accuracy of classification and recognition of coal gangue, and is of great significance to the separation of coal gangue industry. Abstract: Accurate identification of coal-gangue have great significance for separation of coal-gangue. The traditional coal-gangue identification method has the disadvantages of low accuracy and slow speed. Therefore, an intelligent classification method of coal-gangue based on multispectral imaging technology and target detection is proposed in this paper. According to the model structure of YOLOv5, add scSE module in CSPDarknet and CSP module. The improved YOLOv5 is referred to as YOLOv5.1. To begin with, the multispectral data of coal-gangue are collected, and the collected coal-gangue images are screened. Beside, three bands with high recognition rate and correlation are selected from 25 bands to form pseudo-RGB images. Otherwise, the RGB image of coal-gangue was detected by theYOLOv5.1. By detecting the separated single band, the recognition rate and correlation of band 6, 10 and 12 are higher. The experimental results show that the average accuracy of detecting coal-gangue in the test set reaches 98.34 %, and the detection time is about 3.62 s by using the model of YOLOv5.1 to train the RGB image of coal-gangue. This method can not only accurately identify coal-gangue, but also obtain the relative position of coal-gangue, which can be effectively used for coal-gangue identification.