Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

An Image Depth Estimation Algorithm based on Pixel-wise Confidence and Concordance Correlation Coefficient

픽셀단위 상대적 신뢰도와 일치상관계수를 이용한 영상의 깊이 추정 알고리즘

  • Kim, Yeonwoo (Dept. of Electronics and Computer Eng, Chonnam National University) ;
  • Lee, Chilwoo (School of Electronic and Computer Eng, Chonnam National University)
  • Received : 2018.01.12
  • Accepted : 2018.01.24
  • Published : 2018.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we describe an algorithm for extracting depth information from a single image based on CNN. When acquiring three-dimensional information from a single two-dimensional image using a deep-learning technique, it is difficult to accurately predict the edge portion of the depth image because it is a part where the depth changes abruptly. in this paper, we introduce the concept of pixel-wise confidence to take advantage of these characteristics. We propose an algorithm that estimates depth information from a highly reliable flat part and propagates it to the edge part to improve the accuracy of depth estimation.

Keywords

References

  1. D. Eigen, C. Puhrsch, and R. Fergus, "Depth Map Prediction from a Single Image Using a Multi-scale Deep Network," Proceeding of Conference on Neural Information Processing Systems, Vol. 3, No. 9, pp. 2366-2374, 2014.
  2. D. Eigen and R. Fergus, "Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture," Proceeding of International Conference on Computer Vision, pp. 2650-2658, 2015.
  3. J.S. Park and I.S. Kweon, "Single Image Depth Estimation Using Convolutional Neural Networks with NCC-based Loss," Proceeding of The International Workshop on Frontiers of Computer Vision, pp. 12-16, 2017.
  4. S. Ioffe and C. Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," Proceedings of the 32nd International Conference on Machine Learning, Vol. 37, pp. 448-456, 2015.
  5. K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," Clinical Orthopaedics and Related Research, Vol. abs/1409.1556, pp. 1409-1556, 2014.
  6. N. Silberman, D. Hoiem, P. Kohli, and R. Fergus, "Indoor Segmentation and Support Inference from RGBD Images," Proceedings of the 12th European Conference on Computer Vision, pp. 746-760, 2012.
  7. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, and J. Dean, and et al., "Tensorflow: Large-Scale Machine Learning on Heterogeneous Distributed Systems," arXiv, arXiv: 1603.04467, 2016.
  8. L. Bo, S. Chunhua, D. Yuchao, K. Hengel, and H. Mingyi, "Depth and Surface Normal Estimation from Monocular Images Using Regressionon Deep Features and Hierarchical CRFs," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1119-1127, 2015.
  9. D. Scharstein and R. Szeliski, “Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms,” International Journal of Computer Vision, Vol. 47, No. 1, pp. 7-42, 2002. https://doi.org/10.1023/A:1014573219977
  10. A. Saxena, M. Sun, and A. Ng, “Make3D: Learning 3D Scene Structure from a Single Still Image,” Pattern Analysis and Machine Intelligence, Vol. 31, No. 5, pp. 824-840, 2009. https://doi.org/10.1109/TPAMI.2008.132
  11. M. Liu, M. Salzmann, and X. He, "Discrete-Continuous Depth Estimation from a Single Image," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 716-723, 2014.
  12. A. Schwing and R. Urtasun, "Efficient Exact Inference for 3D Indoor Scene Understanding," Proceedings of the 12th European Conference on Computer Vision, pp. 299-313, 2012.
  13. B. Liu, S. Gould, and D. Koller, "Single Image Depth Estimation from Predicted Semantic Labels," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1253-1260, 2010.
  14. L. Fayaou, S. Chunhuan, L. Guosheng, and R. Ian, “Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields,” Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 10, pp. 2024-2039, 2016. https://doi.org/10.1109/TPAMI.2015.2505283
  15. H.J. Jung and K.H. Sohn, "Single Image Depth Estimation With Integration of Parametric Learning and Non-Parametric Sampling,"Journal of Korea Multimedia Society, Vol. 19, No. 9, pp. 1659-1668, 2016 https://doi.org/10.9717/kmms.2016.19.9.1659