Camera Vision Based Animal Beat Back System for Agriculture Using Machine Learning

Authors

  • Rathish J
  • Manikandan S
  • Priyadarshini S
  • Velmani Ramasamy S

Keywords:

Animal detection, Energy reduction, Deep learning.

Abstract

Recently, automatic wild animal detection methods using deep learning for taken images by camera traps have been reported. Energy consumption is important for edge devices that include deep learning because such devices are required to use outside where commercial power is not supplied. In this paper, we propose energy reduction methods for a wild animal detection device. The proposed methods are sensitivity adjustment for the motion sensor, attachment of a hat, motion detection by a frame difference method, and separation of functions on the device. The sensitivity adjustment for the motion sensor reduces the number of taking images by the camera. The attachment of a hat reduces the number of sensing’s by the motion sensor. The frame difference method reduces the number of inferences by deep learning. The separation of functions on the device reduces the power consumption in both operation time and idle time. In the experiments, we evaluate the effect of the proposed four methods by applying them to a wild animal detection device which we proposed previously. We compare the energy reduction ratio when each method is applied and all methods are combined. Compared to the device without the proposed methods, we can reduce the energy consumption by more than half when we combined all methods.

Downloads

Download data is not yet available.

Downloads

Published

2023-05-19

How to Cite

Rathish J, Manikandan S, Priyadarshini S, & Velmani Ramasamy S. (2023). Camera Vision Based Animal Beat Back System for Agriculture Using Machine Learning. International Journal of Progressive Research in Science and Engineering, 4(5), 105–118. Retrieved from https://journal.ijprse.com/index.php/ijprse/article/view/845

Issue

Section

Articles