Jemput Pekerja Bebas ke Projek
Anda tidak mempunyai projek aktif pada masa ini. Kenapa tidak memaparkan projek sekarang? Ia percuma!Siarkan Projek
- 100%Kerja Diselesai
- 88%Mengikut Bajet
- 88%Tepat Pada Masa
- N/AKadar Ulang Upah
AI Research & Development EngineerMay 2019
Leading a state-of-the-art AI Research & Development team in Webville.
Co-founder of a Computer Vision Research GroupJul 2017
• Implementation of state-of-the-art neural networks for computer vision tasks such as semantic segmentation, object detection, etc. • Publishing research ideas in reputed conferences.
Deep Learning ResearcherApr 2017 - Aug 2018 (1 year)
• Conducted state-of-the-art research in deep learning application to autonomous driving. • Worked on combining computer vision area with deep learning techniques. • Implemented several research ideas on different platforms including real hardware and embedded systems such as: - Extracting information from LiDAR/Camera using semantic segmentation. - Building an end-to-end driving system using deep learning. - Using object detection as a part of a safety-critical driving system.
Co-founder of a Deep Learning Research GroupMar 2017
Contributing to the open-source community by implementing, developing, and reproducing state-of-the-art algorithms.
B.Sc., Computer Engineering2014 - 2018 (4 years)
Top Student on Class (2018)Faculty of Engineering, Cairo University
RTSeg: Real-time Semantic Segmentation Comparative Study
A Comparative Study of Real-time Semantic Segmentation for Autonomous Driving
ShuffleSeg: Real-time Semantic Segmentation Network
Realtime Semantic Segmentation Benchmarking Framework
Deep Convolution Long-Short Term Memory Network for LIDAR Semantic Segmentation
Real-Time Segmentation with Appearance, Motion and Geometry
Real-time Segmentation is of crucial importance to robotics related applications such as autonomous driving, driving assisted systems, and traffic monitoring from unmanned aerial vehicles imagery. We propose a novel two-stream convolutional network for motion segmentation, which exploits flow and geometric cues to balance the accuracy and computational efficiency trade-offs. The geometric cues take advantage of the domain knowledge of the application. In case of mostly planar scenes from high altitude unman
End-To-End Multi-Modal Sensors Fusion System For Urban Automated Driving
In this paper, we present a novel framework for urban automated driving based on multi-modal sensors; LiDAR and Camera. Environment perception through sensors fusion is key to a successful deployment of automated driving systems, especially in complex urban areas. Our hypothesis is that a well designed deep neural network is able to end-to-end learn a driving policy that fuses LiDAR and Camera sensory input, achieving the best out of both. In order to improve the generalization and robustness of the learned
- Bayaran Disahkan
- Telefon Disahkan
- E-mel Disahkan