Classification of bird species from video using appearance and motion features

Atanbori, John and Duan, Wenting and Shaw, Edward and Appiah, Kofi and Dickinson, Patrick (2018) Classification of bird species from video using appearance and motion features. Ecological Informatics, 48 . pp. 12-23. ISSN 1574-9541

Full content URL: https://www.sciencedirect.com/science/article/pii/...

Documents
atanbori-ecoinf-2018.pdf

Request a copy
[img] PDF
atanbori-ecoinf-2018.pdf - Whole Document
Restricted to Repository staff only until 18 July 2020.
Available under License Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International.

1MB
Item Type:Article
Item Status:Live Archive

Abstract

The monitoring of bird populations can provide important information on the state of sensitive ecosystems; however, the manual collection of reliable population data is labour-intensive, time-consuming, and potentially error prone. Automated monitoring using computer vision is therefore an attractive proposition, which could facilitate the collection of detailed data on a much larger scale than is currently possible.

A number of existing algorithms are able to classify bird species from individual high quality detailed images often using manual inputs (such as a priori parts labelling). However, deployment in the field necessitates fully automated in-flight classification, which remains an open challenge due to poor image quality, high and rapid variation in pose, and similar appearance of some species. We address this as a fine-grained classification problem, and have collected a video dataset of thirteen bird classes (ten species and another with three colour variants) for training and evaluation. We present our proposed algorithm, which selects effective features from a large pool of appearance and motion features. We compare our method to others which use appearance features only, including image classification using state-of-the-art Deep Convolutional Neural Networks (CNNs). Using our algorithm we achieved an 90% correct classification rate, and we also show that using effectively selected motion and appearance features together can produce results which outperform state-of-the-art single image classifiers. We also show that the most significant motion features improve correct classification rates by 7% compared to using appearance features alone.

Keywords:Computer vision, Bird specied recognition
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:32791
Deposited On:23 Jul 2018 09:10

Repository Staff Only: item control page