Automated visual monitoring of nesting seabirds

Seabird populations are considered an important andaccessible indicator of the health of marine environments:variations have been linked with climate changeand pollution [9], as well as changes in fish stock levels.However, manual monitoring of large populationsis labour-intensive, and so necessarily limited in scope.In this paper we present work currently being conductedas a pilot to develop computer vision as a means of automaticallymonitoring nesting birds. The long-termobjective is to provide ecology researchers with behaviouraldata on a scale not currently available.We begin by describing the context and objectivesfor our work, which are centred around on-going manualmonitoring of a specific population of CommonGuillemots on Skomer Island, West Wales (UK). Thisproject was initiated in February 2010, and as such stillin an early stage of development: from this perspectivewe describe our forthcoming data collection programme,anticipated technical challenges, and initialdevelopment of video and image processing techniques.