Postdoctoral Research Associate in Computer Vision, UK

Sponsored Links

Career Blog

Jewelry Design Scholarships 2012 – Career in Gemology and Jewelry Manufacturing

UNCF Scholarships Program 2012 – United Negro College Fund

September 4, 2010

Postdoctoral Research Associate, Computer Vision, University of Edinburgh, UK

Job Description: The School of Informatics has been awarded funding from the EC for participation in a multi-site research project entitled Fish4Knowledge: “Supporting humans in knowledge gathering and question answering w.r.t. marine and environmental monitoring through analysis of multiple video streams”. The principal investigator on the Edinburgh component of the project that is responsible for process modelling and workflow execution is Dr. Jessica Chen-Burger. The project is funded from October 1, 2010 until September 30, 2013.

The research proposed here will take place in the AIAI unit of the Centre of Intelligent Systems and their Applications. CISA undertakes basic and applied research and development in knowledge representation and reasoning. Through its Artificial Intelligence Applications Institute (AIAI) it works with others to deploy the technologies associated with this research. AIAI specialises in Intelligent Systems – systems making use of the knowledge of experts, or systems that learn.

The research proposed here is funded under the EC’s Framework 7 ICT programme (Intelligent Information Management). Fish4Knowledge is a STREP (Specific Targeted Research Project).

The study of marine ecosystems is vital for understanding environmental effects, such as climate change and the effects of pollution, but is extremely difficult because of the inaccessibility of data. Undersea video data is usable but is tedious to analyse (for both raw video analysis and abstraction over massive sets of observations), and is mainly done by hand or with hand-crafted computational tools. Fish4Knowledge will allow a major increase in the ability to analyse this data: 1) Video analysis will automatically extract information about the observed marine animals which is recorded in an observation database. 2) Interfaces will be designed to allow researchers to formulate and answer higher level questions over that database.

The project will investigate: information abstraction and storage methods for reducing the massive amount of video data (from 10E+15 pixels to 10E+12 units of information), machine and human vocabularies for describing fish, flexible process architectures to process the data and scientific queries and effective specialised user query interfaces. A combination of computer vision, database storage, workflow and human computer interaction methods will be used to achieve this.

The project will use live video feeds from 10 underwater cameras as a test-bed for investigating more generally applicable methods for capture, storage, analysis and querying of multiple video streams. We will collate a public database from 2 years containing video summaries of the observed fish and associated descriptors. Expert web-based interfaces will be developed for use by the marine researchers themselves, allowing unprecedented access to live and previously stored videos, or previously extracted information. The marine researcher interface will also allow easy formulation of new queries. Extensive user community evaluations will be carried out to provide information on the accuracy, ease and speed of retrieval of information.

Project Environment and Conditions
The Edinburgh portion of the project will normally not use any specialised equipment. The image capture and supercomputer based processing are primarily NARL’s responsibility. A 500+ node compute server parallel system is also accessible by the group. Wherever possible we will use either MATLAB and C/C++ within a LINUX/UNIX environment (mainly for speed). There is some existing software related to this project. Altogether, there are 10 PCs available for use by the vision research group (consisting of about 10 members, including contract research staff, PhD and MSc students).

The UEDIN workflow team will have to liaise closely with other teams, particularly with the UCATANIA image processing team over the interaction and use of their fish detection and tracking software, the UEDIN machine vision team over the interaction and use of their fish recognition system, the CWI team over the development of properties suitable for question answering and the interaction with their systems, and the NARL team over the development of parallel workflow execution algorithms.

Application Deadline: 5th October 2010

For further scholarship information

Scholarship Tags: associate, Fellowship, Postdoctoral, research