Hello! I'm Mohamed, a PhD student supervised by Prof. Gabriel Brostow at University College London (UCL).
My current research is focused on methods for improving the robustness of core computer vision tasks for better performance in real world deployments. I also designed and built the majority of LookOut, a system for automating the task of pointing a camera during filming for low budget or small size crews (down to one camera-operator as the base case).
Check out my resume here.
Improved Handling of Motion Blur in Online Object Detection
We wish to detect specific categories of objects, for online vision systems that will run in the real world. Object detection is already very challenging. It is even harder when the images are blurred, from the camera being in a car or a hand-held phone. Most existing efforts either focused on sharp images, with easy to label ground truth, or they have treated motion blur as one of many generic corruptions.
Instead, we focus especially on the details of egomotion induced blur. We explore five classes of remedies, where each targets different potential causes for the performance gap between sharp and blurred images. For example, first deblurring an image changes its human interpretability, but at present, only partly improves object detection. The other four classes of remedies address multi-scale texture, out-of-distribution testing, label generation, and conditioning by blur-type. Surprisingly, we discover that custom label generation aimed at resolving spatial ambiguity, ahead of all others, markedly improves object detection. Also, in contrast to findings from classification, we see a noteworthy boost by conditioning our model on bespoke categories of motion blur.
We validate and cross-breed the different remedies experimentally on blurred COCO images and real-world blur datasets, producing an easy and practical favorite model with superior detection rates.
LookOut! Interactive Camera Gimbal Controller for Filming Long Takes
Mohamed Sayed, Robert Cinca, Enrico Costanza, Gabriel BrostowProject Page, Paper, Video, Filmed Scenes
The job of a camera operator is more challenging, and potentially dangerous, when filming long moving camera shots. Broadly, the operator must keep the actors in-frame while safely navigating around obstacles, and while fulfilling an artistic vision. We propose a unified hardware and software system that distributes some of the camera operator's burden, freeing them up to focus on safety and aesthetics during a take. Our real-time system provides a solo operator with end-to-end control, so they can balance on-set responsiveness to action vs planned storyboards and framing, while looking where they're going. By default, we film without a field monitor.
Our LookOut system is built around a lightweight commodity camera gimbal mechanism, with heavy modifications to the controller, which would normally just provide active stabilization. Our control algorithm reacts to speech commands, video, and a pre-made script. Specifically, our automatic monitoring of the live video feed saves the operator from distractions. In pre-production, an artist uses our GUI to design a sequence of high-level camera "behaviors.'' Those can be specific, based on a storyboard, or looser objectives, such as "frame both actors.'' Then during filming, a machine-readable script, exported from the GUI, ties together with the sensor readings to drive the gimbal. To validate our algorithm, we compared tracking strategies, interfaces, and hardware protocols, and collected impressions from a) film-makers who used all aspects of our system, and b) film-makers who watched footage filmed using LookOut.
TL;DR: LookOut controls the camera's orientation automatically and follows actors based on what you tell it to do.
Bachelor's Thesis at Cairo University, in cooperation with Mentor
Worked with Mentor (formerly Mentor Graphics) on using Process Mining to improve the performance of a widely used tool developed by Mentor.
Unsupervised Skin Lesion Segmentation
A fully unsupervised engineered segmentation pipeline in Matlab for dermoscopic skin lesions. This was just before the International Skin Imaging Collaboration challenge was introduced and provided large datasets for supervised deep learning approaches. There also some engineered feature extraction steps for melanoma classification in the repo. I wrote this code while working with Prof. Tawfik Ismail at Cairo University.[Code]