Shichao Kan

Papers

Total Citations

H-Index

About

Shichao Kan is a researcher at the forefront of computer vision and deep learning, with a focused expertise in real-time object detection for challenging environments. His most impactful work centers on advancing the YOLO (You Only Look Once) family of algorithms, particularly for underwater applications. Kan’s landmark paper, "Real-time underwater target detection based on improved YOLOv7" (2025), has already garnered 10 citations, demonstrating its immediate relevance and influence. In this work, he introduced critical architectural enhancements to YOLOv7, such as optimized feature extraction and attention mechanisms, enabling robust detection of marine targets under low-light, turbid conditions. This contribution not only pushes the boundaries of autonomous underwater robotics and marine monitoring but also provides a practical framework for deploying high-speed, accurate vision systems in resource-constrained settings. Kan’s research bridges the gap between theoretical model improvements and real-world deployment, making him a key figure in applied deep learning. His work is essential reading for students and engineers seeking to understand how state-of-the-art detection models can be adapted for specialized, non-ideal environments.