Computer vision detection of foreign objects in coal processing using attention CNN. (June 2021)

• Record Type: Journal Article
• Authors: Zhang, Kanghui; Wang, Weidong; Lv, Ziqi; Fan, Yuhan; Song, Yang
• Is Part Of: Engineering applications of artificial intelligence. Volume 102(2021)
• Publication Date: 2021-06
• Subjects: Foreign object detection -- Model uncertainties -- Attention mechanisms -- Visualization; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104242
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Foreign objects in coal seriously affect the efficiency and safety of clean coal production. Currently, the removal of foreign objects in coal preparation plant mainly depends on manual picking, which has disadvantages of high labor intensity and low efficiency. Therefore, there is an urgent need for rapid detection and removal of foreign objects. However, due to the inference of the background and surround objects, it is a challenge for the accurate detection of foreign objects. In this study, a convolutional neural network (CNN) with attention modules was designed to accurately segment foreign objects from a complex background in real-time. The proposed network consists of an encoder and a decoder, and the attention mechanism was introduced into the decoder to capture rich semantic information. The visualization results proved that the attention modules could focus on the features of the salient region and inhibit the irrelevant background, which significantly improved the accuracy of the detection The results showed that the proposed model correctly recognized 97% of the foreign objects in the 1871 sets of test images. The mean intersection over union (MIOU) of the optimal model was 91.24%, and the inference speed was greater than 15 fps/s, which satisfied the real-time requirement. Graphical abstract: Highlights: An attention CNN for the detection of foreign objects was designed. The model uncertainties were introduced for the prediction results. The challenges of foreign object detection in coal was revealed. The feature extraction process of attention CNN was visualized. The performance of CNN before and after attention modules introduced was compared.