Development of a Detection System for Endangered Mammals in Negros Island, Philippines Using YOLOv5n

Citation

Castañeda, John Alfred J. and De Castro, Angelo L. and Sy, Michael Aaron G. and AlDahoul, Nouar and Tan, Myles Joshua Toledo and Abdul Karim, Hezerul (2023) Development of a Detection System for Endangered Mammals in Negros Island, Philippines Using YOLOv5n. Lecture Notes in Electrical Engineering, 983. pp. 435-447. ISSN 1876-1100

Full text not available from this repository.

Abstract

Many species have gone extinct as a result of human neglect and various environmental influences. Monitoring these species has proven to be a challenge due to their small population, remote habitats, and evasiveness, among other reasons. Nonetheless, they can be routinely tracked by using CCTV cameras. This project made use of a transfer learning approach to detect the presence of Malayan civets (Viverra tangalunga), Visayan leopard cats (Prionailurus javanensis sumatranus), Visayan spotted deer (Rusa alfredi) and Visayan warty pigs (Sus cebifrons) in the forests of Negros Island. We also developed a web application to record camera data and assign timestamps. The setup consisted of a Raspberry Pi 3B+ and a Raspberry Pi camera module powered by a solar power bank. The method used YOLOv5n, a lightweight object detection algorithm, to detect the four species. The trained model yielded 91% mAP, 64% mAP@0.5:0.95, and the following average precisions: 94% (Visayan warty pig), 91% (Malayan civet), 88% (Visayan leopard cat), and 91% (Visayan spotted deer) with 4.5 GFLOPs.

Item Type: Article
Uncontrolled Keywords: Animal detection, Transfer learning, Endangered species, Negros Island, Object detection, Philippines, Raspberry Pi, YOLOv5n
Subjects: Q Science > QP Physiology > QP501-801 Animal biochemistry
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 04 Jul 2023 02:23
Last Modified: 04 Jul 2023 02:23
URII: http://shdl.mmu.edu.my/id/eprint/11508

Downloads

Downloads per month over past year

View ItemEdit (login required)