Autonomous recognition and positioning of shield segments based on red, green, blue and depth information

Abstract

Automatic shield segment assembly can reduce intensive labour and increase tunnel boring efficiency. However, insufficient lighting and multi-interference environments significantly affect segment recognition and positioning accuracy. This study develops a highly reliable and low-cost recognition and positioning system, including both hardware and software, for segment markers based on real-time monocular vision and light-insensitive depth measurements. An improved discrete wavelet transform based on the HSV channels and an adaptive multiscale Retinex algorithm with colour recovery are developed to enhance image brightness and colour contrast. Compared to traditional feature matching, support vector machine recognition and classification increase the real-time recognition accuracy. One hundred full-scale and field tests were performed under the original, insufficient, and interferential lighting environments. The recognition time was approximately 0.7 s, and the recognition accuracy was higher than 90%. A grasping experiment verified the feasibility of the system.