Delong Li
Papers
1
Total Citations
3
H-Index
1
About
Delong Li is a researcher in computer vision and embedded systems, with a focus on real-time object and pedestrian detection. His most-cited work, "Real Time Pedestrian Detection-based Faster HOG/DPM and Deep Learning Approaches" (2020), demonstrates the feasibility of integrating classical feature extraction methods—such as Histogram of Oriented Gradients (HOG) and Deformable Part Models (DPM)—with modern deep learning techniques for efficient embedded vision applications. This work addresses the critical challenge of balancing accuracy and computational speed in resource-constrained environments, making it relevant for autonomous systems and surveillance. While his citation count is modest, Li’s contributions highlight a practical pathway for deploying advanced detection algorithms in real-world, low-power devices. His research bridges traditional computer vision and deep learning, offering insights for engineers and scientists working on edge computing and intelligent transportation systems. Li’s work underscores the ongoing importance of optimizing detection pipelines for real-time performance, a key area in the evolution of embedded AI.
Research Focus
Key Achievements
Top Papers
- 1