PROJECT TITLE :
Person Re-Identification Based on Spatiogram Descriptor and Collaborative Representation
Feature and metric planning are two vital aspects in person re-identification. In this letter, we tend to firstly propose a completely unique spatiogram based mostly person descriptor. Such spatiograms of various image regions from many color channels are calculated and accumulated to create a histogram vector and 2 distinctive spatial statistical vectors. Secondly, through any investigating the multi-shot set-based metric primarily based on the recent collaborative representation model, we have a tendency to propose an effective and economical multi-shot metric, that fuses the residual and coding coefficients once collaboratively coding samples on all person classes. Finally, we evaluate the proposed descriptor and metric with other published strategies on benchmark datasets. Our strategies not only achieve state-of-the-art results however also are novel, easy and computationally efficient, which will facilitate the important-time surveillance applications such as pedestrian tracking.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here