A method of object tracking based on particle filter and optical flow
Takahiro Kodama, Teruo Yamaguchi, Hiroshi Harada · 2009 ICCAS-SICE · 2009
In this paper, we propose the technique for tracking the velocity of objects that combines the particle filter with optical flow. If color of the target or feature of its shape is unknown, some conventional particle filters are hard to apply because the prediction step of them are based on probabilistic theory. This problem can be solved by estimation method of optical flow. Experimental results show that unstructured objects can be tracked.