基于颜色内相关和自适应支撑权重的立体匹配算法

Adaptive support weight (ASW) strategies in local stereo matching have recently attracted many researchers due to their compelling results. In this paper, we present an evaluation study that focuses on weight computation methods that have been suggested in the most recent literature. We implemented 9 ASW stereo methods and tested them on all (35) ground truth test stereo image pairs of the Middlebury benchmark. Our evaluation considers both the accuracy of the matching process and the computational efficiency of its GPU implementation. According to our results, high-quality matching results at real-time processing speeds can be achieved by using the guided image filter weights.

Video sensor networking technologies have developed very rapidly in the last ten years. In this paper, a cross-based framework strategy for cost aggregation is presented for the depth map estimation based on video sensor networks. We formulate the process as a local regression problem consisting of two main steps with a pair of video sensors. The first step is to calculate estimates for a set of points within a shape-adaptive local support region. The second step is to aggregate the matching cost for the gradient-based weight of the support region at the outmost pixel. The proposed algorithm achieves strong results in an efficient manner using the two main steps. We have achieved improvement of up to 6.9%, 8.4%, and 8.3%, when compared with adaptive support weight (ASW) algorithm. Comparing to cross-based algorithm, the proposed algorithm gives 2.0%, 1.3%, and 1.0% in terms of nonocclusion, all, and discontinuities, respectively.

A cross-based framework strategy for performance of gradient-based weight cost aggregation strategy is presented. We formulate the process as a local regression problem consisting of two main steps. The first step is to calculate estimates for a set of points within a shape-adaptive local support region. The second step is to aggregate the matching cost for the gradient-based weight of the support region at the outmost pixel. The proposed algorithm achieves strong results in an efficient manner using the two main steps. We have achieved improvement of up to 6.9%, 8.4% and 8.3%, when compared with Adaptive Support weight (ASW) algorithm. Comparing to Cross-based algorithm, the proposed algorithm gives 2.0%, 1.3% and 1.0% in terms of non-occlusion, all and discontinuities, respectively.

This paper presents a new local binocular stereo matching algorithm. A local window with adaptive support weights is used to aggregate matching costs. A more robust matching score is set up combining sum of absolute intensity differences and a gradient based measure. Each pixel has a different disparity search range according to disparity gradient analysis and computational complexity decreases rapidly. Experimental results using the Middlebury stereo test bed demonstrate the validity of our presented approach.

High-performance real-time stereo vision system is crucial to various stereo vision applications, such as robotics, autonomous vehicles, multiview video coding, freeview TV, and 3-D video conferencing. In this paper, we proposed a high-performance hardware-friendly disparity estimation algorithm called mini-census adaptive support weight (MCADSW) and also proposed its corresponding real-time very large scale integration (VLSI) architecture. To make the proposed MCADSW algorithm hardware-friendly, we proposed simplification techniques such as using mini-census, removing proximity weight, using YUV color representation, using Manhattan color distance, and using scaled-and-truncate weight approximation. After applied these simplifications, the MCADSW algorithm was not only hardware-friendly, but was also 1.63 times faster. In the corresponding real-time VLSI architecture, we proposed partial column reuse and access reduction with expanded window to significantly reduce the bandwidth requirement. The proposed architecture was implemented using United Microelectronics Corporation (UMC) 90 nm complementary metal-oxide-semiconductor technology and can achieve a disparity estimation frame rate of 42 frames/s for common intermediate format size images when clocked at 95 MHz. The synthesized gate-count and memory size is 563 k and 21.3 kB, respectively.

In a local and perceptual organization framework, a novel stereo correspondence algorithm is proposed to provide dense and accurate disparity maps under point ambiguity. First, the initial matching technique is based on raw matching cost obtained from local descriptor with contrast context histogram and two-pass cost aggregation via segmentation-based adaptive support weight. Second, the disparity estimation procedure consists sequentially of two steps: namely, a narrow occlusion handling and a multi-directional weighted least square (WLS) fitting for large occlusion. The experiment results indicate that our algorithm can increase robustness against outliers, and then obtain comparable and accurate disparity than other local stereo methods effectively, and it is even better than some algorithms using advanced and offline but computationally complicated global optimization based algorithms.KeywordsStereo visionstereo matchinglocal descriptorsegmentationparallel computingweighted least squarelarge occlusion

基于人眼视觉特性的自适应支持权重立体匹配算法