IMAGE-GUIDED NON-LOCAL DENSE MATCHING WITH THREE-STEPS OPTIMIZATION

Abstract. This paper introduces a new image-guided non-local dense matching algorithm that focuses on how to solve the following problems: 1) mitigating the influence of vertical parallax to the cost computation in stereo pairs; 2) guaranteeing the performance of dense matching in homogeneous intensity regions with significant disparity changes; 3) limiting the inaccurate cost propagated from depth discontinuity regions; 4) guaranteeing that the path between two pixels in the same region is connected; and 5) defining the cost propagation function between the reliable pixel and the unreliable pixel during disparity interpolation. This paper combines the Census histogram and an improved histogram of oriented gradient (HOG) feature together as the cost metrics, which are then aggregated based on a new iterative non-local matching method and the semi-global matching method. Finally, new rules of cost propagation between the valid pixels and the invalid pixels are defined to improve the disparity interpolation results. The results of our experiments using the benchmarks and the Toronto aerial images from the International Society for Photogrammetry and Remote Sensing (ISPRS) show that the proposed new method can outperform most of the current state-of-the-art stereo dense matching methods.

[1]  Qingxiong Yang,et al.  Stereo Matching Using Tree Filtering , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Ding Yuan,et al.  Cross-trees, edge and superpixel priors-based cost aggregation for stereo matching , 2015, Pattern Recognit..

[3]  Takeshi Naemura,et al.  Graph Cut Based Continuous Stereo Matching Using Locally Shared Labels , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[5]  Joost van de Weijer,et al.  Accurate Stereo Matching by Two-Step Energy Minimization , 2015, IEEE Transactions on Image Processing.

[6]  Yann LeCun,et al.  Computing the stereo matching cost with a convolutional neural network , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  D. Nistér,et al.  Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Chang-Su Kim,et al.  Consistent Stereo Matching Under Varying Radiometric Conditions , 2013, IEEE Transactions on Multimedia.

[9]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Xing Mei,et al.  On building an accurate stereo matching system on graphics hardware , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[11]  Xing Mei,et al.  Real-time local stereo via edge-aware disparity propagation , 2014, Pattern Recognit. Lett..

[12]  Pierre Boulanger,et al.  Radiometric invariant stereo matching based on relative gradients , 2012, 2012 19th IEEE International Conference on Image Processing.

[13]  In-So Kweon,et al.  Adaptive Support-Weight Approach for Correspondence Search , 2006, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[15]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

[16]  Jian Sun,et al.  Guided Image Filtering , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Jae Wook Jeon,et al.  Domain Transformation-Based Efficient Cost Aggregation for Local Stereo Matching , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[18]  Heiko Hirschmüller,et al.  Evaluation of Stereo Matching Costs on Images with Radiometric Differences , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Wen Gao,et al.  Local Stereo Matching with Improved Matching Cost and Disparity Refinement , 2014, IEEE MultiMedia.

[20]  Petros Daras,et al.  Enhanced disparity estimation in stereo images , 2015, Image Vis. Comput..

[21]  Cevahir Çigla,et al.  Information permeability for stereo matching , 2013, Signal Process. Image Commun..