首页 > 论文 > 激光与光电子学进展 > 55卷 > 12期(pp:121004--1)

基于改进卷积神经网络的稠密视差图提取方法

Dense Disparity Map Extraction Method Based on Improved Convolutional Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对现有的卷积神经网络方法所生成的视差图中细节损失严重的问题, 提出了在结构上改进的新方法。将原有网络中特征提取部分的4层卷积结构提升到7层, 最大化提高了精度; 在网络中引入了双金字塔结构, 将多尺度降采样信息和特征信息进行了融合, 保持了输入图像中的原始细节信息。实验结果表明, 改进后网络的错误率从3.029%降到了2.795%, 生成的视差图具有更好的连通性。

Abstract

According to the problem of the severe detail loss of the disparity map generated by the current convolutional neural network methods, a structural improvement method is proposed. The 4 layers convolutional structure of the feature extraction part from original network is added to 7 layers to maximize the accuracy. And, the proposed dual pyramid structure is introduced to the network to combine the multi-scale down-sampling information with the feature information, which keeps the details of the original input images. Experimental results show that the error rate of the improved network reduces from 3.029% to 2.795%, and the generated disparity maps have better connectivity.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN911.73

DOI:10.3788/lop55.121004

所属栏目:图像处理

基金项目:微系统技术国防科技重点实验室基金(CXJJ-17S072)

收稿日期:2018-05-04

修改稿日期:2018-06-04

网络出版日期:2018-06-08

作者单位    点击查看

黄东振:中国科学院上海微系统与信息技术研究所微系统技术重点实验室, 上海 201800中国科学院大学, 北京 100049
赵沁:中国科学院上海微系统与信息技术研究所微系统技术重点实验室, 上海 201800中国科学院大学, 北京 100049
刘华巍:中国科学院上海微系统与信息技术研究所微系统技术重点实验室, 上海 201800
李宝清:中国科学院上海微系统与信息技术研究所微系统技术重点实验室, 上海 201800
袁晓兵:中国科学院上海微系统与信息技术研究所微系统技术重点实验室, 上海 201800

联系人作者:袁晓兵(sinowsn@mail.sim.ac.cn)

【1】Wang Q L, Li J Y, Shen H K. Target tracking system of binocular vision and laser range sensor[J]. Acta Optica Sinica, 2016, 36(9): 0912002.
王琪龙, 李建勇, 沈海阔. 双目视觉-激光测距传感器目标跟踪系统[J]. 光学学报, 2016, 36(9): 0912002.

【2】Scharstein D, Szeliski R, Zabih R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[C]∥Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision, 2001: 131-140.

【3】Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137.

【4】Hirschmuller H. Stereo processing by semiglobal matching and mutual information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2): 328-341.

【5】Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

【6】Bay H, Ess A, Tuytelaars T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

【7】Zhang X, Jin Y X, Xue D. Image matching algorithm based on SICA-SIFT and particle swarm optimization[J]. Laser & Optoelectronics Progress, 2017, 54(9): 091002.
张鑫, 靳雁霞, 薛丹. SICA-SIFT和粒子群优化的图像匹配算法[J]. 激光与光电子学进展, 2017, 54(9): 091002.

【8】Zhu S P, Yan L N, Li Z. Stereo matching algorithm based on improved Census transform and dynamic programming[J]. Acta Optica Sinica, 2016, 36(4): 0415001.
祝世平, 闫利那, 李政. 基于改进Census变换和动态规划的立体匹配算法[J]. 光学学报, 2016, 36(4): 0415001.

【9】LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.

【10】Zagoruyko S, Komodakis N. Learning to compare image patches via convolutional neural networks[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 4353-4361.

【11】bontar J, LeCun Y. Computing the stereo matching cost with a convolutional neural network[C]∥ IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 1592-1599.

【12】Zhang K, Lu JB, Lafruit G. Cross-based local stereo matching using orthogonal integral images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009, 19(7): 1073-1079.

【13】He KM, Sun J, Tang X O. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.

【14】Mei X, Sun X, Zhou M C, et al. On building an accurate stereo matching system on graphics hardware[C]∥ IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2011: 467-474.

【15】Li LC, Yu X, Zhang S L, et al. 3D cost aggregation with multiple minimum spanning trees for stereo matching[J]. Applied Optics, 2017, 56(12): 3411-3420.

【16】Li L C, Zhang S L, Yu X, et al. PMSC: PatchMatch-based superpixel cut for accurate stereo matching[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(3): 679-692.

【17】Park H, LeeK M. Look wider to match image patches with convolutional neural networks[J]. IEEE Signal Processing Letters, 2017, 24(12): 1788-1792.

【18】Fan B, Niu J C, Zhao J. Three-phase full-controlled rectifier circuit fault diagnosis based on optimized neural networks[C]∥ 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC), 2011: 6048-6051.

【19】Srivastava R K, Greff K, Schmidhuber J. Training very deep networks[C]∥Neural Information Processing Systems, 2015: 2377-2385.

【20】He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]∥ IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 770-778.

【21】Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]∥International Conference on Machine Learning, 2015: 448-456.

引用该论文

Huang Dongzhen,Zhao Qin,Liu Huawei,Li Baoqing,Yuan Xiaobing. Dense Disparity Map Extraction Method Based on Improved Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121004

黄东振,赵沁,刘华巍,李宝清,袁晓兵. 基于改进卷积神经网络的稠密视差图提取方法[J]. 激光与光电子学进展, 2018, 55(12): 121004

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF