[visionlist] Fully-funded Phd Oportunity at Queen's University

[Jesus Martinez del Rincon]

DEL CSIT PhD Studentship 2013
Vision-based activity recognition for real life applications
Principal Supervisor: Jesus Martinez del Rincon
Project Description:

Research into human activity recognition is becoming one of the most active research areas of the computer vision community.  This is motivated by the increasing needs of real-world applications in areas as ambient assisted living and security surveillance. In this framework, the acquisition of activity information describing interactions between individuals is particularly relevant. This capability would lead to a significant enhancement of safety and security by automatically detecting, for example, fighting or damaging property in public places or elderly people falling at home.

A typical activity recognition system is composed of four steps, namely target detection, behaviour tracking, action recognition and finally a reasoned activity evaluation. While considerable progress has been made in all the steps, activity recognition systems still suffer from scalability and reusability. This is due to the complexity of real world scenarios, such as highly varied activities or the diversity of natural environments.
The aim of this work is to address the previous limitations and to develop a novel framework for extracting, modelling and classifying activities. The system will be verified and its performance evaluated in realistic datasets and real world applications.
Objectives:

    To explore local 2d/3d features to characterise atomic actions and activities by encapsulating spatio-temporal information.
    To investigate, optimise and develop new classification and activity recognition strategies based on machine learning and pattern recognition.
    To use new and innovative sensors such as Microsoft Kinect, depth cameras, microphones and RFID tags to complement and enhance the information provided by monocular video cameras.
    To extend previous action recognition algorithms into interactive activities, where the interaction between actors can improve the global decisions.
    To develop new strategies to detect anomalous and dangerous behaviours out of the knowledge base.

Academic Requirements:

A minimum 2.1 honours degree or equivalent in Electrical and Electronic Engineering or Computer Science or other relevant subject is required.
Start Date: 1 October 2013
General Information

This 3 year PhD studentship, funded by the Department for Employment and Learning (DEL), commences on 1 October 2013, covers approved tuition fees and a maintenance grant of approximately £13,590.

Applicants should apply electronically through the Queen's online application portal at: https://dap.qub.ac.uk/portal/

Further information available at:  http://www.qub.ac.uk/schools/eeecs/PhD/PostgraduateResearchScholarships/
Contact details:
Supervisor Name:            Dr Jesus Martinez del Rincon
Address:              ECIT Institute,
Queens Road,
Belfast,
BT3 9DT
Email:    j.martinez-del-rincon at qub.ac.uk
Tel:         +44 28(0) 9097 1779
Web:     http://www.csit.qub.ac.uk

Deadline for Submission of Applications: 15 March 2013

For further information on Research Area click on link below:
http://www.csit.qub.ac.uk/Research/ResearchGroups/IntelligentSurveillanceSystems/







DEL CSIT PhD Studentship 2013
Genetics-inspired Video Analysis
Principal Supervisor: Jesus Martinez del Rincon
Project Description:

Current video analysis approaches rely on controlling the huge number of parameters involved in videos. Since this results in the inability to address most real-life situations, a new strategy is required: it must be underpinned by the realisation that scene variability should be the expected norm rather than an inconvenience to control. This is exactly what a genetics-inspired approach will offer to the field of video analysis.

Analogies can be drawn between genomic data and images in terms of structure, evolution and processing tasks. Similarly to a line in an image which can be coded as a string of pixels, genetic material has a digital structure which is represented by a string of characters. Moreover, genetic material evolves over time through mutations. Likewise, a continuous video can be interpreted as the capture of a single image evolving through time. Thus, video analysis could be addressed by detecting and measuring these evolutions over time by quantifying 'mutations'.

The aim of this project is to devise, develop and apply a novel approach for video processing where videos are seen as mutating images. This analogy to genetics will allow the exploitation of genetics concepts to design novel algorithms for the field of video analysis [1,2].

References
[1] Dense Pixel Matching Between Unrectified And Distorted Images Using Dynamic Programming, J. Martínez del Rincón, J. Thevenon, R. Dieny, & J.-C. Nebel, International Conference on Computer Vision Theory & Applications, Italy, 2012
[2] Bioinformatics inspired algorithm for stereo correspondence, R. Dieny, J. Thevenon, J. Martínez del Rincón & J.-C. Nebel, International Conference on Computer Vision Theory & Applications, Portugal, 2011
Objectives:

    To design and develop a mutation based algorithm to allow the alignment of pairs of overlapping images. Images will neither require rectification nor be captured by lenses of similar focal-length, e.g. they could be taken by a moving camera with a zoom lens
    To design and develop an algorithm finding pixel correspondences across a set of images to extract scene background
    To validate the above approach, by implementing a system allowing robust tracking of objects in videos

Academic Requirements:

A minimum 2.1 honours degree or equivalent in Electrical and Electronic Engineering or Computer Science or other relevant subject is required.
Start Date: 1 October 2013
General Information

This 3 year PhD studentship, funded by the Department for Employment and Learning (DEL), commences on 1 October 2013, covers approved tuition fees and a maintenance grant of approximately £13,590.

