Adaptive Occlusion Boundary Extraction for Depth Inference

In this paper, we propose an adaptive occlusion boundary extraction method for depth inference based on an adaptive segmentation and classification. First, an Adaptive DRW is proposed to generate more precise seeds and adaptive segmentation results, which can improve the feature quality and lower the boundary imbalance degree. Then, to deal with the imbalanced classification, we design a cost-sensitive boosting method–Adaptive AdaCost to better classify the imbalanced boundary, which can further improve overall performance and lower the cumulative misclassification cost and cost upper bound. Benefited from our Adaptive DRW and AdaCost, we extract more reliable and precise occlusion boundaries and use them for depth inference. The experiment results demonstrate that the combination of our Adaptive DRW and Adaptive AdaCost can produce more precise occlusion boundaries, and the depth inference result with our occlusion boundaries can be greatly improved.

[1]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[2]  Nuno Vasconcelos,et al.  Cost-sensitive Boosting Cost-sensitive Boosting , 2007 .

[3]  Luc Van Gool,et al.  SEEDS: Superpixels Extracted via Energy-Driven Sampling , 2012, ECCV.

[4]  Philippe Salembier,et al.  From local occlusion cues to global monocular depth estimation , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yang Wang,et al.  Parameter Inference of Cost-Sensitive Boosting Algorithms , 2005, MLDM.

[7]  Nuno Vasconcelos,et al.  Cost-Sensitive Boosting , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Eric Granger,et al.  Loss factors for learning Boosting ensembles from imbalanced data , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[9]  Kai Ming Ting,et al.  A Comparative Study of Cost-Sensitive Boosting Algorithms , 2000, ICML.

[10]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Tsuhan Chen,et al.  A learning-based framework for depth ordering , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Lei Zhu,et al.  Dynamic Random Walk for Superpixel Segmentation , 2018, ACCV.

[13]  Alexei A. Efros,et al.  Recovering Surface Layout from an Image , 2007, International Journal of Computer Vision.

[14]  Mohamed R. Amer,et al.  Monocular Extraction of 2.1D Sketch Using Constrained Convex Optimization , 2014, International Journal of Computer Vision.

[15]  Xuelong Li,et al.  Lazy Random Walks for Superpixel Segmentation , 2014, IEEE Transactions on Image Processing.

[16]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Salvatore J. Stolfo,et al.  AdaCost: Misclassification Cost-Sensitive Boosting , 1999, ICML.

[18]  Philippe Salembier,et al.  Occlusion-based depth ordering on monocular images with Binary Partition Tree , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Philippe Salembier,et al.  Monocular Depth Ordering Using T-Junctions and Convexity Occlusion Cues , 2013, IEEE Transactions on Image Processing.

[20]  Sabine Süsstrunk,et al.  Superpixels and Polygons Using Simple Non-iterative Clustering , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Alexei A. Efros,et al.  Recovering Occlusion Boundaries from an Image , 2011, International Journal of Computer Vision.

[22]  Rama Chellappa,et al.  Entropy rate superpixel segmentation , 2011, CVPR 2011.

[23]  Yong-Jin Liu,et al.  A global energy optimization framework for 2.1D sketch extraction from monocular images , 2014, Graph. Model..