Shaokai Wu

Papers

Total Citations

H-Index

About

Shaokai Wu has made impactful contributions at the intersection of computer vision and industrial automation, with a particular focus on developing efficient, lightweight object detection models for real-world applications. His most-cited work, "An Industrial Meter Detection Method Based on Lightweight YOLOX-CAlite" (2023), addresses a critical need in inspection robotics: the automatic detection and identification of pointer meters in challenging environments such as pumping stations, substations, and laboratories. By proposing the YOLOX-CAlite algorithm, Wu tackled the persistent problem of performance degradation when detecting small, densely arranged targets under varying lighting and occlusion conditions. This work has already garnered 5 citations, reflecting its relevance to both researchers and practitioners in industrial IoT and smart infrastructure. Wu’s research is notable for bridging the gap between cutting-edge deep learning architectures and the practical constraints of edge deployment, ensuring that high-accuracy detection can run on resource-limited robotic platforms. His contributions are helping to advance the reliability and autonomy of inspection systems, with potential applications in safety monitoring and predictive maintenance across critical industries.