Abstract

Seabird populations are considered an important and
accessible indicator of the health of marine environments:
variations have been linked with climate change
and pollution [9], as well as changes in fish stock levels.
However, manual monitoring of large populations
is labour-intensive, and so necessarily limited in scope.
In this paper we present work currently being conducted
as a pilot to develop computer vision as a means of automatically
monitoring nesting birds. The long-term
objective is to provide ecology researchers with behavioural
data on a scale not currently available.
We begin by describing the context and objectives
for our work, which are centred around on-going manual
monitoring of a specific population of Common
Guillemots on Skomer Island, West Wales (UK). This
project was initiated in February 2010, and as such still
in an early stage of development: from this perspective
we describe our forthcoming data collection programme,
anticipated technical challenges, and initial
development of video and image processing techniques.