Abstract—Occlusion detection is one of the key technologies for 3D texture reconstruction of multi-view images. In this paper, an efficient occlusion detection algorithm is proposed aiming at the existence fragments, seams in 3D texture mapping form multi-view images. Firstly, we reconstructed the 3D surface model form multi-view images. Then, based on the projection relationship between object point and image point, we proposed an occlusion detection algorithm based on OpenGL. At last, compared with the algorithm of occlusion detection based on sparse grid, the experimental results show that our method can better solve the problems of occlusion detection in 3D texture reconstruction based on multi-view images.
Index Terms—Z-buffer, OpenGL, sparse grid, multi-view image.
The authors are with the State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan, Hubei, 430074 China (e-mail: lisouming@ whu.edu.cn, 00201550@ whu.edu.cn, Zhangweilong@ whu.edu.cn).
Cite: Ming Li, Bingxuan Guo, and Weilong Zhang, "An Occlusion Detection Algorithm for 3D Texture Reconstruction of multi-View Images," International Journal of Machine Learning and Computing vol. 7, no. 5, pp. 152-155, 2017.