Affordable Access

Application of Reliability Methods in Hydrodynamical Modelling

Publication Date


Adaptive Non-Local Means for Cost Aggregation in a Local Disparity Estimation Algorithm Casper Pedersen, Kamal Nasrollahi, and Thomas B. Moeslund Visual Analysis of People Laboratory, Aalborg University Sofiendalsvej 11, 9200 Aalborg, Denmark Email:[email protected] Abstract—The overall method used for determining disparity in a stereo setup is a widely recognized framework consist- ing of four steps of cost space computation, cost aggregation, disparity selection, and post-processing. In this paper a cost aggregation approach for a typical local disparity estimation method is introduced. The method introduced is built on top of an existing method called Adaptive Support-Weight using this known framework. The introduced method improves Adaptive Support-Weight method by utilizing a larger amount of data inspired by the method of Non-Local Means. The extra data is handled in a way that tries to preserve the location of depth discontinuities in the final disparity map. Experimental results on Middlebury benchmark database show that the proposed method suffers from less artifacts compared to state-of-the-art disparity estimation methods. I. INTRODUCTION The task of disparity estimation has been widely researched for a number of years. It is in almost every case presented as a task of finding corresponding pixels between two images. These two images are typically taken by two cameras in a stereo setup where the cameras are aligned horizontally. The task of finding the disparity of a pixel in one image can thereby give the depth of what that pixel is conveying in the scene indirectly if the baseline between the cameras is known. This is utilized in many applications. There are two main approaches that are used for finding per pixel correspondence between two images. There are global approaches which try to determine the disparity of more than one pixel at a time. This is seen in a lot of works where the focus is on an accurate disparity map, for example in [1], [4], [11]. In [1] dynamic

There are no comments yet on this publication. Be the first to share your thoughts.