Zhang Handuo is currently a Ph.D student in Nanyang Technological University. His research interest is localization and machine learning on robot vision. Currently he is involved in a stereo vison based project for unmanned ground vehicle.
PhD in 3D Robot Vision, 2016
Nanyang Technological University
MEng in Pattern Recognition, 2011
BSc in Automation, 2007
Assistance Research in the State Key Laboratory of Robotics, in charge of:
Conventional SLAM algorithms takes a strong assumption of scene motionlessness, which limits the application in real environments. This paper tries to tackle the challenging visual SLAM issue of moving objects in dynamic environments. We present GMC, grid-based motion clustering approach, a lightweight dynamic object filtering method that is free from high-power and expensive processors. GMC encapsulates motion consistency as the statistical likelihood of detected key points within a certain region. Using this method can we provide real-time and robust correspondence algorithm that can differentiate dynamic objects with static backgrounds. We evaluate our system in public TUM dataset. To compare with the state-of-the-art methods, our system can provide more accurate results by detecting dynamic objects.