| An Efficient Person Re-Identification Method Based on Deep Transfer Learning Techniques |
| Paper ID : 1024-ICCI2021 (R1) |
| Authors: |
|
Shimaa Saber *1, Khalid Amin2, Mohamed Hammad3 1Information Technology
Faulty of Computer and Information
Menofia University , Egypt 2Information Technology Faulty of Computer and Information Menofia University , Egypt 3Information Technology Department, Faculty of Computers and Information |
| Abstract: |
| Person re-identification (Re-ID) is a significant process in applications of video analysis. Several applications in different areas such as airports and stations are used multiple cameras in different places for monitoring and investigation, which are expensive and can be easily abused. Therefore, automatic person re-identification techniques are highly required. The main issue of this field is to find distinguishing features that represent the person. In this paper, we proposed an efficient method to extract the main features based on deep transfer learning technique for person re-identification system. In addition, we employed support vector classifier (SVC) as a separated classifier for final decision to increase the accuracy of the system. We employed several publicly available datasets, which are the main datasets used in person re-identification purposes in the literature. The proposed method achieved the best accuracy of 89.59% for rank-1, which outperforms the state-of the-art methods. Finally, the simulation results reveal that the proposed system is efficient prior to person re-identification. |
| Keywords: |
| person re-identification; transfer learning; SVC; deep learning; video analysis |
| Status : Paper Accepted |
