Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation

About

Inferring the depth of images is a fundamental inverse problem within the field of Computer Vision since depth information is obtained through 2D images, which can be generated from infinite possibilities of observed real scenes. Benefiting from the progress of Convolutional Neural Networks (CNNs) to explore structural features and spatial image information, Single Image Depth Estimation (SIDE) is often highlighted in scopes of scientific and technological innovation, as this concept provides advantages related to its low implementation cost and robustness to environmental conditions. In the context of autonomous vehicles, state-of-the-art CNNs optimize the SIDE task by producing high-quality depth maps, which are essential during the autonomous navigation process in different locations. However, such networks are usually supervised by sparse and noisy depth data, from Light Detection and Ranging (LiDAR) laser scans, and are carried out at high computational cost, requiring high-performance Graphic Processing Units (GPUs). Therefore, we propose a new lightweight and fast supervised CNN architecture combined with novel feature extraction models which are designed for real-world autonomous navigation. We also introduce an efficient surface normals module, jointly with a simple geometric 2.5D loss function, to solve SIDE problems. We also innovate by incorporating multiple Deep Learning techniques, such as the use of densification algorithms and additional semantic, surface normals and depth information to train our framework. The method introduced in this work focuses on robotic applications in indoor and outdoor environments and its results are evaluated on the competitive and publicly available NYU Depth V2 and KITTI Depth datasets.

Raul de Queiroz Mendes, Eduardo Godinho Ribeiro, Nicolas dos Santos Rosa, Valdir Grassi Jr• 2020

Related benchmarks

TaskDatasetResultRank
Monocular Depth EstimationKITTI (Eigen)
Abs Rel0.071
502
Depth EstimationNYU v2 (test)
Threshold Accuracy (delta < 1.25)88.5
423
Surface Normal EstimationNYU v2 (test)
Mean Angle Distance (MAD)8.6
206
Depth CompletionNYU-depth-v2 official (test)
RMSE0.102
187
Depth CompletionKITTI depth completion official (test)
RMSE (mm)226.2
154
Depth CompletionKITTI Depth (Eigen Split)
Abs Rel0.019
12
Visual OdometryKITTI Odometry Sequence 04
RMSE2.309
11
Visual OdometryKITTI Odometry Sequence 05
RMSE7.1224
8
Visual OdometryKITTI Odometry Sequence 00
RMSE16.9438
6
Visual OdometryKITTI Odometry Sequence 02
RMSE14.9513
6
Showing 10 of 16 rows

Other info

Follow for update