Authors :
K Bhumika; Sirisha Madhuri T. ; G. Radhika; CH Ellaji
Volume/Issue :
Volume 7 - 2022, Issue 12 - December
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3vf5CeE
DOI :
https://doi.org/10.5281/zenodo.7472010
Abstract :
One of the greatest dangers to agricultural
productivity is animal damage to agriculture. Crop
raiding has become one of the most antagonistic humanwildlife conflicts as cultivated land has expanded into
previous wildlife habitat. Farmers in India endures major
risks from pests, natural disasters, and animal damage, all
of which result in lesser yields. Traditional farming
methods are unsuccessful and hiring guards to watch
crops and keep animals at bay is not a practical solution.
It is critical to protect crops from animal damage while
also redirecting the animal without injuring it, as the
safety of both animals and people is essential. To get over
these obstacles and accomplish our goal, we employ the
deep learning concept of convolutional neural networks, a
subfield of computer vision, to identify animals as they
enter our farm. The primary goal of this project is to
constantly monitor the entire farm using a camera that
records the surroundings at all hours of the day. We
identify animal infiltration using a CNN algorithm
and Xgboost and notify farmers when this occurs.
Keywords :
CNN, XGBoost, Computer vision.
One of the greatest dangers to agricultural
productivity is animal damage to agriculture. Crop
raiding has become one of the most antagonistic humanwildlife conflicts as cultivated land has expanded into
previous wildlife habitat. Farmers in India endures major
risks from pests, natural disasters, and animal damage, all
of which result in lesser yields. Traditional farming
methods are unsuccessful and hiring guards to watch
crops and keep animals at bay is not a practical solution.
It is critical to protect crops from animal damage while
also redirecting the animal without injuring it, as the
safety of both animals and people is essential. To get over
these obstacles and accomplish our goal, we employ the
deep learning concept of convolutional neural networks, a
subfield of computer vision, to identify animals as they
enter our farm. The primary goal of this project is to
constantly monitor the entire farm using a camera that
records the surroundings at all hours of the day. We
identify animal infiltration using a CNN algorithm
and Xgboost and notify farmers when this occurs.
Keywords :
CNN, XGBoost, Computer vision.
