Video detection of foreign objects on the surface of belt conveyor underground coal mine based on improved SSD

  • PDF / 1,498,813 Bytes
  • 10 Pages / 595.276 x 790.866 pts Page_size
  • 101 Downloads / 248 Views

DOWNLOAD

REPORT


ORIGINAL RESEARCH

Video detection of foreign objects on the surface of belt conveyor underground coal mine based on improved SSD Yuanbin Wang1 · Yujing Wang1 · Langfei Dang1 Received: 11 March 2020 / Accepted: 27 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract Aiming at the problem of belt conveyor damage caused by the presence of foreign objects on the belt conveyor in coal mines, this paper proposed that video detection of foreign objects on the belt surface was performed based on SSD. Improvements on SSD network are made from following aspects. Firstly, the deep separable convolution method is used to reduce the amount of parameters in the SSD algorithm and improve the speed. Then, GIOU loss function is adopted instead of the position loss function in the original SSD to improve the detection accuracy. Finally, the extracted position of the feature map and the proportion of the default boxes are optimized to improve the detection accuracy. The experiment results show that the improved algorithm proposed in this paper is superior to the original SSD algorithm, the average accuracy rate has been increased from 87.1 to 90.2%, and the detection frame rate has been increased from 32 to 41 FPS.

1 Introduction Coal mine underground belt conveyor is the key equipment for underground coal transportation. In the process of coal transportation, foreign objects such as anchor rods, wooden blocks, wooden poles, and large blocks of coal often cause damage to the belt conveyor, resulting in the suspension of coal mine production and huge economic losses (Huqi 2015). Therefore, foreign objects on the belt conveyor, such as coal belt, large coal, anchor rods, wooden blocks, wooden poles, should be monitored real time to minimize the probability of the accident, the degree of impact, and the economic loss in coal mine enterprise. At present, the main methods for the detection of foreign objects on the belt conveyor are manual inspection, ray method and image recognition method. The manual inspection method requires workers to observe the belt surface of the belt by their eyes whole day, which is easy to cause visual fatigue of the workers and result in safety hazards in the coal mine. The ray method (Zengcai et al. 2002) uses the different energy absorbed by the reflection of the ray to

* Yujing Wang [email protected] * Langfei Dang [email protected] 1



Xi’an University of Science and Technology, Xi’an, China

identify coal and non-coal materials, but the relevant equipment used in this method is expensive and difficult to maintain; For image recognition method, image can be captured by a high-definition camera under the coal mine, and then detected by computer intelligently. This method is simple for installing and maintaining, and has high detection efficiency, so it has a wide application prospects. At present, machine vision-based foreign object detection algorithms are mainly divided into two categories. The first category is traditional target detection algorithms. This kind of algor