Surround-view fisheye camera perception for automated driving: Overview, survey & challenges

VR Kumar, C Eising, C Witt… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Surround-view fisheye cameras are commonly used for near-field sensing in automated
driving. Four fisheye cameras on four sides of the vehicle are sufficient to cover 360° around …

Woodscape: A multi-task, multi-camera fisheye dataset for autonomous driving

S Yogamani, C Hughes, J Horgan… - Proceedings of the …, 2019 - openaccess.thecvf.com
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance,
augmented reality and in particular automotive applications. In spite of their prevalence …

[HTML][HTML] A hybrid deep convolutional neural network for accurate land cover classification

N Wambugu, Y Chen, Z Xiao, M Wei, SA Bello… - International Journal of …, 2021 - Elsevier
Land cover classification provides updated information regarding the Earth's resources,
which is vital for agricultural investigation, urban management, and disaster monitoring …

Syndistnet: Self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving

VR Kumar, M Klingner, S Yogamani… - Proceedings of the …, 2021 - openaccess.thecvf.com
State-of-the-art self-supervised learning approaches for monocular depth estimation usually
suffer from scale ambiguity. They do not generalize well when applied on distance …

MobTCast: Leveraging auxiliary trajectory forecasting for human mobility prediction

H Xue, F Salim, Y Ren, N Oliver - Advances in Neural …, 2021 - proceedings.neurips.cc
Human mobility prediction is a core functionality in many location-based services and
applications. However, due to the sparsity of mobility data, it is not an easy task to predict …

Multinet++: Multi-stream feature aggregation and geometric loss strategy for multi-task learning

S Chennupati, G Sistu, S Yogamani… - Proceedings of the …, 2019 - openaccess.thecvf.com
Multi-task learning is commonly used in autonomous driving for solving various visual
perception tasks. It offers significant benefits in terms of both performance and computational …

Near-field perception for low-speed vehicle automation using surround-view fisheye cameras

C Eising, J Horgan, S Yogamani - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Cameras are the primary sensor in automated driving systems. They provide high
information density and are optimal for detecting road infrastructure cues laid out for human …

Unrectdepthnet: Self-supervised monocular depth estimation using a generic framework for handling common camera distortion models

VR Kumar, S Yogamani, M Bach, C Witt… - 2020 IEEE/RSJ …, 2020 - ieeexplore.ieee.org
In classical computer vision, rectification is an integral part of multi-view depth estimation. It
typically includes epipolar rectification and lens distortion correction. This process simplifies …

Blazeneo: Blazing fast polyp segmentation and neoplasm detection

NS An, PN Lan, DV Hang, DV Long, TQ Trung… - IEEE …, 2022 - ieeexplore.ieee.org
In recent years, computer-aided automatic polyp segmentation and neoplasm detection
have been an emerging topic in medical image analysis, providing valuable support to …

Dynamic task weighting methods for multi-task networks in autonomous driving systems

I Leang, G Sistu, F Bürger, A Bursuc… - 2020 IEEE 23rd …, 2020 - ieeexplore.ieee.org
Deep multi-task networks are of particular interest for autonomous driving systems. They can
potentially strike an excellent trade-off between predictive performance, hardware …