Classification of flying bats using computer vision techniques

Atanbori, John and Dickinson, Patrick (2012) Classification of flying bats using computer vision techniques. BMVA Summer School.

Documents
poster_bmva_esprc.pdf
[img]
[Download]
[img]
Preview
PDF
poster_bmva_esprc.pdf - Whole Document

311kB
Item Type:Other
Item Status:Live Archive

Abstract

We are developing computer vision techniques to automatically monitor bat populations, and extract biometric features which will
be used to gather important population data. The biometric features will include shape, speed, trajectory features, and wing beat
frequency. We will then use classifiers built using Support Vector Machines (SVM) and Neural Networks, to classify bats into
species type, male, female, pregnant and young by tracking individual bats in 2D and 3D in low-light using standard cameras
The Department for environment, food and rural affairs (DEFRA) in association with the Bat Conservation Trust (BCT) started a
national bat monitoring programme in 1996. Questions that their surveys seek to answer include: Which species are affected by
habitat changes? What are bats’ hibernation habits? And how many bats at roosting site are females/males, young, pregnant etc.?
Bat populations also roost in buildings, including historic buildings such as churches. This habitation often leads to damage to
building fabric and sensitive artefacts. Data about these populations enables the effective management and protection of the
buildings they inhabit, and we anticipate that our work will be useful not only to conservationist studying bats, but also to building
managers and professional ecologists surveying these buildings.

Additional Information:We are developing computer vision techniques to automatically monitor bat populations, and extract biometric features which will be used to gather important population data. The biometric features will include shape, speed, trajectory features, and wing beat frequency. We will then use classifiers built using Support Vector Machines (SVM) and Neural Networks, to classify bats into species type, male, female, pregnant and young by tracking individual bats in 2D and 3D in low-light using standard cameras The Department for environment, food and rural affairs (DEFRA) in association with the Bat Conservation Trust (BCT) started a national bat monitoring programme in 1996. Questions that their surveys seek to answer include: Which species are affected by habitat changes? What are bats’ hibernation habits? And how many bats at roosting site are females/males, young, pregnant etc.? Bat populations also roost in buildings, including historic buildings such as churches. This habitation often leads to damage to building fabric and sensitive artefacts. Data about these populations enables the effective management and protection of the buildings they inhabit, and we anticipate that our work will be useful not only to conservationist studying bats, but also to building managers and professional ecologists surveying these buildings.
Keywords:Computer Vision
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:5946
Deposited On:05 Jul 2012 21:13

Repository Staff Only: item control page