Illumination Invariant Dense Image Matching based on Sparse Features

In this paper we propose an algorithm for dense depth estimation based on a cost function, which is robust against changes in illumination. For this purpose, we utilize census transformation and Phase Congruency. The process of cost computation is supported by a triangle-based depth prediction approach using a set of matched feature points. These points can reliably be detected even under drastic changes in illumination. We demonstrate the performance of our approach on the challenging KITTI stereo dataset and a set of images with simulated changes. The results show that the concept achieves state-of-the-art on images with similar illumination conditions and is robust against changed conditions.

[1]  Thomas S. Huang,et al.  The importance of phase in image processing filters , 1975 .

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

[3]  Peter Kovesi,et al.  Image Features from Phase Congruency , 1995 .

[4]  Ingemar J. Cox,et al.  Dynamic histogram warping of image pairs for constant image brightness , 1995, Proceedings., International Conference on Image Processing.

[5]  H. Hirschmüller.  Stereo Processing by Semiglobal Matching and Mutual Information , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

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

[7]  Andreas Geiger,et al.  Efficient Large-Scale Stereo Matching , 2010, ACCV.

[8]  Sang Uk Lee,et al.  Robust Stereo Matching Using Adaptive Normalized Cross-Correlation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  C. Heipke,et al.  Multi-view dense matching supported by triangular meshes , 2011 .

[10]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

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

[12]  Sang Uk Lee,et al.  Robust stereo matching under radiometric variations based on cumulative distributions of gradients , 2013, 2013 IEEE International Conference on Image Processing.

[13]  Paul Newman,et al.  Illumination Invariant Imaging : Applications in Robust Vision-based Localisation , Mapping and Classification for Autonomous Vehicles , 2014 .

[14]  Seungryong Kim,et al.  Mahalanobis Distance Cross-Correlation for Illumination-Invariant Stereo Matching , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  Raquel Urtasun,et al.  Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation , 2014, ECCV.

[16]  Christian Heipke,et al.  Joint 3d Estimation of Vehicles and Scene Flow , 2015 .

[17]  Hongyang Chao,et al.  MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[18]  Cevahir Çigla.  Recursive edge-aware filters for stereo matching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Nabil Aouf,et al.  A Novel Image Representation via Local Frequency Analysis for Illumination Invariant Stereo Matching , 2015, IEEE Transactions on Image Processing.

[20]  Andreas Geiger,et al.  Object scene flow for autonomous vehicles , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Vincent Lepetit,et al.  TILDE: A Temporally Invariant Learned DEtector , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Xiaolong Hu,et al.  Autonomous Driving in the iCity—HD Maps as a Key Challenge of the Automotive Industry , 2016 .

[23]  Vijayan K. Asari,et al.  Histogram of oriented phase (HOP): a new descriptor based on phase congruency , 2016, Commercial + Scientific Sensing and Imaging.