PGRs Research Presentations – July 2013

Amr Ahmed / / Uncategorized

The May’s PGRs Research Presentations was held on Wed. 10th July, 2pm, Meeting Room, MC3108 (3rd floor).

This session we had the following presentations:

Title: “Using anisotropic spatiotemporal smoothing to reduce blurring in images under low light conditions“. Title:   “Automated Robot Control with Behaviour Selection, Object Classification and Background Subtraction”

By: Gabriel Zahi

By: Daniel Pashley & Sean Walton
Abstract:Improving images in low light involves the process of summing neighbouring pixels locally in space and time to improve the reliability of the intensity of each pixel and to reduced the effect of noise acquired when capturing images under low light conditions. The summation process is stronger among neighbourhood pixels closer to the central pixel and reduces as the pixels are further away from the central pixel. Though the summation process is an effective way of improving the reliability of  low light images, it has an adverse effect of blurring the image. This presentation introduces the use of the gradient as an anisotropic method to reduce the noise in the images as well as reducing the blurring caused by the summation method. Using the gradient in the three dimension (x,y,t),  we can channel the summation process to lean more towards homogenous pixels and less along non-homogenous pixels. This new approach has proven to reduce the blurring while preserving structures and details.. Abstract: Our research aims to try and tackle some common risks and issues in traditional search and rescue methods by providing an alternative method by which search and rescue can be carried out.  We show how automated ground and air based robots can be used to reduce risk and cost but in turn increase speed of searching.  To do this, cost differences between current search and rescue methods and commercial robotic platforms that can be used in place of traditional methods are shown.  Along with this, we present how search methods can be improved by replacing one or two helicopters with forty ground and air robots laid out in an efficient pattern that allows the fastest search method.  We also show how we can utilise these robots through a central system and use all images and data provided by each of the connected robots to perform background removal and face detection, then use the data in a finite state machine based control system to send control commands back to the robots.  Finally, we present a series of experiments along with their results to prove the validity of this solution.

 

 

Additional presentation by Oliver Szymanezyk , titled:

“Brief on the Masters Prizes and his experience of the event”

 

The Q/A was followed by a brief cath-up meeting.

 

EMESP Masters Prize 2013

Oliver Szymanezyk / / Uncategorized

On Thursday, 19th June 2013, Olivier Szymanezyk, a PhD games computing student at the Lincoln School of Computer Science travelled to Leicester to represent the University of Lincoln at the East Midlands Engineering and Science Professionals (EMESP) Masters Prize.

As described on their homepage, the EMESP provides a voice for the engineering and science profession in the East Midlands. It aims to make people aware and appreciative of the contributions of engineering and science to the economy, prosperity and quality of life. The yearly EMESP Masters Prize aims to link research with industry, allowing prosperous candidates to show their research, ideas and innovations in front of a well-chosen panel of industry experts and academics.

Upon his arrival, Olivier was warmly welcomed by the EMESP Chairman, Ian Treacy, who introduced him to other Masters Prize University representatives. This was shortly followed by a twenty minute presentation of each candidate of their ongoing work. Presentations were most interesting and included talks about blood clotting countermeasures, climate change dwelling adaptations, big data visualisations and novel approaches to the control of quad-rotor helicopters. Olivier talked about his games computing related work on the verification and validation process of simulated crowds for serious applications and video-game environments.

“It was most honourable to have been appointed by a panel of University of Lincoln academics as the representative of the University of Lincoln for the EMESP Masters Prize Event”, says Olivier, “This was a fantastic opportunity to show my work – I highly enjoy talking about my interdisciplinary crowd simulation research, and this was a great opportunity to do so. Furthermore, this was a most well organised event to see research presentations from other EMESP Masters Prize candidates from a wide array of research fields.”

Olivier was awarded the prize as the University’s representative, for his project and presentation, which, in the view of the EMESP Masters Prize 2013 judges and the evidence of its content, was of a high standard and has the potential to make commercial impact. Pictures of the award can be seen below – more pictures of the event will follow shortly.

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 – June 2013

Amr Ahmed / / Uncategorized

The May’s PGRs Research Presentations was held on Wed. 14th June, 11am, Meeting Room, MC3108 (3rd floor).

This session we had the following presentations:

Title: “Automatic Analysis of the Social Behaviours of Fish using Computer Vision“. Title:   “Investigating text analysis of user-generated contents for health related applications”

By: Alaa Al-Zoubi

By: Deema Abdal Hafeth
Abstract: The development of computer vision as a method for automatically monitoring and analysing human activities is a well established research area. However, the application of this technology to support analysis of animal behaviour is a relatively new area of research that is attracting increasing attention from both the computer science and biological science communities.
Current state-of-the-art fish monitoring systems are lack of intelligent in interpreting fish behaviors automatically. Sticklebacks have been a model species in behavioral biology for over half a century.  Traditional methods of studying the social behavior of these fish involve manual observation and recording. However, these methods are time-consuming, potentially error prone, and a limiting factor on the amount of data which can be analysed. To tackle these problems, We are developing a computer vision system to automatically detect and track the social behaviors of sticklebacks, under laboratory conditions. Our system will provide automated quantitative measurements for researchers to collect and analysis stickleback’s behaviors. The system will have the ability to deal with large dataset for a long period of time to facilitate studying the sticklebacks life cycle.		 Abstract: Data in patients’ records includes free-form text, which have valuable medical related information embedded in. This data can be extremely useful in aiding and providing better patient care. Text analysis techniques have demonstrated the potential to unlock such information from text. One challenge with clinical reports’ data is their strict availability and difficulties in accessing them. On the other hand, people are expressing themselves more widely nowadays and the online user-generated contents (UGC), like forums and blogs, are becoming more available. The aim of this work is to investigate the potential of text analysis techniques in predicting the smoking status but from user-generated contents such as forums. This especially includes the use of Psycholinguistic features on analysing forums, with the hypothesis that forum posts have different linguistic features and are rich in personal stories, fresh opinions, and thoughts.

 

 

 

The Q/A was followed by a brief cath-up meeting.

 

PGRs Research Presentations – May 2013

Amr Ahmed / / Uncategorized

The May’s PGRs Research Presentations was held on Wed. 8th May, 2pm, Meeting Room, MC3108 (3rd floor).

This session we had the following presentations:

Title: “Automatic Phonetization of Holy Quran Text to build Arabic phonetic corpus“. Title:   “Understanding the correlation between the personalities of video game players and the decisions they make in a game environment; using action analysis and personal temperament profiling techniques to expand game design theory.”

By: Belal Al-Daradkah

By: Samuel Battye
Abstract:The large vocabulary phonetic corpus is an essential component of speech processing application. This research is to build an Arabic phonetic corpus from the Holy Quran text. This will be the base of developing Text-to-Speech (TTS) and Large Vocabulary Speech Recognition (LVSR) . The corpus will be built on a phonetic dictionary generated automatically by using Arabic pronunciation rules of Arabic language and Tajweed rules. Abstract: As more people become video game players, due to the vast expanse of the gaming industry, there are more player personalities than ever in the gaming environment. Different kinds of players often conflict with one another in multiplayer environments as diverse and varied play-styles emerge. Using temperament profiling techniques, game design theory and a player decision oriented game, this project looks at understanding how these vast ranges of personalities interact, and how innovative game design can be used to create games that accommodate as many different kinds of video game players as possible, while increasing a user’s enjoyment by reducing player to player conflict.

The Q/A was followed by a brief cath-up meeting with update on the latest procedures.