Multi-Person Re-Identification Based on Face, Pose and Texture Analysis in Unconstrained Videos

Abstract

We present a method for re-identification of images of multiple people that appear in 2D RGB video sequences. The method needs no initialization or supervision and works with unconstrained sequences that include camera shot transitions and strong visual variations. In order to preserve tracking along the frames, our method combines facial recognition, clothing texture analysis and pose detection to compute a distance between tracked people at frame t-1, and detected people at frame t. We use techniques based on Convolutional Neural Networks (CNNs) to extract this information from the people that appear in the images. The results obtained show that the proposed method achieves accurate tracking of the people even in those difficult sequences where faces appear occluded or people present similar textures.Index Terms-Multi-person re-identification, people tracking, Unconstrained tracking in videos

Disturbance and Plausibility in a Virtual Rock Concert: A Pilot Study

“…For the concert recreation we started from the video footage included in the live concert DVD "Alchemy" from Dire Straits (Figure 1 left). The members of the Dire Straits band were tracked using the method presented in [27]. This uses Convolutional Neural Networks (CNNs) to combine facial recognition, texture analysis and 2D poses and spatial information in order to track the main characters of the concert along the frames.…”