Person Re-Identification

Abstract

Abstract-Networks of smart cameras share large amounts of data to accomplish tasks such as re-identification. We propose a feature selection method that minimizes the data needed to represent the appearance of objects by learning the most appropriate feature set for the task at hand (person re-identification). The computational cost for feature extraction and the cost for storing the feature descriptor are considered jointly with feature performance in order to select cost-effective good features. This selection allows us to improve inter-camera re-identification while reducing the bandwidth that is necessary to share data across the camera network. We also rank the selected features in the order of effectiveness for the task to enable a further reduction of the feature set by dropping the least effective features when application constraints require this adaptation. We compare the proposed approach with state-of-the-art methods on the i-LIDS and VIPeR datasets and show that the proposed approach considerably reduces network traffic due to inter-camera feature sharing while keeping the re-identification performance at an equivalent or better level compared with the state of the art.

A new framework for Person Re-identification: Integrated level feature pattern (ILEP)

“…Person Re-identification (Person re-id) [4] is an inevitable activity for ensuring security in significant overpopulated areas or public places such as bus terminals, railway stations, airports, hospitals, universities, and malls. A good surveillance system with intelligence, multi-camera tracking [6], multi-camera activity analysis [7,8] and crowd counting [9,10] is required for locating a particular individual or a missed child/person among the large crowd.…”

“…The same theory was further implemented to re-identify objects for diverse applications such as logic [2] and psychology [3]. Later, the researchers worked on implementing this concept for person reidentification [4]. Though many works were reported on this area, effective implementation became quite challenging because of reasons like (1) Wearing similar attires by different people, (2) Variations in body shape because of occlusion and illumination conditions, (3) Different images taken at different viewpoints, (4) The picture capturing done with a camera of very low frame rate, and (5) Lack of accuracy in algorithm during real-time video detection.…”