Scene Segmentation from 3D Motion and Category-Specific Information

2009 
In this paper we address the problem of detecting objects from a moving camera by jointly considering low-level image features and high-level object information. The proposed method partitions an image sequence into independently moving regions with similar 3-dimensional (3D) motion and distance to the observer. In the recognition stage, category-specific information is integrated into the partitioning process. An object category is represented by a set of descriptors expressing the local appearance of salient object parts. To account for the geometric relationships among object parts, a structural prior over part configurations is designed. This prior structure expresses the spatial dependencies of object parts observed in a training data set. To achieve global consistency in the recognition process, information about the scene is extracted from the entire image based on a set of global image features. These features are used to predict the scene context of the image from which characteristic spatial distributions and properties of an object category are derived. The scene context helps to resolve local ambiguities and achieves locally and globally consistent image segmentation. Segmentation results are presented based on real image sequences.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    15
    References
    0
    Citations
    NaN
    KQI
    []