IEEE 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET 2016)

181 / 2015-11-30 21:17:58

An Improved Faulting Detection Algorithm for Subway Tunnel Segment

faulting, deep learning, depth image, classification and recognition, convolution operation

Novel security detection technology are needed to meet the growing demand of subway operation. In this paper, an improved faulting detection algorithm for subway tunnel segment is proposed. A combined denoising technique is used to convert the depth image of faulting acquired by Kinect into binary image of the height difference which can be processed by digital image. The obvious advantage of this method is that it can avoid the interference of environmental light and improve the detection speed. In addition, we focus on how to classify and identify different types of faulting line based on the idea of deep learning algorithm. And a fast CNN (convolution neural network) has been built to classify and identify faulting line. Finally, it shows that the proposed algorithm is effective through the experimental data.