Multi-Scale Aggregation Stereo Matching Network Based on Dense Grouping Atrous Convolution
Source abstract
Abstract
The key to image depth estimation is to accurately find corresponding points between the left and right images. A binocular camera can directly estimate the depth of the left and right image range, which completely avoids the requirement of target recognition accuracy in a monocular depth estimation. However, it is difficult for binocular stereo matching to accurately segment objects and find matching points in the ill-posed areas (weak texture, deformation, object edge, etc.) of the left and right images. In the semantic segmentation task, atrous convolution is used to solve the contradiction between the receptive field and the segmentation accuracy. This research focused on balancing the impact of holes on the segmentation task. In addition, in order to solve the issue where matching points in the ill-posed regions of left and right images are affected by noise, we used a 3D convolution to aggregate the cost volume to obtain better accuracy. However, the 3D convolution method is prone to mismatching in ill-posed areas of the image. To tackle the problems above, we proposed a dense grouping atrous convolution spatial pyramid pooling (DenseGASPP) method. The feature of the DenseGASPP method is that there is a dense connection between the group atrous convolutions to fully integrate feature information. This method can expand the receptive field and balance the effect of holes on the segmentation task. Moreover, we introduced multi-scale cost aggregation into our method, which uses the repeated exchange of information between cost volumes of different scales to obtain rich contextual information and reduce the mismatching of the network. To evaluate the performance of our method, we conducted several groups of typical algorithm experiments on the scene flow and KITTI 2015 standard datasets. From the results, our model achieves better performance, reducing the EPE from 1.09 to 0.67, which improves the mismatching ability of binocular depth estimation algorithm in ill-posed regions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Vision and Imaging · Image Processing Techniques and Applications · Optical measurement and interference techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Information Engineering Faculty, Dalian University, Dalian 116622, China
Funding
National Natural Science Foundation of China · Liaoning Province
References (33)
Show source-provided references
1. Marr, D. (1983). Vision a Computational Investigation into the Human Representation and Processing of Visual Information, MIT Press.
2. Robust Control Algorithm of Bionic Robot Based on Binocular Vision Navigation
3. Trzcinski, T., Christoudias, M., Fua, P., and Lepetit, V. (2013, January 23–28). Boosting Binary Keypoint Descriptors. Computer Vision and Pattern Recognition. Proceedings of the CVPR–2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.370 ↗
4. Backpropagation Applied to Handwritten Zip Code Recognition10.1162/neco.1989.1.4.541 ↗
5. Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., and Brox, T. (2016, January 27–30). A Large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.438 ↗
6. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs10.1109/TPAMI.2017.2699184 ↗
7. Yu, F., Koltun, V., and Funkhouser, T. (2017, January 21–26). Dilated Residual Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.75 ↗
8. Zhu, Z., He, M., Dai, Y., Rao, Z., and Li, B. (2019, January 19–21). Multi-scale cross-form pyramid network for stereo matching. Proceedings of the 2019 14th IEEE Conference on lndustrial Electronics and Applications (ICIEA), Xi’an, China.10.1109/ICIEA.2019.8834193 ↗
9. Zhu, Z., Guo, W., Chen, W., Li, Q., and Zhao, Y. (2021, January 19–22). MPANet: Multi-Scale Pyramid Aggregation Network For Stereo Matching. Proceedings of the 2021 IEEE International Conference on lmage Processing (ICIP), Virtual.10.1109/ICIP42928.2021.9506705 ↗
10. Yang, M., Yu, K., Zhang, C., Li, Z., and Yang, K. (2018, January 18–23). DenseASPP for Semantic Segmentation in Street Scenes. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00388 ↗
11. Group-Based Atrous Convolution Stereo Matching Network10.1155/2021/7386280 ↗
12. Yang, P., Sun, X., Li, W., Ma, S., Wu, W., and Wang, H. (2018, January 21–25). SGM: Sequence Generation Model for Multi-label Classification. Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, NM, USA.
13. Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., and Bry, A. (2017, January 22–29). End-to-end learning of geometry and context for deep stereo regression. Proceedings of the IEEE International Conference on Computer Vision 2017, Venice, Italy.10.1109/ICCV.2017.17 ↗
14. Chang, J., and Chen, Y. (2018, January 18–23). Pyramid stereo matching network. Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00567 ↗
15. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms10.1023/A:1014573219977 ↗
16. Stereo matching using belief propagation
17. Kolmogorov, V., and Zabih, R. (2001, January 7–14). Computing visual correspondence with occlusions using graph cuts. Proceedings of the Eighth IEEE International Conference on Computer Vision, Vancouver, BC, Canada.
18. Adaptive support-weight approach for correspondence search10.1109/TPAMI.2006.70 ↗
19. Fast Cost-Volume Filtering for Visual Correspondence and Beyond10.1109/TPAMI.2012.156 ↗
20. Min, D., Lu, J., and Do, M.N. (2011, January 6–13). A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy?. Proceedings of the 2011 International Conference on Computer Vision, Washington, DC, USA.10.1109/ICCV.2011.6126416 ↗
21. Xu, H., and Zhang, J. (2020, January 13–19). AANet: Adaptive Aggregation Network for Efficient Stereo Matching. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00203 ↗
22. Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D., and Brox, T. (2015, January 7–13). FlowNet: Learning optical flow with convolutional networks. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.316 ↗
23. Real-Time Stereo Vision System: A Multi-Block Matching on GPU10.1109/ACCESS.2018.2859445 ↗
24. Wang, D., Hua, L., and Cheng, X. (2018). A Miniature Binocular Endoscope with Local Feature Matchingand Stereo Matching for 3D Measurement and 3D Reconstruction. Sensors, 18.10.3390/s18072243 ↗
25. Review of stereo matching algorithms based on deep learning
26. Sun, K., Xiao, B., Liu, D., and Wang, J. (2019, January 16–17). Deep high-resolution representation learning for human pose estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00584 ↗
27. Yu, F., and Koltun, V. (2016, January 2–4). Multi-Scale Context Aggregation by Dilated Convolutions. Proceedings of the International Conference on Learning Representations—ICLR, San Juan, Puerto Rico.
28. Huang, G., Liu, Z., Van der Maaten, L., and Weinberger, Q.K. (2017, January 21–26). Densely connected convolutional Networks. Proceedings of the Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
29. Calonder, M., Lepetit, V., Strecha, C., and Fua, P. (2010, January 5–11). BRIEF: Binary robust independent elementary features. Proceedings of the European Conference on Computer Vision (ECCV), Heraklion, Greece.10.1007/978-3-642-15561-1_56 ↗
30. Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv.
31. (2015, January 7–12). Object scene flow for autonomous vehicles. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
32. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. Proceedings of the Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems.
33. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.