Object-based disparity estimation for stereoscopic images

Disparity estimation has been a critical procedure in stereoscopic or multiview video processing. In this paper, we present an object-based disparity estimation algorithm capable of providing an accurate disparity map from a stereo pair effectively. The algorithm involves a preprocessing step, which identifies the foreground object, and a predictive hierarchical block matching with different parameters for foreground and background. Left-to-right disparity map is calculated, the right image is used as a reference and the left image is reconstructed at the receiver end. The algorithm has been tested and the quality of the reconstruction using the disparity map demonstrates its effectiveness.