Citation

Ong, Chee Thong and Tee, Connie and Goh, Michael Kah Ong and Choo, Kan Yeep (2023) Fusion of Visual and Acoustic Signals for Wildlife Recognition. In: 2023 IEEE 4th International Conference on Pattern Recognition and Machine Learning (PRML), 04-06 August 2023, Urumqi, China.

Text 37.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

In recent years, wildlife-vehicle collisions (WVC) on highways have become a serious problem, causing harm to both wild animals and drivers. Wildlife surveillance has emerged as an important tool to address this issue. CCTV systems can provide low-cost wildlife monitoring, but their performance can be hindered by environmental factors such as low light and poor weather conditions, leading to blurry and grainy imageries. To address these limitations, we propose a robust approach that integrates visual and acoustic signals for improved wildlife recognition. Our method utilizes machine learning techniques to extract features from both modalities and combines them through a multi-modal fusion framework. We evaluate our approach on a dataset of wildlife recordings and demonstrate its superiority over state-of-the-art methods that rely solely on visual or audio information. Our results highlight the potential of integrating visual and audio signals for wildlife recognition, with potential applications in conservation and ecological research

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Visual Signal, dataset of wildlife
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science U Military Science > U Military Science (General)
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	22 Feb 2024 07:32
Last Modified:	22 Feb 2024 07:32
URII:	http://shdl.mmu.edu.my/id/eprint/12116

Downloads

Edit (login required)