Urban building recognition during significant temporal variations

In literature, existing researches on building recognition mainly concentrate on scales, rotations, and viewpoints variance. In urban environment, large temporal variations of weather and lighting conditions should also be considered as major challenges for robust recognition. For instances, there are differences between images captured during daytime and nighttime, especially significant changes in building appearances between seasons because of the differences in light setting. To date, these large temporal variation issues have not been fully investigated. In this paper, we therefore focus on constructing a system that deals with the temporal difference factors in recognizing urban buildings. In order to build such a system, two main criteria are raised, namely the efficiency of the recognition algorithm and the speed for interactive search purpose. For recognition purpose, we exploit the MOPS features (Multi-scale Oriented Patches) in [2], which extract features of patches around interest points. To speed up the searching process, we employ the vocabulary tree based search technique in [12]. Our final system shows high performance in recognizing buildings under significant temporal variations with a fast processing reaction.