Prof. Mohamed El-Helw

Semantic Segmentation of satellite images is one of the most challenging problems in computer vision as it requires a model capable of capturing both local and global information at each pixel. Current state of the art methods are based on Fully Convolutional Neural Networks (FCNN) with mostly two main components: an encoder which is a pretrained classification model that gradually reduces the

In this paper we present a novel framework for geolocalizing Unmanned Aerial Vehicles (UAVs) using only their onboard camera. The framework exploits the abundance of satellite imagery, along with established computer vision and deep learning methods, to locate the UAV in a satellite imagery map. It utilizes the contextual information extracted from the scene to attain increased geolocalization

We address the problem of recognizing multi-digit numbers in optical character images. Classical approaches to solve this problem include separate localization, segmentation and recognition steps. In this paper, an integrated approach to multi-digit recognition from raw pixels to ultimate multi class labeling is proposed by using recurrent attention model based on a spatial transformer model

Most commercial Small Unmanned Aerial Vehicles (SUAVs) rely solely on Global Navigation Satellite Systems (GNSSs) - such as GPS and GLONASS - to perform localization tasks during the execution of autonomous navigation activities. Despite being fast and accurate, satellite-based navigation systems have typical vulnerabilities and pitfalls in urban settings that may prevent successful drone

New challenges and complexities are continuously increasing in advanced driver assistance systems (ADAS) development (e.g. active safety, driver assistant and autonomous vehicle systems). Therefore, the health management of ADAS’ components needs special improvements. Since software contribution in ADAS’ development is increasing significantly, remote diagnosis and maintenance for ADAS become more

The evaluation of Advanced Driver Assistance Systems (ADAS including driver assistance and active safety) has increasing interest from authorities, industry and academia. AsPeCSS active safety project concludes that good results in a laboratory test for active safety system design does not necessarily equate to an effective system in real traffic conditions. Moreover, many ADAS assessment projects

In this paper, we describe a method for Scale-Adaptive visual tracking using compressive sensing. Instead of using scale-invariant-features to estimate the object size every few frames, we use the compressed features at different scale then perform a second stage of classification to detect the best-fit scale. We describe the proposed mechanism of how we implement the Bayesian Classifier used in

Intelligent camera systems provide an effective solution for road traffic monitoring with traffic stream characteristics, such as volumes and densities, continuously computed and relayed to control stations. However, developing a functional vision-based traffic monitoring system is a complex task that entails the creation of appropriate visual sensing platforms with on-board visual analytics

Tracking by detection methods are becoming increasingly popular in recent years. They use samples classified in previous frames to detect object in a new frame. These methods have shown successful results. However, due to the self updating nature of this approach, tracking by detection methods usually suffer from object drift. Inaccurately detected samples are added to the training set which