Spatio-Visual Fusion-Based Person Re-Identification for Overhead Fisheye Images

Person re-identification (PRID) has been thoroughly researched in typical surveillance scenarios where various scenes are monitored by side-mounted, rectilinear-lens cameras. To date, few methods have proposed for fisheye cameras mounted overhead and their performance is lacking. In order to close this gap, we propose a multi-feature framework PRID combine deep-learning, color-based location-based features means of novel feature fusion. We evaluate the our combinations on FRIDA, public dataset. The results demonstrate that approach outperforms recent appearance-based deep-learning almost 18% points 3% matching accuracy. also potential application people counting large, crowded indoor spaces.