Salvato in:
Dettagli Bibliografici
Autori principali: Li, Kunming, Shan, Mao, Perez, Stephany Berrio, Luo, Katie, Worrall, Stewart
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.12222
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929633984774144
author Li, Kunming
Shan, Mao
Perez, Stephany Berrio
Luo, Katie
Worrall, Stewart
author_facet Li, Kunming
Shan, Mao
Perez, Stephany Berrio
Luo, Katie
Worrall, Stewart
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2412_12222
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Endangered Alert: A Field-Validated Self-Training Scheme for Detecting and Protecting Threatened Wildlife on Roads and Roadsides
Li, Kunming
Shan, Mao
Perez, Stephany Berrio
Luo, Katie
Worrall, Stewart
Computer Vision and Pattern Recognition
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
title Endangered Alert: A Field-Validated Self-Training Scheme for Detecting and Protecting Threatened Wildlife on Roads and Roadsides
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.12222