A Ground Segmentation Method Based on Point Cloud Map for Unstructured Roads
This addresses ground segmentation for unmanned vehicles in challenging unstructured environments, representing an incremental improvement over existing methods.
The paper tackles ground segmentation in unstructured road scenes like open-pit mines, where irregular boundaries cause errors, by proposing a method based on point cloud map with region extraction, registration, and background subtraction, achieving a correct segmentation rate of 99.95% and a 7.43% accuracy improvement over Patchwork++.
Ground segmentation, as the basic task of unmanned intelligent perception, provides an important support for the target detection task. Unstructured road scenes represented by open-pit mines have irregular boundary lines and uneven road surfaces, which lead to segmentation errors in current ground segmentation methods. To solve this problem, a ground segmentation method based on point cloud map is proposed, which involves three parts: region of interest extraction, point cloud registration and background subtraction. Firstly, establishing boundary semantic associations to obtain regions of interest in unstructured roads. Secondly, establishing the location association between point cloud map and the real-time point cloud of region of interest by semantics information. Thirdly, establishing a background model based on Gaussian distribution according to location association, and segments the ground in real-time point cloud by the background substraction method. Experimental results show that the correct segmentation rate of ground points is 99.95%, and the running time is 26ms. Compared with state of the art ground segmentation algorithm Patchwork++, the average accuracy of ground point segmentation is increased by 7.43%, and the running time is increased by 17ms. Furthermore, the proposed method is practically applied to unstructured road scenarios represented by open pit mines.