Shan Chang
Papers
1
Total Citations
5
H-Index
1
About
Shan Chang is an emerging researcher specializing in computer vision and autonomous perception systems, with a particular focus on monocular 3D object detection for mobile platforms. Their work addresses one of the most pressing challenges in modern robotics and autonomous driving: accurately inferring three-dimensional spatial information from a single camera feed, a notoriously difficult problem due to the inherent depth ambiguity of monocular vision. Chang's most notable contribution, "Exploiting Ground Depth Estimation for Mobile Monocular 3D Object Detection" (2025), tackles the compounding difficulties of near-far disparity and dynamic camera positioning — challenges that are critical for real-world deployment on vehicles, drones, and robots. By leveraging ground depth estimation as a geometric prior, this work offers a principled approach to improving detection accuracy for distant objects, a longstanding weakness in monocular systems. Although still early in their research career, with the paper accumulating 5 citations shortly after publication, Chang's contributions sit at the intersection of 3D scene understanding, mobile robotics, and deep learning — areas of rapidly growing importance. Their research holds strong implications for the advancement of cost-effective, camera-based perception systems in autonomous navigation and intelligent transportation.
Research Focus
Key Achievements
Top Papers
- 1