Applicants should apply electronically through the Queen's online application portal at: https://dap.qub.ac.uk/portal/

Further information available at:  http://www.qub.ac.uk/schools/eeecs/PhD/PostgraduateResearchScholarships/
Contact details:
Supervisor Name:            Dr Jesus Martinez del Rincon
Address:              ECIT Institute,
Queens Road,
Belfast,
BT3 9DT
Email:    j.martinez-del-rincon at qub.ac.uk
Tel:         +44 28(0) 9097 1779
Web:     http://www.csit.qub.ac.uk

Deadline for Submission of Applications: 15 March 2013

For further information on Research Area click on link below:
http://www.csit.qub.ac.uk/Research/ResearchGroups/IntelligentSurveillanceSystems/








DEL PhD Studentship 2013/14
Human pose estimation for real scenarios. Dealing with multiple people and interaction
Principal Supervisor: Jesus Martinez del Rincon
Project Description:

Human pose recovery is one of the most challenging research areas in computer vision. Successful estimations of the human pose provide information and simplify further tasks such as activity recognition or behaviour analysis, and therefore, it can benefit a wide range of industrial sectors such as video surveillance, physical security or sport performance enhancement.

Constant steps forward have been made in this field, solving the problem for a single person performing a simple and repetitive activity in heavily constrained scenarios. However, pose recovery of complex actions in an unconstrained environment still remains a challenging problem. Even more if we consider that interaction
scenarios are of particular interest, e.g. martial arts, boxing, football in the sports domain, fighting, theft, exchanging luggage in the surveillance domain and dancing in the arts domain. To our knowledge, no research has been done for simultaneously recovering the pose of multiple people on video footage.

The aim of this project is to produce a system that tracks the articulated motion of a group of human beings that interact with each other in the scene. The system should be able to work in real life scenarios, such as sport analysis and video surveillance, combining information from multiple cameras. The project will incorporate and combine techniques from different field of expertise, such as activity recognition, action modelling, pose estimation and human tracking.
Objectives:

    To develop pose estimation algorithms capable of consider occlusions and interactions between multiple people and its impact in the individual pose estimation, as well as developing strategies to tackle their inherent problems.
    To combine activity recognition methods with pose recovery techniques in order to integrate coherently both philosophies, feeding back information to each other and improving the pose estimation accuracy when the activity or the interaction performed by the subjects is identified.
    To explore models and algorithms capable of representing interactions between people in the space of activities, by combining non-linear dimensionality reduction methods with advanced Markovian approaches that are able to model interactive activities.
    To validate the above approach, by implementing a system that tracks the 3D pose of small groups of interacting people from video footage on a general purpose scenario without pre-assumption of the performed activities.

Academic Requirements:

A minimum 2.1 honours degree or equivalent in Electrical and Electronic Engineering or Computer Science or other relevant subject is required.
General Information

This 3 year PhD studentship, funded by the Department for Employment and Learning (DEL), commences on 1 October 2013, covers approved tuition fees and a maintenance grant (unknown for 2013/14) is approximately £13,000 - £14,000.

Applicants should apply electronically through the Queen's online application portal at: https://dap.qub.ac.uk/portal/

Further information available at: http://www.qub.ac.uk/schools/eeecs/PhD/PostgraduateResearchScholarships/
Contact details:
Supervisor Name:            Jesus Martinez del Rincon
Address:              ECIT,
Queen's Road,
Queen's island
Belfast,
BT3 9DT
Email:    j.martinez-del-rincon at qub.ac.uk
Tel:         +44 28(0) 9097 1779
Web:     www.csit.qub.ac.uk

Deadline for Submission of Applications: 15 February 2013






SOFTWARE AND HARDWARE INTEGRATION IN TACKLING GLOBAL FOOD FRAUD AND FOOD PROCESSING PROBLEMS
Dr Jesus Martinez del Rincon and Dr Tassos Koidis of the School of Biological Sciences
Project Description:

In the current scene of global food supply and production, it is becoming increasingly challenging to detect sophisticated fraud, to tackle food processing problems and to meet consumers' elevated requirements of quality and safety. There is therefore a need to develop intelligent information systems, based on machine learning, artificial intelligence and pattern recognition, as well as integrating software and hardware in solving some key food science related problems such as detecting adulteration and geographical origin (e.g. oils) and automating food process control.

Current methods to authenticate foods are based on laboratory analyses or processing control, which requires heavy and expensive instruments or manual labour. By applying pattern recognition methods, food properties can be estimated accurately under complex scenarios, which would otherwise require time-consuming and often expensive analytical testing. In this project we aim to explore the applicability of signal processing and pattern recognition techniques in order to develop software useful in tackling food authenticity, safety and security problems. Moreover, mobile technology has yet to find its way in areas like food processing and control, which creates even more opportunities if appropriate software is embedded into low-cost mobile devices.

Some outcomes to be explored in this PhD are: a) software tools that help with calibration and analysis of complex chromatography, spectroscopic and other signals to verify authenticity of specific foods, based on machine learning and pattern recognition techniques, b) development of next generation searchable databases with food authenticity data to fight global food fraud, c) the proof-of-concept use of low-cost mobile computer in food processing and processing control including decision making.
Academic Requirements:

A minimum 2.1 honours degree or equivalent in Electrical and Electronic Engineering or Computer Science or other relevant subject is required.
General Information

This 3 year PhD studentship, funded by the Department for Employment and Learning (DEL), commences on 1 October 2013, covers approved tuition fees and a maintenance grant (unknown for 2013/14) is approximately £13,000 - £14,000.

Applicants should apply electronically through the Queen's online application portal at: https://dap.qub.ac.uk/portal/

Further information available at: http://www.qub.ac.uk/schools/eeecs/PhD/PostgraduateResearchScholarships/
Contact details:
Supervisor Name:            Jesus Martinez del Rincon
Address:              ECIT,
Queen's Road,
Queen's island
Belfast,
BT3 9DT
Email:    j.martinez-del-rincon at qub.ac.uk
Tel:         +44 28(0) 9097 1779
Web:     www.csit.qub.ac.uk
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist/attachments/20130123/4546e8fe/attachment.htm>