Mennatullah Siam

Recurrent Fully Convolutional Networks for Video Segmentation

Image segmentation is an important step in most visual tasks. While convolutional neural networks have shown to perform well on single image segmentation, to our knowledge, no study has been done on leveraging recurrent gated architectures for video segmentation. Accordingly, we propose and implement a novel method for online segmentation of video sequences that incorporates temporal data. The network is built from a fully convolutional network and a recurrent unit that works on a sliding window over the temporal data. We use convolutional gated recurrent unit that preserves the spatial information and reduces the parameters learned. Our method has the advantage that it can work in an online fashion instead of operating over the whole input batch of video frames. The network is tested on video segmentation benchmarks in Segtrack V2 and Davis. It proved to have 5% improvement in Segtrack and 3% improvement in Davis in F-measure over a plain fully convolutional network.

Parking-stall vacancy indicator system, based on deep convolutional neural networks

Parking-management systems, including services that recognize vacant stalls, can play a valuable role in reducing traffic and energy waste in large cities. Visual methods for detecting vacant parking spots are cost-effective options since they can take advantage of the cameras already available in many parking lots. However, visual-detection methods can be fragile and not easily generalizable. In this paper, we present a robust detection algorithm based on deep convolutional neural networks. We implemented and tested our algorithm on a large baseline dataset, and also tested on video feeds from web-accessible parking-lot cameras. Our detection method improved the state of the art AUC by 8.13%. It also showed robust performance in different testing scenarios including tests on public cameras. We have developed a fully functional system, from server-side image analysis to front-end user interface, to demonstrate the practicality of our method.

Comparative Evaluation of 3D Pose Estimation of Industrial Objects in RGB Pointclouds

3D pose estimation is a crucial element for enabling robots to work in industrial environment to perform tasks like bin-picking or depalletizing. Even though there exist various pose estimation algorithms, they usually deal with common daily objects applied in lab environments. However, coping with real-world industrial objects is a much harder challenge for most pose estimation techniques due to the difficult material and structural properties of those objects. A comparative evaluation of pose estimation algorithms in regard to these object characteristics has yet to be done. This paper aims to provide a description and evaluation of selected state-of-the-art pose estimation techniques to investigate their object-related performance in terms of time and accuracy. The evaluation shows that there is indeed not a general algorithm which solves the task for all different objects, but it outlines the issues that real-world application have to deal with and what the strengths and weaknesses of the different pose estimation approaches are.

Unifying Registration Based Tracking: A Case Study with Structural Similarity

This paper adapts a popular image quality measure called structural similarity for high precision registration based tracking while also introducing a simpler and faster variant of the same. Further, these are evaluated comprehensively against existing measures using a unified approach to study registration based trackers that decomposes them into three constituent sub modules - appearance model, state space model and search method. Several popular trackers in literature are broken down using this method so that their contributions - as ofthis paper - are shown to be limited to only one or two ofthese submodules. An open source tracking framework is made available that follows this decomposition closely through extensive use of generic programming. It is used to perform all experiments on four publicly available datasets so the results are easily reproducible. This framework provides a convenient interface to plug in a new methodfor any sub module and combine it with existing methods for the other two. It can also serve as a fast and flexible solution for practical tracking needs due to its highly efficient implementation.