Self-supervised monocular depth estimation with multiscale perception

Y Zhang, M Gong, J Li, M Zhang… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Extracting 3D information from a single optical image is very attractive. Recently emerging
self-supervised methods can learn depth representations without using ground truth depth …

Joint optimization of depth and ego-motion for intelligent autonomous vehicles

Y Gao, F Tian, J Li, Z Fang, S Al-Rubaye… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
The three-dimensional (3D) perception of autonomous vehicles is crucial for localization and
analysis of the driving environment, while it involves massive computing resources for deep …

3D hierarchical refinement and augmentation for unsupervised learning of depth and pose from monocular video

G Wang, J Zhong, S Zhao, W Wu, Z Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Depth and ego-motion estimations are essential for the localization and navigation of
autonomous robots and autonomous driving. Recent studies make it possible to learn the …

Joint learning of frequency and spatial domains for dense image prediction

S Jia, W Yao - ISPRS Journal of Photogrammetry and Remote …, 2023 - Elsevier
Current artificial neural networks mainly conduct the learning process in the spatial domain
but neglect the frequency domain learning. However, the learning course performed in the …

Self-supervised depth estimation leveraging global perception and geometric smoothness

S Jia, X Pei, W Yao, SC Wong - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Self-supervised depth estimation has drawn much attention in recent years as it does not
require labeled data but image sequences. Moreover, it can be conveniently used in various …

Comprehensive Review of Smart Urban Traffic Management in the Context of the Fourth Industrial Revolution

JN Fadila, NHA Wahab, A Alshammari, A Aqarni… - IEEE …, 2024 - ieeexplore.ieee.org
The Fourth Industrial Revolution (4IR) has ushered in a new era of efficiency across various
domains, including the management of Road Traffic Congestion (RTC) in metropolitan cities …

Cbwloss: constrained bidirectional weighted loss for self-supervised learning of depth and pose

F Wang, J Cheng, P Liu - IEEE Transactions on Intelligent …, 2023 - ieeexplore.ieee.org
Photometric differences are widely used as supervision signals to train neural networks for
estimating depth and camera pose from unlabeled monocular videos. However, this …

DERNet: driver emotion recognition using onboard camera

D Wang, S Jia, X Pei, C Han, D Yao… - IEEE Intelligent …, 2023 - ieeexplore.ieee.org
Driver emotion is considered an essential factor associated with driving behaviors and thus
influences traffic safety. Dynamically and accurately recognizing the emotions of drivers …

Self-supervised multi-frame monocular depth estimation with pseudo-LiDAR pose enhancement

W Wu, G Wang, J Zhong, H Wang… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Depth estimation is one of the most important tasks in scene understanding. In the existing
joint self-supervised learning approaches of depth-pose estimation, depth estimation and …

[HTML][HTML] Self-supervised multi-task learning framework for safety and health-oriented road environment surveillance based on connected vehicle visual perception

S Jia, W Yao - International Journal of Applied Earth Observation and …, 2024 - Elsevier
Cutting-edge connected vehicle (CV) technologies have drawn much attention in recent
years. The real-time traffic data captured by a CV can be shared with other CVs and data …