1 code implementation • 14 Nov 2022 • Eslam Mohamed BAKR, Ahmad El Sallab, Mohsen A. Rashwan
Recently, attention mechanisms have been explored with ConvNets, both across the spatial and channel dimensions.
no code implementations • 11 Jul 2021 • Hazem Rashed, Mariam Essam, Maha Mohamed, Ahmad El Sallab, Senthil Yogamani
In this work, we explore end-to-end Moving Object Detection (MOD) on the BEV map directly using monocular images as input.
no code implementations • 22 Apr 2021 • Hazem Rashed, Ahmad El Sallab, Senthil Yogamani
In this work, we aim to leverage the vehicle motion information and feed it into the model to have an adaptation mechanism based on ego-motion.
1 code implementation • 5 Aug 2020 • Abdullah Tarek Farag, Ahmed Raafat Abd El-Wahab, Mahmoud Nada, Mohamed Yasser Abd El-Hakeem, Omar Sayed Mahmoud, Reem Khaled Rashwan, Ahmad El Sallab
The common encoder in our architecture can capture useful common features present in the different tasks.
no code implementations • 1 Dec 2019 • Mohamed Ramzy, Hazem Rashed, Ahmad El Sallab, Senthil Yogamani
The trajectory of the ego-vehicle is planned based on the future states of detected moving objects.
no code implementations • 24 Nov 2019 • Ahmad El Sallab, Ibrahim Sobh, Mohamed Zahran, Mohamed Shawky
Evaluation is performed on unseen real LiDAR frames from KITTI dataset, with different amounts of simulated data augmentation using the two proposed approaches, showing improvement of 6% mAP for the object detection task, in favor of the augmenting LiDAR point clouds adapted with the proposed neural sensor models over the raw simulated LiDAR.
no code implementations • 11 Oct 2019 • Hazem Rashed, Mohamed Ramzy, Victor Vaquero, Ahmad El Sallab, Ganesh Sistu, Senthil Yogamani
In this work, we propose a robust and real-time CNN architecture for Moving Object Detection (MOD) under low-light conditions by capturing motion information from both camera and LiDAR sensors.
no code implementations • 1 Jun 2019 • Khaled El Madawy, Hazem Rashed, Ahmad El Sallab, Omar Nasr, Hanan Kamel, Senthil Yogamani
Motivated by the fact that semantic segmentation is a mature algorithm on image data, we explore sensor fusion based 3D segmentation.
1 code implementation • 17 May 2019 • Ahmad El Sallab, Ibrahim Sobh, Mohamed Zahran, Nader Essam
Simulators are often used for data augmentation, which requires realistic sensor models that are hard to formulate and model in closed forms.
no code implementations • 10 Oct 2018 • Ibrahim Sobh, Loay Amin, Sherif Abdelkarim, Khaled Elmadawy, Mahmoud Gamal Saeed, Omar Abdeltawab, Mostafa Gamal, Ahmad El Sallab
In this paper, we present a novel framework for urban automated driving based on multi-modal sensors; LiDAR and Camera.
3 code implementations • 7 Aug 2018 • Waleed Ali, Sherif Abdelkarim, Mohamed Zahran, Mahmoud Zidan, Ahmad El Sallab
LiDAR sensors are employed to provide the 3D point cloud reconstruction of the surrounding environment, while the task of 3D object bounding box detection in real time remains a strong algorithmic challenge.
no code implementations • 11 Jun 2017 • Ahmad El Sallab, Mahmoud Saeed, Omar Abdel Tawab, Mohammed Abdou
Under the proposed framework, we propose MetaDAgger, a novel algorithm which tackles the generalization issues in traditional imitation learning.
1 code implementation • 8 Apr 2017 • Ahmad El Sallab, Mohammed Abdou, Etienne Perot, Senthil Yogamani
This is of particular relevance as it is difficult to pose autonomous driving as a supervised learning problem due to strong interactions with the environment including other vehicles, pedestrians and roadworks.
no code implementations • 13 Dec 2016 • Ahmad El Sallab, Mohammed Abdou, Etienne Perot, Senthil Yogamani
This is of particular interest as it is difficult to pose autonomous driving as a supervised learning problem as it has a strong interaction with the environment including other vehicles, pedestrians and roadworks.