Endangered Alert: A Field-Validated Self-Training Scheme for Detecting and Protecting Threatened Wildlife on Roads and Roadsides

TL;DR

This paper introduces a self-training detection scheme using cloud and edge computing, combined with a novel label-augmentation method, to identify threatened wildlife like cassowaries on roads, thereby reducing animal-vehicle collisions.

Contribution

It presents a field-validated self-training approach with LA-NMS and vision-language models for detecting rare animals in resource-limited environments, improving detection accuracy.

Findings

Improved detection accuracy over baseline models

Effective automatic data labelling with LA-NMS and VLM

Robust performance confirmed during five-month deployment

Abstract

Traffic accidents are a global safety concern, resulting in numerous fatalities each year. A considerable number of these deaths are caused by animal-vehicle collisions (AVCs), which not only endanger human lives but also present serious risks to animal populations. This paper presents an innovative self-training methodology aimed at detecting rare animals, such as the cassowary in Australia, whose survival is threatened by road accidents. The proposed method addresses critical real-world challenges, including acquiring and labelling sensor data for rare animal species in resource-limited environments. It achieves this by leveraging cloud and edge computing, and automatic data labelling to improve the detection performance of the field-deployed model iteratively. Our approach introduces Label-Augmentation Non-Maximum Suppression (LA-NMS), which incorporates a vision-language model (VLM) to enable automated data labelling. During a five-month deployment, we confirmed the method's robustness and effectiveness, resulting in improved object detection accuracy and increased prediction confidence. The source code is available: https://github.com/acfr/CassDetect