Fangjun Kuang

Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Fangjun Kuang is a researcher at the forefront of intelligent robotics and computer vision, with a primary focus on target tracking and visual saliency. His most-cited work, "The Research and Application of Visual Saliency and Adaptive Support Vector Machine in Target Tracking Field" (2013, 7 citations), tackles the critical challenge of enabling mobile robots to reliably track objects in unpredictable environments. Kuang's key contribution lies in integrating visual saliency—the ability to identify the most visually prominent regions in a scene—with an adaptive Support Vector Machine (SVM) classifier. This hybrid approach addresses persistent issues in real-world tracking, such as illumination changes, target shape deformation, and state estimation uncertainty, which often degrade performance in traditional algorithms. By dynamically adjusting the SVM to environmental variations, his method enhances robustness and accuracy, offering a practical solution for autonomous navigation and surveillance systems. Though his citation count is modest, Kuang's work provides a foundational step for more adaptive and resilient tracking systems, directly impacting the development of intelligent robots that must operate in complex, changing settings. His research continues to inspire advancements in visual perception for autonomous agents.