Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

A convolutional neural network for automatic analysis of aerial imagery

Maire, F., Mejias, L. and Hodgson, A.ORCID: 0000-0002-9479-3018 (2014) A convolutional neural network for automatic analysis of aerial imagery. In: International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014, 24-27 November 2014, Wollongong, NSW, Australia pp. 1-8.

Link to Published Version:
*Subscription may be required
Free to read:
*No subscription required


This paper introduces a new method to automate the detection of marine species in aerial imagery using a Machine Learning approach. Our proposed system has at its core, a convolutional neural network. We compare this trainable classifier to a handcrafted classifier based on color features, entropy and shape analysis. Experiments demonstrate that the convolutional neural network outperforms the handcrafted solution. We also introduce a negative training example-selection method for situations where the original training set consists of a collection of labeled images in which the objects of interest (positive examples) have been marked by a bounding box. We show that picking random rectangles from the background is not necessarily the best way to generate useful negative examples with respect to learning.

Item Type: Conference Paper
Murdoch Affiliation(s): School of Veterinary and Life Sciences
Publisher: IEEE
Copyright: © 2015 IEEE
Item Control Page Item Control Page