Konovalov, Dmitry A., Jahangard, Simindokht, and Schwarzkopf, Lin (2018) In situ cane toad recognition. In: Proceedings of the International Conference on Digital Image Computing. From: DICTA 2018: Digital Image Computing: techniques and applications, 10-13 December 2018, Canberra, ACT, Australia.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Cane toads are invasive, toxic to native predators, compete with native insectivores, and have a devastating impact on Australian ecosystems, prompting the Australian government to list toads as a key threatening process under the Environment Protection and Biodiversity Conservation Act 1999. Mechanical cane toad traps could be made more native-fauna friendly if they could distinguish invasive cane toads from native species. Here we designed and trained a Convolution Neural Network (CNN) starting from the Xception CNN. The XToadGmp toad-recognition CNN we developed was trained end-to-end using heat-map Gaussian targets. After training, XToadGmp required minimum image pre/post-processing and when tested on 720×1280 shaped images, it achieved 97.1% classification accuracy on 1863 toad and 2892 not-toad test images, which were not used in training.

Item ID:	57212
Item Type:	Conference Item (Research - E1)
ISBN:	978-1-5386-6602-9
Related URLs:	Publisher
Date Deposited:	27 Feb 2019 00:19
FoR Codes:	46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461199 Machine learning not elsewhere classified @ 100%
SEO Codes:	96 ENVIRONMENT > 9604 Control of Pests, Diseases and Exotic Species > 960402 Control of Animal Pests, Diseases and Exotic Species in Coastal and Estuarine Environments @ 100%
Downloads:	Total: 4
	More Statistics