Conference paper
A convolutional neural network for automatic analysis of aerial imagery
2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp.1-8
IEEE
International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014 (Wollongong, NSW, Australia, 24/11/2014–27/11/2014)
2014
Abstract
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.
Details
- Title
- A convolutional neural network for automatic analysis of aerial imagery
- Authors/Creators
- F. Maire (Author/Creator) - Queensland University of TechnologyL. Mejias (Author/Creator) - Queensland University of TechnologyA. Hodgson (Author/Creator) - Murdoch University
- Publication Details
- 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp.1-8
- Conference
- International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014 (Wollongong, NSW, Australia, 24/11/2014–27/11/2014)
- Publisher
- IEEE
- Identifiers
- 991005541947907891
- Copyright
- © 2015 IEEE
- Murdoch Affiliation
- School of Veterinary and Life Sciences
- Language
- English
- Resource Type
- Conference paper
Metrics
102 Record Views