Use this URL to cite or link to this record in EThOS:
Title: Monitoring individual animals through a collaborative crowdsourcing and citizen science platform
Author: Mason, Aaron D.
ISNI:       0000 0004 5923 3714
Awarding Body: University of Surrey
Current Institution: University of Surrey
Date of Award: 2016
Availability of Full Text:
Access from EThOS:
Access from Institution:
Improvements in communication technology means that increasing numbers of people around the world can share information with increasing ease. This information is forming knowledge in forms that was not previously conventionally possible. It is enabling new communities to be formed. This research aimed to determine how this data could be exploited and combined with additional complementary tools to enable automated large-scale non-intrusive monitoring of wildlife, and in particular keystone species. Three proof-of-concept research studies explored automated camera traps, citizen science and large-scale crowdsourcing to determine the potential of a system that combines this technology and its use for automated monitoring of wild animals. The results demonstrated that internet-connected camera traps are capable of collecting valuable visual data at a large-scale. However, for keystone species, such as tigers, the scale required for monitoring presents technical and economic challenges. The participation of citizen scientists to collect and analyse data demonstrated a potential monitoring mechanism. However, the volume of data provided for such a focused practice proved insufficient for accurate large-scale monitoring. The Wildsense project, which used publicly-available image data from the Web as its primary data source demonstrated that there is additional data available that can be processed with the participation of citizen scientists. The popularity and overall interest towards this project showed that crowdsourcing is a viable method for collecting relevant data for animal monitoring. It was concluded that the proof-of-concept experiments completed provided evidence that there is a potential to monitor individual animals through an automated approach and a system architecture is proposed. There is potential for automated large scale monitoring using the proposed framework. However, there are significant challenges to overcome and multiple directions for future work are recommended for exploration.
Supervisor: Krause, Paul J. Sponsor: EPSRC
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available