Multi-Scale Spatio-Temporal Feature Extraction and Depth Estimation from Sequences by Ordinal Classification

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.

An intelligent ubiquitous compression technique for DNA sequencing using Hadoop

“…The larger the reduction of data, the longer the time for compression processing. Therefore, the evaluation of the compression method is the evaluation of its balance in space and time [32]. …”

Deep learning for monocular depth estimation: A review

“…There are several deep learning models in classification for monocular depth estimation, such as full convolutional models [11], residual models [74,116,134], and ordinal classification models [33,87]. Fu et al [33] put forward a deep ordered classification network to estimate monocular depth maps.…”