Finding disparity maps between stereo images is a well studied topic within computer vision. While both classical and machine learning approaches exist in the literature, they frequently struggle to correctly solve the disparity in regions with low texture, sharp edges or occlusions. Finding approximate solutions to these problem areas is frequently referred to as disparity refinement, and is usually carried out separately after an initial disparity map has been generated. In the recent literature, the use of Normalized Convolution in Convolutional Neural Networks have shown remarkable results when applied to the task of stereo depth completion. This thesis investigates how well this approach performs in the case of disparity refinement. Specifically, we investigate how well such a method can improve the initial disparity maps generated by the stereo matching algorithm developed at Saab Dynamics using a rectified stereo rig. To this end, a dataset of ground truth disparity maps was created using equipment at Saab, namely a setup for structured light and the stereo rig cameras. Because the end goal is a dataset fit for training networks, we investigate an approach that allows for efficient creation of significant quantities of dense ground truth disparities. The method for generating ground truth disparities generates several disparity maps for every scene measured by using several stereo pairs. A densified disparity map is generated by merging the disparity maps from the neighbouring stereo pairs. This resulted in a dataset of 26 scenes and 104 dense and accurate disparity maps. Our evaluation results show that the chosen Normalized Convolution Network based method can be adapted for disparity map refinement, but is dependent on the quality of the input disparity map.

Fusion of multiple stereo algorithms is performed in order to obtain accurate disparity segmentation. Reliable disparity map of real-time stereo images is estimated and disparity segmentation is performed for object detection purpose. First, stereo algorithms which have high performance in real-time applications are chosen among the algorithms in the literature and three of them are implemented. Then, the results of these algorithms are fused to gain better performance in disparity estimation. In fusion process, if a pixel has the same disparity value in all algorithms, that disparity value is assigned to the pixel. Other pixels are labelled as unknown disparity. Then, unknown disparity values are estimated by a refinement procedure where neighbourhood disparity information is used. Finally, the resultant disparity map is segmented by using mean shift segmentation. The proposed method is tested in three different stereo data sets and several real stereo pairs. The experimental results indicate an improvement for the stereo analysis performance by the usage of fusion process and refinement procedure. Furthermore, disparity segmentation is realized successfully by using mean shift segmentation for detecting objects at different depth levels.