Autonomous Multiple Tramp Materials Detection in Raw Coal Using Single-Shot Feature Fusion Detector

Dongjun Li,Lili Xu,Guoying Meng,Zhiyuan Sun

doi:10.3390/app12010107

Abstract

In the coal mining process, various types of tramp materials will be mixed into the raw coal, which will affect the quality of the coal and endanger the normal operation of the equipment. Automatic detection of tramp materials objects is an important process and basis for efficient coal sorting. However, previous research has focused on the detection of gangue, ignoring the detection of other types of tramp materials, especially small targets. Because the initial Single Shot MultiBox Detector (SSD) lacks the efficient use of feature maps, it is difficult to obtain stable results when detecting tramp materials objects. In this article, an object detection algorithm based on feature fusion and dense convolutional network is proposed, which is called tramp materials in raw coal single-shot detector (TMRC-SSD), to detect five types of tramp materials such as gangue, bolt, stick, iron sheet, and iron chain. In this algorithm, a modified DenseNet is first designed and a four-stage feature extractor is used to down-sample the feature map stably. After that, we use the dilation convolution and multi-branch structure to enrich the receptive field. Finally, in the feature fusion module, we designed cross-layer feature fusion and attention fusion modules to realize the semantic interaction of feature maps. The experiments show that the module we designed is effective. This method is better than the existing model. When the input image is 300 × 300 pixels, it can reach 96.12% MAP and 24FPS. Especially in the detection of small objects, the detection accuracy has increased by 4.1 to 95.57%. The experimental results show that this method can be applied to the actual detection of tramp materials objects in raw coal.

Highlights

Due to the limitations of equipment and technology, tramp materials such as gangue, bolt, stick, iron sheet, and iron chain will be mixed into the raw coal in the mining process [1,2]
As the most important solid waste generated during coal mining, gangue will affect the calorific value of coal during the combustion process and cause environmental pollution [4]
8.3 and 6.9% higher than that of Single Shot MultiBox Detector (SSD) and 6.9% higher than that of DSSD, which shows that the three modules—multi-branch dilation convolution structure (MDCS), cross-layer feature fusion module (CLFF) and attention fusion module (AFM)—designed to improve detection accuracy are effective

Summary

Introduction

Due to the limitations of equipment and technology, tramp materials such as gangue, bolt, stick, iron sheet, and iron chain will be mixed into the raw coal in the mining process [1,2]. This method mainly relies on the manual identification of objects, resulting in a poor working environment, high physical labor intensity, and low productivity, all of which endangers the health of miners, and is not in line with the intelligent development of mines. Other sorting methods, such as wet sorting, will use a lot of water and cause water pollution, while dry sorting has become

Methods

Results

Conclusion