4.6 Article

Parallax Inference for Robust Temporal Monocular Depth Estimation in Unstructured Environments

Journal

SENSORS
Volume 22, Issue 23, Pages -

Publisher

MDPI
DOI: 10.3390/s22239374

Keywords

depth estimation; deep learning; unmanned vehicles; parallax

Ask authors/readers for more resources

This paper presents a depth estimation method suitable for autonomous vehicles using on-board RGB cameras. By establishing a relationship between depth and visual parallax, a pyramidal convolutional neural network is utilized to perform precise depth estimation. The method also incorporates customized cost volumes to improve the estimation results and ensure robustness in various scenes.
Estimating the distance to objects is crucial for autonomous vehicles, but cost, weight or power constraints sometimes prevent the use of dedicated depth sensors. In this case, the distance has to be estimated from on-board mounted RGB cameras, which is a complex task especially for environments such as natural outdoor landscapes. In this paper, we present a new depth estimation method suitable for use in such landscapes. First, we establish a bijective relationship between depth and the visual parallax of two consecutive frames and show how to exploit it to perform motion-invariant pixel-wise depth estimation. Then, we detail our architecture which is based on a pyramidal convolutional neural network where each level refines an input parallax map estimate by using two customized cost volumes. We use these cost volumes to leverage the visual spatio-temporal constraints imposed by motion and make the network robust for varied scenes. We benchmarked our approach both in test and generalization modes on public datasets featuring synthetic camera trajectories recorded in a wide variety of outdoor scenes. Results show that our network outperforms the state of the art on these datasets, while also performing well on a standard depth estimation benchmark.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available