Unsupervised semantic video objects segmentation over optical-flow field
Kai‐Kuang Ma, Haiyun Wang · 2004
An unsupervised semantic video objects segmentation system is introduced in this paper, which is a region-based non-parametric spatio-temporal approach over optical-flow field. The proposed method overcomes multiple drawbacks inherited in existing supervised pixel-based parametric schemes. The unsupervised mechanism is realized by extracting the phase of the optical-flow field and forming the phase histogram to identify the number of dominant video objects contained within the video frame. Through extensive simulations, dominant video objects are automatically detected and segmented with high accuracy. The segmented VOs have semantic meaning that matches human being's perception; thus, the proposed segmentation system should be very useful to many applications encountered in multimedia, virtual reality and computer vision.