Vision-based semantic segmentation in scene understanding for autonomous driving: Recent achievements, challenges, and outlooks

K Muhammad, T Hussain, H Ullah… - IEEE Transactions …, 2022‏ - ieeexplore.ieee.org
Scene understanding plays a crucial role in autonomous driving by utilizing sensory data for
contextual information extraction and decision making. Beyond modeling advances, the …

RGB-D and thermal sensor fusion: A systematic literature review

M Brenner, NH Reyes, T Susnjak, ALC Barczak - IEEE Access, 2023‏ - ieeexplore.ieee.org
In the last decade, the computer vision field has seen significant progress in multimodal data
fusion and learning, where multiple sensors, including depth, infrared, and visual, are used …

CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers

J Zhang, H Liu, K Yang, X Hu, R Liu… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Scene understanding based on image segmentation is a crucial component of autonomous
vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting …

Delivering arbitrary-modal semantic segmentation

J Zhang, R Liu, H Shi, K Yang, S Reiß… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Multimodal fusion can make semantic segmentation more robust. However, fusing an
arbitrary number of modalities remains underexplored. To delve into this problem, we create …

Bending reality: Distortion-aware transformers for adapting to panoramic semantic segmentation

J Zhang, K Yang, C Ma, S Reiß… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Panoramic images with their 360deg directional view encompass exhaustive information
about the surrounding space, providing a rich foundation for scene understanding. To unfold …

Cmda: Cross-modality domain adaptation for nighttime semantic segmentation

R **a, C Zhao, M Zheng, Z Wu… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Most nighttime semantic segmentation studies are based on domain adaptation approaches
and image input. However, limited by the low dynamic range of conventional cameras …

Trans4Trans: Efficient transformer for transparent object and semantic scene segmentation in real-world navigation assistance

J Zhang, K Yang, A Constantinescu… - IEEE Transactions …, 2022‏ - ieeexplore.ieee.org
Transparent objects, such as glass walls and doors, constitute architectural obstacles
hindering the mobility of people with low vision or blindness. For instance, the open space …

Capturing omni-range context for omnidirectional segmentation

K Yang, J Zhang, S Reiß, X Hu… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Abstract Convolutional Networks (ConvNets) excel at semantic segmentation and have
become a vital component for perception in autonomous driving. Enabling an all …

Polarization-driven semantic segmentation via efficient attention-bridged fusion

K **ang, K Yang, K Wang - Optics Express, 2021‏ - opg.optica.org
Semantic segmentation (SS) is promising for outdoor scene perception in safety-critical
applications like autonomous vehicles, assisted navigation and so on. However, traditional …

From slam to situational awareness: Challenges and survey

H Bavle, JL Sanchez-Lopez, C Cimarelli, A Tourani… - Sensors, 2023‏ - mdpi.com
The capability of a mobile robot to efficiently and safely perform complex missions is limited
by its knowledge of the environment, namely the situation. Advanced reasoning, decision …