查看文章

Detection and pose estimation of texture-less objects still faces several challenges such as foreground occlusions, background clutter, multi-instance objects, large scale and pose changes to name but a few. In this paper, we present an improved method for template-based detection and pose estimation of texture-less objects, LINEMOD, in order to improve the robustness of pose estimation with partial foreground occlusions. For template creation, we divided template divided into four equal parts. After this process, four patches of the template are matched independently of each other. And we use image pyramid searching method for fast template matching. We improve the accuracy of fine pose estimation. Experimental results show that our approach is more robust to estimate the pose of texture-less objects with partial foreground occlusions.