3D Reconstruction of Underground Tunnel Using Kinect Camera

The underground structure of coal mine is intricate for non-uniform illumination. Establish a three dimensional model for underground environment has received significant attention and concern during the recent years. There is a high requirements for the quality of underground monitoring images in coal mine to ensure safe and efficient production. In this paper, the RGB image and depth image are obtained by Kinect camera. The acquired RGB and depth maps are filtered for removing noise point or outliers. The feature points of the depth image are extracted to realize the precise matching between the RGB image and the depth image. Point clouds are obtained and registered into a single position using improved Iterative Closest Point algorithm. The experimental results show the effectiveness and practicability of the proposed method. Accurate 3D reconstruction of the object has been achieved with dense point cloud.