Stereo matching and depth map collection algorithm based on deep learning

This paper elaborates the research on stereo matching and depth map collection algorithm based on deep learning, use the Torch deep learning framework based on Linux platform to build neural network. The neural network refers to open source algorithm to achieve the use of convolution neural network instead of the traditional algorithm to calculate the matching cost function. This paper also improves the structure of the convolution neural network by using different activation function and adding the batch normalization layer and other methods, reducing the error matching rate, and then get the disparity map and depth map by the post-processing algorithm which includes the matching cost aggregation, disparity computation, disparity refinement. Then the paper verified the effect of the algorithm by experiment and analyzed the experiment results, and used the Middlebury stereo algorithm evaluation platform to evaluate the algorithm. And finally the porposed algorithm gets better stereo matching effect than before.

[1]  Shiping Zhu,et al.  An Improved Inter-Frame Prediction Algorithm for Video Coding Based on Fractal and H.264 , 2017, IEEE Access.

[2]  Zheng Li,et al.  Stereo matching algorithm with guided filter and modified dynamic programming , 2015, Multimedia Tools and Applications.

[3]  Narendra Ahuja,et al.  Cresceptron: a self-organizing neural network which grows adaptively , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[4]  Kevin Skadron,et al.  Scalable parallel programming , 2008, 2008 IEEE Hot Chips 20 Symposium (HCS).

[5]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Chunyan Zhang,et al.  A fast algorithm of intra prediction modes pruning for HEVC based on decision trees and a new three-step search , 2017, Multimedia Tools and Applications.

[8]  Yann LeCun,et al.  Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches , 2015, J. Mach. Learn. Res..

[9]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[10]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[11]  Qiaosong Wang,et al.  Stereo vision–based depth of field rendering on a mobile device , 2014, J. Electronic Imaging.

[12]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[13]  Shiping Zhu,et al.  Local stereo matching algorithm with efficient matching cost and adaptive guided image filter , 2017, The Visual Computer.

[14]  Shiping Zhu,et al.  Spatiotemporal visual saliency guided perceptual high efficiency video coding with neural network , 2018, Neurocomputing.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Heiko Hirschmüller,et al.  Stereo Processing by Semiglobal Matching and Mutual Information , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[19]  Xi Wang,et al.  High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth , 2014, GCPR.

[20]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[21]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[22]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.