Wireless Multimedia Sensor Network Based Subway Tunnel Crack Detection Method

Abstract

Subway tunnel cracks directly reflect the structural integrity of a tunnel, and as such the detection of subway tunnel cracks is always an important task in tunnel structure monitoring. This paper presents a convenient, fast, and automated crack detection method based on a wireless multimedia sensor subway tunnel network. This method primarily provides a solution for image acquisition, image detection and identification of cracks. In order to quickly obtain a surface image of the tunnel, we used special train image sensor nodes to provide the high speed and high performance processing capability with a large-capacity battery. The proposed process can significantly reduce the amount of data transmission by compressing the binary image obtained by initial processing of the original image. We transferred the data compressed by the sensor to an appropriate station and uploaded them to a database when the train passes through the station. We also designed a fast, easy to implement fracture identification and detection image processing algorithm that can solve the image identification and detection problem. In real subway field tests, this method provided excellent performance for subway tunnel crack detection, and recognition.