Dhaval Shah
Papers
1
Total Citations
2
H-Index
1
About
Dhaval Shah is a researcher at the forefront of embedded computer vision and edge AI, with a focus on real-time object detection for autonomous systems. His most-cited work, "SD-YOLOv5: Implementation of Real-Time Staircase Detection on Jetson Nano Board" (2025), demonstrates a practical application of lightweight deep learning models on resource-constrained hardware. By adapting the YOLOv5 architecture for staircase detection, Shah addresses a critical challenge in assistive robotics and autonomous navigation—enabling low-power devices to perceive complex environments with speed and accuracy. This contribution has already garnered early citations, signaling its relevance to the growing field of edge AI. Shah’s research bridges the gap between algorithmic efficiency and hardware deployment, offering scalable solutions for real-world scenarios such as robotic mobility aids and smart infrastructure. His work exemplifies how optimizing neural networks for embedded platforms can democratize advanced perception capabilities, making them accessible for cost-sensitive and energy-constrained applications. As the demand for on-device intelligence surges, Shah’s innovations in real-time detection on compact boards like the Jetson Nano position him as a key contributor to the next generation of autonomous and assistive technologies.
Research Focus
Key Achievements
Top Papers
- 1