Dr. Mohamed Abdellatif

School of civil engineering, University of Leeds, United Kingdom.

Professor of Future University in Egypt. 

Research Area: Computer vision, Machine learning.

Topic:

Deep learning and Computer vision research for autonomous inspection of Infrastructure and smart cities monitoring

Abstract: 

There is a trend to exploit computer vision and deep learning for inspection of infrastructure in smart cities such as bridges and other civil structures. The challenges of using drones or mobile robot to inspect and detect anomalies are huge but is worth exploring. The recent challenges that deep learning face is the need for enormous and annotated data to learn the visual information. Deep learning replaced mobel - based geometry approaches but still much can be learned from the geometry models. The geometry can give us good hints about metrics needed to select fewer training data for deep learning. Carefully selected training data spanning wider range of the required metric will enable the deep learning model to generalize faster after training with a small number of images.

Assoc Prof. Han Wang

School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore

Topic:

Using Stereovision System on a Fast Moving Unmanned Ground Vehicle

Abstract: 

This talk  is about developing a high speed, high accuracy stereo vision system and apply it onto an Unmanned Ground Vehicle (UGV). Currently UGV mainly uses expensive active sensors such as Lidar and Radar to provide ranging sensing. We talk about obstacle detection, recognition and tracking system, road feature detection, self-localization and mapping system into the all weather, all terrain unmanned autonomous vehicles with the help of stereo camera and graphics processing unit (GPU), so that it can run at high speed from 15 km/h to 60 km/h. The talk will include
 
·         Obstacle Detection
·         Object Classification and Tracking
·         Road Slope Estimation
·         Localization and Mapping
·         Lane and Kerb Detection

Assoc.Prof.Dr. Nada M. Al Hakkak

IT faculty at Baghdad College for Economic Sciences University, Iraq

Title:

Deep Learning with CVOID019

Abstract:

Deep learning applications covers important areas of life like healthcare, image coloring, image captioning, and robotics. Deep learning is reshaping healthcare industry with new solutions to improve people’s life.

In this speech I would like to talk about the deep learning technology and how it can help in limiting the infection of COVID-19 and make everyone safer.