Abstract: Annually, the field harvest damaged by the wild animals is in sharp increase in India. It sometime poses hazards to humans and animals. Since then, more and more wild animals are causing damage to crops and farmland so that humans cannot tolerate it. Therefore, they require an vital and appropriate solution to overcome this situation. The goal of this research article is to recognize
animals before they are introduced in cultivation areas and implement appropriate real-time warning mechanisms. The presence of the animal will be sent to the farmer through application with an audible sound. In this study, two Convolutional Neural Networks (CNN) classification models have been developed using the machine learning YOLO algorithm as a pretrained model to detect elephants, wild boars. The two models have been merged and run on, which referred as the system processing unit for this, takes animal images, and predicts them.
The findings of this research indicate that the accuracy rate of the classification model is 86 percentage. This system dramatically reduces human animal conflicts between human animals in crop fields by automatically setting up alert mechanism depending on the prediction.

Keywords: Animal Recognition, User Alert, Convolutional Neural Network, IOT, YOLO

PDF | DOI: 10.17148/IJARCCE.2022.114159

Open chat
Chat with IJARCCE