# In Situ Cane Toad Recognition

## TL;DR

This paper presents a CNN-based method for accurately identifying invasive cane toads in images, aiding in the development of more wildlife-friendly traps and conservation efforts.

## Contribution

We developed XToadGmp, a CNN trained end-to-end for cane toad recognition, achieving high accuracy with minimal pre/post-processing.

## Key findings

- 97.1% classification accuracy on test images
- Effective end-to-end training with heat-map Gaussian targets
- Minimal image pre/post-processing required

## 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 720x1280 shaped images, it achieved 97.1% classification accuracy on 1863 toad and 2892 not-toad test images, which were not used in training.