Efficient Disparity Computation without Maximum Disparity for Real-Time Stereo Vision

Abstract

In order to improve the performance of correlation-based disparity computation of stereo vision algorithms, standard methods need to choose in advance the value of the maximum disparity (MD). This value corresponds to the maximum displacement of the projection of a physical point expected between the two images. It generally depends on the motion model, the camera intrinsic parameters and on the depths of the observed scene.In this paper, we show that there is no optimal MD value that minimizes the matching errors in all image regions simultaneously and we propose a novel approach of the disparity computation that does not rely on any a priori MD. Two variants of this approach will be presented. When compared to traditional correlation-based methods, we show that our approach improves not only the accuracy of the results but also the efficiency of the algorithm. A local energy minimization is also proposed for fast refinement of the results.An extensive comparative study with ground truth is carried out on classical stereo images and the results show that the proposed method clearly gives more accurate results and it is two times faster than the fastest possible implementation of traditional correlation-based methods.

Efficient stereo matching for moving cameras and decalibrated rigs

“…We compare our proposal to the method originally introduced in [4], which does not account for deviations of epipolar geometry. All in all, we show the performance of three different methods: …”

“…Our approach generalizes and extends the concepts proposed in [4]. 1) Definitions: For every pixel location p = (x, y)…”

“…The overall disparity-error (y-axis) of different stereo methods for growing values of the epipolar deviation (x-axis): the errors are percentages of disparities that differ by more than 1 from the ground truth. We tested the standard approach [4], our method (section III-A) and the optimized variant of our proposal (section III-C). 1) Standard: Our implementation of [4], which does not account for epipolar deviations.…”

“…We tested the standard approach [4], our method (section III-A) and the optimized variant of our proposal (section III-C). 1) Standard: Our implementation of [4], which does not account for epipolar deviations. 2) Our Method: Our implementation of the concepts presented in section III-A, which can handle very large deviations.…”

“…For this, we generalize and extend the concepts of the efficient disparity computation approach given in [4], which was originally designed for highly efficient disparity computation using accurately rectified image pairs. There, stereo matching is performed iteratively by alternating minimization and propagation phases at every pixel.…”