Back to Search
Start Over
Estimating Depth From Monocular Images as Classification Using Deep Fully Convolutional Residual Networks.
- Source :
-
IEEE Transactions on Circuits & Systems for Video Technology . Nov2018, Vol. 28 Issue 11, p3174-3182. 9p. - Publication Year :
- 2018
-
Abstract
- Depth estimation from single monocular images is a key component in scene understanding. Most existing algorithms formulate depth estimation as a regression problem due to the continuous property of depths. However, the depth value of input data can hardly be regressed exactly to the ground-truth value. In this paper, we propose to formulate depth estimation as a pixelwise classification task. Specifically, we first discretize the continuous ground-truth depths into several bins and label the bins according to their depth ranges. Then, we solve the depth estimation problem as classification by training a fully convolutional deep residual network. Compared with estimating the exact depth of a single point, it is easier to estimate its depth range. More importantly, by performing depth classification instead of regression, we can easily obtain the confidence of a depth prediction in the form of probability distribution. With this confidence, we can apply an information gain loss to make use of the predictions that are close to ground-truth during training, as well as fully-connected conditional random fields for post-processing to further improve the performance. We test our proposed method on both indoor and outdoor benchmark RGB-Depth datasets and achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10518215
- Volume :
- 28
- Issue :
- 11
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Circuits & Systems for Video Technology
- Publication Type :
- Academic Journal
- Accession number :
- 132893974
- Full Text :
- https://doi.org/10.1109/TCSVT.2017.2740321