Pixel wise segmentation of motion coherent particles

The survey describes an approach for object –oriented video segmentation based on motion coherence. Using a tracking process ,2-D motion patterns are identified with an ensemble clustering approach. Particles are clustered to obtain a pixel-wise segmentation in space and time domains. The limitation of the segmentation method concerning with complex 3-D spatial motion can be solved by using reality-based 3-D models. The reality-based 3-D models are produced with range-based, image-based or CAD modeling techniques. Each 3-D model can contain different levels of geometry and need therefore to be semantically segmented and organized in different ways. Index Terms-Ensemble clustering, motion segmentation, object-based video segmentation, point tracking, video coding, reality-based 3-D models.