A New Approach for Disparity Map Estimation from Stereo Image Sequences using Hybrid Segmentation Algorithm

In this paper, a stereo matching algorithm based on image segments is presented. We propose the hybrid segmentation algorithm that is based on a combination of the Belief Propagation and K-Means algorithms with aim to refine the final sparse disparity map by using a stereo pair of images. Firstly, a color based segmentation method is applied for segmenting the left image of the input stereo pair (reference image) into regions. The main aim of the segmentation is to simplify representation of the image into the form that is easier to analyze and is able to locate objects in images. Secondly, results of the segmentation are used as an input of the SIFT-SAD matching method to determine the disparity estimate of each image pixel. This matching algorithm is proposed by combining Scale Invariant Feature Transform (SIFT) with the Sum of Absolute Difference (SAD). Finally, the comparisons between the three robust feature detection methods: Scale Invariant Feature Transform (SIFT), Affine SIFT (ASIFT) and Speeded Up Robust Features (SURF) are presented. The obtained experimental results demonstrate that the performance of our method is competitive and the final disparity maps are close to the ground truth data.