Mapping 3D road model to 2D street-view video using Image and Semantic Feature Matching

Kuan-Ting Chen, Jheng-Wei Su, Kai-Wen Hsiao, Kuo-Wei Chen, Chih-Yuan Yao, Ruen-Rone Lee, Hung-Kuo Chu

Abstract: We propose a novel method to estimate the mapping between the 3D road model and the 2D street-view video. Our results show that our method can perform a high- quality 2D-to-3D mapping on various street-view videos.