Classification based person identification in group living environment

In this research, we investigated a method of person identification in closed indoor environment, such as office or laboratory, under the condition which the members change their clothes day-by-day. Furthermore, we did not assume any constraint to posture or location of people even if a face of a person cannot be seen. This is a challenging problem due to the change of their pose and clothes cause serious intra-person variation of appearance. To deal with this problem, we used a recent visual object classification method with commonly available RGB-D camera. In particular, we employed a classifier based approach using Fisher vector representation with weakly labeled image dataset. We built the person classifier and we validated the effectiveness of our approach by experiments.