Chen-Burger, Y-H. and Tate, A. (2016) The Fish4Knowledge Virtual World Gallery, in "Fish4Knowledge: Collecting and Analyzing Massive Coral Reef Fish Video Data" (Fisher R.B., Chen-Burger, Y-H., Giordano, D., Hardman, L. and Lin, F.P. eds.), Chapter 17, pp. 245-251, April 2016, Intelligent Systems Reference Library, Volume 104, Springer. Book DOI 10.1007/978-3-319-30208-9 Electronic ISBN: 978-3-319-30208-9 Print ISBN: 978-3-319-30206-5. [PDF]
Chen-Burger, Y-H. and Tate, A. (2016) Fish4Knowlege: a Virtual World Exhibition Space for a Large Collaborative Project, Virtual Worlds Best Practices in Education 2016 (VWBPE-2016), HORIZONS: 9-14 March 2016. In Journal of Virtual Studies, Volume 7, Number 1, pp. 34-38, 2016, ISSN 2155-0107. [Online Journal, PDF] [VWBPE Resources Web Page]
See http://fish4knowledge.eu for more details of the Fish4Knowledge project [Alternative Site at Edinburgh].
OpenSim Resources - A directory of resources for the EU Fish4Knowledge project and its Second Life and OpenSim assets as OpenSim Archives (OARs) and Inventory Archives (IARs) licenced under the LGPL licence. Also provides an archive of the in world textures used for signboards and posters.
Screenshots - A directory of screenshots of the Fish4Knowledge Pavilion and Underwater Observatory in Second Life and OpenSim.
Fish4Knowledge Pavilion and Underwater Observatory in Second Life and OpenSim - Blog Post by Austin Tate (14th May 2013).
Fish4Knowledge Pavilion and Underwater Gallery in OpenSim - Blog Post by Austin Tate (20th October 2015).
The Fish4Knowledge Virtual Gallery can be accessed in several virtual
worlds locations:
Second Life and OpenSim
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 provides a major increase in the ability to analyse this data: 1) Video analysis automatically extracts information about the observed marine animals which is recorded in an observation database. 2) Interfaces have been designed to allow researchers to formulate and answer higher level questions over that database.
Click here to see a typical source video.
The project investigates: 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 was used to achieve this.
The project used live video feeds from 10 underwater cameras as a testbed for investigating more generally applicable methods for capture, storage, analysis and querying of multiple video streams. The project collateed a public database from 2 years containing video summaries of the observed fish and associated descriptors. Expert web-based interfaces were developed for use by the marine researchers themselves, allowing unprecedented access to live and previously stored videos, and previously extracted information. The marine researcher interface also allowed easy formulation of new queries. Extensive user community evaluations werecarried out to provide information on the accuracy, ease and speed of retrieval of information.
For a longer overview of the project: click here
Detecting targets in noisy environments.
Characterising interactions between the targets.
Recognising fish species by integrating multiple 2D perspectively distorted views over time.
Exploiting ontologies to interpret user queries.
Exploiting ontologies to convert queries into workflow sequences.
Storing and accessing massive amounts of video and RDF data in a timely manner.
Integration of the research in a publically usable web tool.
Creation of a fish database suitable for behavioural and environmental studies.
Training of staff in cross-disciplinary methods (computer vision with database and workflow scientists, computer scientists with biologists).
Fish4Knowledge was funded by the European Union Seventh Framework Programme [FP7/2007-2013] under grant agreement 257024, addressing Objective ICT-2009.4.3: Intelligent Information Management, Challenge 4: Digital Libraries and Content. NARL/NCHC is funded by the Taiwan National Science Council under grant agreement NSC 101-2923-I-492-002-MY2. We would also like to thank the Taiwan Power Company, Taiwan Ocean Research Institute and Kenting National Park for sharing their video datasets collected from their underwater observatories at Nanwan, Lanyu and Houbi Lake of Taiwan, which enabled this research. The project ran from October 1, 2010 through September 30, 2013.