Abstract
To address the challenges posed by significant parallax, dynamic changes in monitoring camera positions, and the need for rapid wide-field image stitching in underground coal mine tunneling faces, this paper proposes a fast image stitching method for tunneling face images based on navigation and positioning data. First, using a pixel-based calculation approach, the tunneling face scene is partitioned into the cutting section and the ground, enhancing the reliability of scene segmentation. Then, the spatial distance between the camera and the cutting plane is computed based on the tunneling machine's navigation and positioning data, and a plane-induced homography model is employed to efficiently determine the dynamic transformation matrix of the cutting section. Finally, the Dual-Homography Warping (DHW) method is applied to achieve fast panoramic image stitching of the tunneling face. Comparative experiments with three classical stitching methods, SURF, SIFT, and BRISK, demonstrate that the proposed method reduces stitching time by 60%. Field experiments in underground environments verify that this method can generate a complete panoramic stitched image of the tunneling face, providing an unobstructed perspective beyond the machine body and cutting head to clearly observe the shovel plate and surrounding ground conditions, significantly enhancing the visibility and convenience of remote operation.