Back to Search
Start Over
Multi-Scale Spatio-Temporal Feature Extraction and Depth Estimation from Sequences by Ordinal Classification.
- Source :
- Sensors (14248220); Apr2020, Vol. 20 Issue 7, p1979, 1p
- Publication Year :
- 2020
-
Abstract
- Depth estimation is a key problem in 3D computer vision and has a wide variety of applications. In this paper we explore whether deep learning network can predict depth map accurately by learning multi-scale spatio-temporal features from sequences and recasting the depth estimation from a regression task to an ordinal classification task. We design an encoder-decoder network with several multi-scale strategies to improve its performance and extract spatio-temporal features with ConvLSTM. The results of our experiments show that the proposed method has an improvement of almost 10% in error metrics and up to 2% in accuracy metrics. The results also tell us that extracting spatio-temporal features can dramatically improve the performance in depth estimation task. We consider to extend this work to a self-supervised manner to get rid of the dependence on large-scale labeled data. [ABSTRACT FROM AUTHOR]
- Subjects :
- FEATURE extraction
DEEP learning
COMPUTER vision
CLASSIFICATION
Subjects
Details
- Language :
- English
- ISSN :
- 14248220
- Volume :
- 20
- Issue :
- 7
- Database :
- Complementary Index
- Journal :
- Sensors (14248220)
- Publication Type :
- Academic Journal
- Accession number :
- 142826477
- Full Text :
- https://doi.org/10.3390/s20071979