| Proj No. | A2047-251 |
| Title | Temporal Point Cloud Analysis for Robust LiDAR-Based Gait Recognition |
| Summary | Gait is an essential biometric, which has the unique advantage of human identification at a distance without physical contact. Gait recognition is a promising biometric technique for human identification in surveillance and security applications. Unlike traditional camera-based methods, LiDAR sensors not only offer privacy-friendly, depth-based point cloud data that preserves geometric details without revealing appearance, but also perform well under challenging situations like low-light environments and long-distance recognition scenarios. However, most existing LiDAR-based gait recognition methods process point clouds frame-by-frame, neglecting the crucial temporal dynamics that play a significant role in accurately capturing and understanding gait patterns. This project aims to explore and develop novel representations and models for analyzing temporal dynamics in point cloud data, with the goal of enhancing the performance of gait recognition. By incorporating temporal information, the project seeks to overcome the limitations of traditional frame-by-frame processing, which often neglects the continuous nature of human motion. In this project, the student is required to explore and develop advanced point cloud data processing models to extract both motion and biometric features for gait recognition tasks. The student could start by investigating the use of deep learning models tailored to point cloud data, such as PointNet or other 3D CNN architectures. The developed model will be evaluated on the publicly available LiDAR datasets SUSTech1K. The students who wish to work on this project are strongly encouraged to contact the supervisor for more information before making the selection. |
| Supervisor | Prof Chang Chip Hong (Loc:S2 > S2 B2C > S2 B2C 97, Ext: +65 67905873) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | VIRTUS, IC Design Centre of Excellence (Loc: S3.2-B2 Tel 6592 1844) |
| Single/Group: | Single |
| Area: | Smart Electronics and IC design |
| ISP/RI/SMP/SCP?: |