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

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Depth Completion KITTI Depth Completion Eigen Split DSN REL 0.019 # 1
RMSE 1.588 # 1
Monocular Depth Estimation KITTI Eigen split DSN absolute relative error 0.075 # 39
Depth Completion NYU-Depth V2 DSN RMSE 0.102 # 2
REL 0.012 # 1
Monocular Depth Estimation NYU-Depth V2 DSN RMSE 0.429 # 49
Surface Normals Estimation NYU-Depth V2 Surface Normals DSN RMSE 12.2 # 1

Methods


No methods listed for this paper. Add relevant methods here