KAUST researchers in the Image and Video Understanding Lab are applying machine learning to computer vision for automated navigation, including self-driving cars and UAVs. They tested their algorithms on KAUST roads, aiming to replicate the brain's efficiency in tasks like activity and object recognition. The team is also exploring the possibility of creative algorithms that can transfer skills without direct training. Why it matters: This research contributes to the advancement of autonomous systems and explores the fundamental questions of replicating human intelligence in machines within the GCC region.
Researchers present RUR53, an unmanned ground vehicle (UGV) capable of autonomous navigation, object recognition, and tool manipulation. The UGV uses a modular software architecture, enabling it to perform complex tasks like detecting panels, docking, and manipulating tools such as wrenches and valve stems. RUR53 was tested at the 2017 Mohamed Bin Zayed International Robotics Challenge where it ranked third in the Grand Challenge as part of a collaboration. Why it matters: This research demonstrates advanced robotics capabilities applicable to various industrial and inspection tasks, highlighting the UAE's focus on robotics innovation.
An MBZUAI team led by Ph.D. student Dmitry Demidov won the Best Student Paper Award at VISAPP 2023 for their work on fine-grained visual classification. Their paper, 'Salient Mask-Guided Vision Transformer for Fine-Grained Classification,' introduces SM-ViT, a technique using a salient mask to improve Vision Transformer accuracy. The model focuses on defining characteristics of objects, outperforming standard ViT architecture, even with fewer or lower-resolution images. Why it matters: This award recognizes MBZUAI's contribution to advancing computer vision, particularly in applications requiring nuanced object recognition, such as robotics and automated systems.
MBZUAI researchers presented "TransRadar," a study at WACV proposing new uses for radar in object identification. The study, led by Yahia Dalbah, explores fusing radar with other technologies to identify objects, particularly for autonomous vehicles. The "TransRadar" approach uses an adaptive-directional transformer for real-time multi-view radar semantic segmentation. Why it matters: This research addresses the limitations of radar by enhancing its object recognition capabilities, potentially improving the reliability of autonomous systems in adverse conditions.
MBZUAI Professor Salman Khan is researching continuous, lifelong learning systems for computer vision, aiming to mimic human learning processes like curiosity and discovery. His work focuses on learning from limited data and adversarial robustness of deep neural networks. Khan, along with MBZUAI professors Fahad Khan and Rao Anwer, and partners from other universities, presented research at CVPR 2022. Why it matters: This research has the potential to significantly improve the ability of AI systems to understand and adapt to the real world, enabling more intelligent autonomous systems.