The findings of our work
contribute to conservation of elephant issues and solutions to human elephant
conflict. We recommend the usage of real time system to identify individual
animals or group of animals approaching the human habitats. This study provides
insights to safeguard the animals from human activities and reduces the work
pressure for the forest officials. Our model overcomes the drawbacks of the
existing system. Location detection and humidity detection along with animal
detection is done. Our system can be deployed at forest borders, tea estates, food
plantation, water holes, migration routes etc. for elephant monitoring and
detection. Human-animal collision can be reduced to a greater extent. Our
system also focuses on conservation of rare species. Humidity can also to
monitored and notified. Traditional observation can be less effective.
Therefore, automated systems are being used. The real time automated approach
minimizes manual work and is more efficient and reliable when compared to all
existing systems. Thus, not only monitoring and detecting, prediction of future
is also possible in Internet of Things (IoT).
1 T. Clutton- Brock
and B. C Sheldon, “Individuals and populations: the role of long-term,
individual-based studies of animals in ecology and evolutionary biology, ”
Trends in Ecology and Evolution, vol. 25, pp. 562-573, Sept. 2010.
2 CH. Lampert, H. Nickisch, and S.
Harmeling, “Learning to detect unseen object classes by between-class
attribute transfer,” in Computer Vision and Pattern Recognition, International
Conference on (CVPR). IEEE, 2009, pp. 951-958.
3 O.M. Parkhi, A.
Vedaldi, A. Zisserman, and Cv. Jawahar, “Cats and dogs,” in Computer
Vision and Pattern Recognition, International Conference on (CVPR). IEEE, 2012,
4 WW Zhang, 1. Sun,
and X.O. Tang, “Cat head detection how to effectively exploit shape and
texture features,” in Computer Vision, European Conference on (ECCV), 2008, pp.
5 J.P. Crall, Cv. Stewart, T. Y.
Berger-Wolf, and D. 1. Etc. Rubenstein, “Hots potter patterned species
instance recognition,” in Application of Computer Vision, IEEE Winter
Conference on (WACV). IEEE, 2013, pp. 230- 237.
6 M. J. Wilber, W. J.
Scheirer, P. Leitner, and B. etc. Heflin, “Animal recognition in the
mojave desert: Vision tools for field biologists, ” in Application of
Computer Vision, IEEE Winter Conference on (WACV). IEEE, 2013, pp. 206-213.
7 P. E Felzenszwalb,
R. B. Girshick, D.Mc Allester, and D. Ramanan, “Object detection with
discriminatively trained part based models, ” Pattern Analysis and Machine
Intelligence, IEEE Transactions on (PAM/), vol. 32, pp. 1627-1645, Sept. 2010.
8 N. Dalal and B.
Triggs, “Histograms of oriented gradients for human detection, ” in
Computer Vision and Pattern Recognition, International Conference on (CVPR).
IEEE, 2005, vol. 1, pp. 886-893.
9 P. Luo, Y.L. Tian,
X. G. Wang, and X.O. Tang, “Switchable deep network for pedestrian
detection, ” in Computer Vision and Pattern Recognition, International
Conference on (CVPR). IEEE, 2014, pp. 899-906.
10 M. Daly, P.R. Behrends, and M. 1. Wilson,
“Activity patterns in small mammals,” Ecological Studies, vol. 141, pp.
11 L. C Liu, A.
Wiliem, S.K. Chen, and B. C Lovell, “Automatic image attribute selection
for zero-shot learning of object categories, ” in Pattern Recognition, International
Conference on (ICPR). IEEE, 2014, pp. 2619-2624.
12 Arnold Wiliem, Vamsi Madasu, Wageeh Boles,
and Prasad Yarlagadda, “A context-based approach for detecting suspicious
behaviours , ” in Digital Image Computing: Techniques and Applications.
IEEE, 2009, pp. 146-153.
Yang, Z.G. Ma, EP. Nie, X. J. Chang, and A. G. Haupt mann, “Multi-class
active learning by uncertainty sampling with diversity maximization,” International
Journal of Computer Vision (lJCV), pp. 1-15, Nov. 2014.