Tag: Video Annotation

New Conference paper Accepted to the “ World Congress on Engineering 2013”

Saddam Bekhet / / Conference, Uncategorized

New Conference paper accepted for publishing in  “World Congress on Engineering 2013“.

The paper title is “Video Matching Using DC-image and Local Features ”

Abstract:

This paper presents a suggested framework for video matching based on local features extracted from the DC-image of MPEG compressed videos, without decompression. The relevant arguments and supporting evidences are discussed for developing video similarity techniques that works directly on compressed videos, without decompression, and especially utilising small size images. Two experiments are carried to support the above. The first is comparing between the DC-image and I-frame, in terms of matching performance and the corresponding computation complexity. The second experiment compares between using local features and global features in video matching, especially in the compressed domain and with the small size images. The results confirmed that the use of DC-image, despite its highly reduced size, is promising as it produces at least similar (if not better) matching precision, compared to the full I-frame. Also, using SIFT, as a local feature, outperforms precision of most of the standard global features. On the other hand, its computation complexity is relatively higher, but it is still within the real-time margin. There are also various optimisations that can be done to improve this computation complexity.

Well done and congratulations to Saddam Bekhet .

PGRs Research Presentations – March 2013

Amr Ahmed / / Uncategorized

The March’s PGRs Research Presentations was held on Wed. 13th March, 2pm, Meeting Room, MC3108 (3rd floor).

This session we had the following presentations:

Title: “A primal-dual fixed point algorithm with nonnegative constraint for CT image
reconstruction“.		 Title:   “Video Similarity in Compressed Domain”

By: Yuchao Tang

By: Saddam Bekhet
Abstract:Computed tomography (CT) image reconstruction problems often can be solved by finding the minimizer of a suitable objective function which usually consists of a data fidelity term  and a regularization term  subject to a convex constraint set $C$. In the unconstrained case, an efficient algorithm called the  primal-dual fixed point algorithm (PDFP$^{2}$O) has recently been developed to this problem, when the data fidelity term is differentiable with Lipschitz
continuous gradient and the regularization term composed by a simple convex function (possibly non-smooth) with a linear transformation. In this paper, we propose a modification of the PDFP$^{2}$O, which allows us to deal with the constrained minimization problem. We further propose accelerated algorithms which based on the Nesterov’s accelerated method. Numerical experiments on image reconstruction benchmark problem show that the proposed algorithms can produce better reconstructed image in signal-to-noise ratio than the original PDFP$^{2}$O and state-of-the-art methods with less iteration numbers. The
accelerated algorithms exhibit the fastest performance compared with all the other algorithms		 AbstractThe volume of video data is rapidly increasing, more than 4 billion hours of video are being watched each month on YouTube and more than 72 hours of video are uploaded to YouTube every minute, and counters are still running fast. A key aspect of benefiting from all that volume of data is the ability to annotate and index videos, to be able to search and retrieve them. The annotation process is time consuming and automating it, with semantically acceptable level, is a challenging task.The majority of available video data exists in compressed format MPEG-1, MPEG-2 and MPEG-4. Extraction of low level features, directly from compressed domain without decompression, is the first step towards efficient video content retrieval. Such approach avoids expensive computations and memory requirement involved in decoding compressed videos, which is the tradition in most approaches. Working on compressed videos is beneficial because they are rich of additional, pre-computed, features such as DCT coefficients, motion vectors and Macro blocks types.

The DC image is a thumbnail version that retains most of the visual features of its original full image. Taking advantage of the tiny size, timeless reconstruction and richness of visual content, the DC image could be employed effectively alone or in conjunction with other compressed domain features (e.g. AC coefficients, macro-block types and motion vectors) to represent video clips (with signature) and to detect similarity between videos for various purposes such as automated annotation, copy detection or any other higher layer built upon similarity between videos.

The Q/A was followed by a demonstration of the PGRs blog and discussion with PGRs (and attending staff) about the blog, BB community,…etc.

 

Amjad Altadmri – PhD

Amr Ahmed / / Uncategorized

Amjad Altadmri has passed his PhD viva, subject to minor amendments, earlier today.

Thesis Title:  “Semantic Video Annotation in Domain-Independent Videos Utilising Similarity and Commonsense Knowledgebases”

Thanks to the external, Dr John Wood from the University of Essex, the internal Dr Bashir Al-Diri and the viva chair, Dr Kun Guo.

Congratulations and Well done.

All colleagues are invited to join Amjad on celebrating his achievement, tomorrow (Thursday 28th Feb) at 12:00noon, in our meeting room MC3108, with some drinks and light refreshments available.

Best wishes.

 

February PGR Research Presentations

Amr Ahmed / / Uncategorized

The PGRs Research Presentations series has started on Wed. 13th Feb, 1pm, Meeting Room, MC3108 (3rd floor).

In each session we expect two PGR presentations. This session we had the following presentations:

 

Title: “A probabilistic approach   to Correctly and Automatically form of Retinal Vasculature“.

 Title:   “Semantic Video Analysis: from Camera Language to Human Language”

By: Touseef Qureshi

By: Amjad Altadmri
Abstract: 

Correct configuration and formation of   retinal vasculature is a vital step towards the diagnoses of these   cardiovascular diseases. A single minor mistake during the process of   connecting broken segments of vessels can lead to a completely incorrect   vasculature. Image processing techniques can’t alone solve this problem. On   the other hand, we are working on multidimensional scientific approach that   integrates Artificial intelligence, image process techniques, statistics and   probability. We are working and expecting an optimal approach towards the   correct configuration of broken vessels segments at junctions, bridges, and   terminals.

 Abstract 

The   rapidly increasing volume of visual data, available online or via   broadcasting, emphasizes the need towards building intelligent tools for   indexing, searching, rating, and retrieval. Textual semantic representations,   such as tagging, labeling and annotation, are often important parts of   videos’ indexing process, due to the advances in text analysis and their   intuitive user-friendly nature for representing semantics suitable for search   and retrieval.

 

Ideally,   this annotation should simulate the human cognitive way of perceiving and   describing videos. While these digital video mediums contain low-level visual   data, human beings have the ability to infer more meaningful information from   videos. The difference between these low-level contents and its corresponding   human perception is referred to as the “semantic gap”. This gap is even   harder to be handled in domain-independent uncontrolled videos, mainly due to   the lack of any previous information about the analyzed video on one side,   and the huge generic knowledge needed to be available on the other.