Porcupine Recognition Algorithm Based on Gaussian Mixture Background Modeling

DOI

10.2991/ceie-16.2017.27How to use a DOI?

Keywords

Porcupine Identification; Intelligent Control; Gaussian Mixture Background Modeling; Contour Detection

Abstract

Porcupine identification is a key part of porcupine intelligent monitoring system. This paper proposes a porcupine recognition algorithm based on Gaussian Mixture background modeling. The algorithm completes identification and feature extraction of the porcupine based on the calculation and withdrawal of image preprocessing, background modeling, foreground segmentation, contour extraction and parameter. Use the video collected in a porcupine farm to randomly screenshot 1036 frames and 1304 frames of night and daytime video image to verify the algorithm. The experimental results show that as for the image of multiple porcupines, the night recognition rate may reach 81.81%. Due to the influence of daytime ray changes, shadow generates from porcupine shape and porcupine life (night activity, daytime sleeping) and the daytime correct recognition rate is only 61.41%. This research provides a reference for research on the porcupine behavior recognition in intelligent monitoring system of porcupine.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shouhua Yu
AU  - Liyi Xian
AU  - Wei Yang
AU  - Tao Zou
AU  - Lingfeng Yuan
AU  - Zhenguo Zhu
AU  - Qingsong Yang
PY  - 2016/10
DA  - 2016/10
TI  - Porcupine Recognition Algorithm Based on Gaussian Mixture Background Modeling
BT  - Proceedings of the International Conference on Communication and Electronic Information Engineering (CEIE 2016)
PB  - Atlantis Press
SP  - 198
EP  - 212
SN  - 2352-5401
UR  - https://doi.org/10.2991/ceie-16.2017.27
DO  - 10.2991/ceie-16.2017.27
ID  - Yu2016/10
ER  -