no code implementations • 13 Jul 2021 • Eslam Mohamed, Ahmad El-Sallab
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames.
no code implementations • 21 Jun 2021 • Eslam Mohamed, Ahmad El-Sallab
Several methods of incorporating motion cues with the Transformer model are explored, including two-stream RGB and Optical Flow (OF) methods, and multi-stream architectures that take advantage of sequence information.
no code implementations • 12 Feb 2021 • Eslam Mohamed, Abdelrahman Shaker, Ahmad El-Sallab, Mayada Hadhoud
We compare our results to the state-of-the-art models for instance segmentation.
no code implementations • 3 Dec 2020 • Hazem Rashed, Eslam Mohamed, Ganesh Sistu, Varun Ravi Kumar, Ciaran Eising, Ahmad El-Sallab, Senthil Yogamani
It is the first detailed study on object detection on fisheye cameras for autonomous driving scenarios to the best of our knowledge.
no code implementations • 16 Aug 2020 • Eslam Mohamed, Mahmoud Ewaisha, Mennatullah Siam, Hazem Rashed, Senthil Yogamani, Waleed Hamdy, Muhammad Helmi, Ahmad El-Sallab
Moving object segmentation is a crucial task for autonomous vehicles as it can be used to segment objects in a class agnostic manner based on their motion cues.
no code implementations • 26 Jun 2019 • Mohammed Abdou, Mahmoud Elkhateeb, Ibrahim Sobh, Ahmad El-Sallab
Imbalanced distribution of classes in the dataset is one of the challenges that face 3D semantic scene labeling task.
no code implementations • 11 Jan 2019 • Hazem Rashed, Senthil Yogamani, Ahmad El-Sallab, Pavel Krizek, Mohamed El-Helw
We also make use of the ground truth optical flow in Virtual KITTI to serve as an ideal estimator and a standard Farneback optical flow algorithm to study the effect of noise.
no code implementations • 6 Jan 2019 • Victor Talpaert, Ibrahim Sobh, B Ravi Kiran, Patrick Mannion, Senthil Yogamani, Ahmad El-Sallab, Patrick Perez
Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind's AlphaGo.
no code implementations • 14 Sep 2017 • Mennatullah Siam, Heba Mahgoub, Mohamed Zahran, Senthil Yogamani, Martin Jagersand, Ahmad El-Sallab
Our experiments show that the proposed method outperforms state of the art methods that utilize motion cue only with 21. 5% in mAP on KITTI MOD.