Unsupervised thermal-to-visible domain adaptation method for pedestrian detection

Abstract

—Pedestrian detection is a common task in the research area of video analysis and its results lay the foundations of a wide range of applications. It is commonly known that under challenging illumination and weather conditions, conventional visible cameras perform poorly and this limitation could be catered using thermal imagery. But, due to the fact that annotated thermal datasets are less available compared to the visible ones, in this paper we emphasis the need for leveraging information from both domains at no additional annotation cost. Precisely, we propose a domain adaptation method by incorporating feature distribution alignments into Faster R-CNN architecture at different levels and at different stages of the network. The resulting proposed thermal-to-visible adaptive detector has the advantage of covering different aspects of the domain shift in order to improve the overall performance. The proposed detector is evaluated on KAIST multispectral dataset and the obtained re-sults demonstrate its effectiveness by improving the adaptability in the thermal domain. Also, by means of comparisons to other existing works, better results are obtained.