In many visual tracking and surveillance systems, it is important to initialize a background model using a training video sequence which may include foreground objects. In such a c...
The ellipse Hough transform (EHT) is a widely-used technique. Most of the previous modifications to the standard EHT improved either the voting procedure that computes the absolut...
This paper describes a fast and robust approach to recovering structure and motion from video frames. It rst describes a robust recursive factorization method for ane projection...
Takeshi Kurata, Jun Fujiki, Masakatsu Kourogi, Kat...
We consider the problem of fitting linearly parameterized models, that arises in many computer vision problems such as road scene analysis. Data extracted from images usually cont...
Although RANSAC is the most widely used robust estimator in computer vision, it has certain limitations making it ineffective in some situations, such as the motion estimation prob...
Trung Ngo Thanh, Hajime Nagahara, Ryusuke Sagawa, ...