| Proj No. | A3200-251 |
| Title | Exploring Visual Cognition Capabilities of AI Agents via Bio-inspired Cameras |
| Summary | This project explores the potential of bio-inspired cameras to enhance the visual cognition capabilities of AI agents. Traditional computer vision systems rely heavily on frame-based cameras, which have limitations in terms of power efficiency, temporal resolution, and the processing of motion. This research will utilize event-based cameras—a bio-inspired alternative offering asynchronous, high-temporal-resolution data—to investigate their impact on an AI agent's visual perception and understanding. The project will design and implement AI agents equipped with bio-inspired visual processing mechanisms and evaluate their performance on a range of tasks, including object recognition, motion tracking, and scene understanding. The comparative analysis between agents using bio-inspired cameras and those using traditional frame-based cameras will reveal the advantages and limitations of the bio-inspired approach. |
| Supervisor | Ast/P Wang Lin (Loc:S2 > S2 B2C > S2 B2C 91, Ext: +65 67905629) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Internet of Things Laboratory (Loc: S1-B4c-14, ext: 5470/5475) |
| Single/Group: | Single |
| Area: | Intelligent Systems and Control Engineering |
| ISP/RI/SMP/SCP?: |