| Proj No. | A3096-251 |
| Title | Comparison of AI/ML and Image processing algorithms for vehicle detection and tracking at traffic junctions for Smart land transportation system |
| Summary | With the rapid development of Smart Transportation Systems, vehicle detection and tracking play a crucial role in traffic management, congestion control, and autonomous driving. This project aims to compare traditional Image Processing techniques with AI/ML-based approaches for vehicle detection and tracking in real-world traffic scenarios. This project focuses on evaluating various algorithms in terms of accuracy, processing speed, robustness, and computational efficiency to determine the best-suited method for smart land transportation systems. Student will be required to compare AI/ML-based Approaches, like Deep Learning (CNNs, YOLO, Faster R-CNN) with Traditional Image Processing Techniques like Edge Detection (Sobel, Canny, etc.), background subtraction, etc. to detect and track moving vehicles at traffic junctions. Open-source datasets like Cityscapes, KITTI, or Berkeley DeepDrive and Real-world video footage will be used for analysis. Expected Outcomes will include a detailed comparison of AI/ML and image processing approaches for their accuracy, efficiency, and real-time performance, which will lead to identify the best approach for vehicle detection and tracking at traffic junctions for smart transportation applications. |
| Supervisor | A/P Mohammed Yakoob Siyal (Loc:S2 > S2 B2A > S2 B2A 28, Ext: +65 67904464) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Information System Research Lab (Loc: S2-B3a-06) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |