Feilong Wang

Papers

Total Citations

H-Index

About

Feilong Wang is a researcher specializing in robot vision, RGB-D object recognition, and machine learning-based visual perception systems. His work sits at the intersection of computer vision and robotics, with a particular focus on developing efficient and discriminative representations that enable robots to better understand and interact with their environments. Wang's most impactful contribution, "Discriminative Bit Selection Hashing in RGB-D Based Object Recognition for Robot Vision" (2018, 9 citations), advances the efficiency of depth-augmented visual recognition by identifying compact binary representations from RGB-D data — a critical challenge in real-time robotic applications. Complementing this, his 2017 work on Feature Graph Fusion leverages Extended Jaccard Graphs and word embeddings to combine RGB and depth information for more robust robot recognition using Kinect sensors, demonstrating his broader interest in multimodal feature integration. Wang has also applied his expertise to practical robotics challenges, developing multiple color recognition methods for Rubik's Cube-solving robots, including the innovative Scatter Balance and Extreme Learning Machine (SB-ELM) approach. Collectively, his research reflects a consistent drive to bridge theoretical machine learning techniques with tangible robotic perception tasks, making him a noteworthy contributor to applied robot vision research.