.png){kind=icon}
.png){kind=icon}
Return
Self-supervised deep monocular visual odometry and depth estimation with observation variation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2023.102553.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recent research in deep learning has greatly advanced the development of monocular visual depth estimation and odometry. These learning-based methods predominantly leverage neural networks to extract prevalent high-dimensional features for regression-based estimation. However, the consistency of observations is still regarded as a core challenge that limits the generalization ability. We attribute this challenge to the significant inconsistency in feature levels due to changes in the environment or motion, collectively referred to as observation variation. To this end, we propose a novel monocular depth estimation and a pose estimation network with attention mechanism to recalibrate features for different environment. The depth and ego -motion estimation tasks are formulated by coupling together in an end-to-end reconstruction problem, and attention modules adaptively recalibrate specific feature responses. Furthermore, we propose a simple sliding window optimization without RNN-based architecture, which is introduced to overcome the movement speed variation and error accumulation. Finally, we collect an observation variation dataset with environmental and motion changes. Evaluations of depth and pose estimation demonstrate that our methods effectively overcomes these observation variation challenges and achieves better performance. Our project will be available at https://github.com/alikesierzhao/OV-SfmLearner.
Keywords:
Monocular depth estimation
Ego-motion estimation
Attention mechanism
Observation variation