Self-supervised monocular depth estimation from oblique UAV videos

TL;DR

This paper presents a self-supervised deep learning method for monocular depth estimation from UAV videos, using a novel architecture and contrastive loss to outperform existing approaches.

Contribution

It introduces a new architecture with 2D encoders and a 3D decoder, and employs a contrastive loss for improved depth estimation from UAV videos.

Findings

Outperforms state-of-the-art methods on UAVid dataset

Uses a novel 2D-3D CNN architecture for temporal feature extraction

Employs contrastive loss to enhance image reconstruction quality

Abstract

UAVs have become an essential photogrammetric measurement as they are affordable, easily accessible and versatile. Aerial images captured from UAVs have applications in small and large scale texture mapping, 3D modelling, object detection tasks, DTM and DSM generation etc. Photogrammetric techniques are routinely used for 3D reconstruction from UAV images where multiple images of the same scene are acquired. Developments in computer vision and deep learning techniques have made Single Image Depth Estimation (SIDE) a field of intense research. Using SIDE techniques on UAV images can overcome the need for multiple images for 3D reconstruction. This paper aims to estimate depth from a single UAV aerial image using deep learning. We follow a self-supervised learning approach, Self-Supervised Monocular Depth Estimation (SMDE), which does not need ground truth depth or any extra information other than images for learning to estimate depth. Monocular video frames are used for training the deep learning model which learns depth and pose information jointly through two different networks, one each for depth and pose. The predicted depth and pose are used to reconstruct one image from the viewpoint of another image utilising the temporal information from videos. We propose a novel architecture with two 2D CNN encoders and a 3D CNN decoder for extracting information from consecutive temporal frames. A contrastive loss term is introduced for improving the quality of image generation. Our experiments are carried out on the public UAVid video dataset. The experimental results demonstrate that our model outperforms the state-of-the-art methods in estimating the depths.