CNN based image detection system for elephant directions to reduce human-elephant conflict

Abstract

Abstract: Human-Elephant Conflict has been a major issue in the forest border areas, where the human habitat is destroyed by the entry of wild elephants. This conflict depends due to the shared field of humans and elephants. Conflict often occurs over access to water and competition for space and food. Economic losses happen due to agricultural destruction or loss of cattle during predation. The major aim of the study is to minimize the human-elephant conflict in the forest border areas and the conservation of elephants from human activities as well as protect human lives from elephant attacks. Humans use various technical and nontechnical methods to reduce this conflict. As this research is using neural networks and image processing technologies, forest authorities can detect how many elephants are in the nearby forest border areas and distinguish elephants from other animals easily. Then authorities can inform villagers and tourists hence reducing the humanelephant conflict. Convolutional Neural Network (CNN) is playing a major role in elephant detection by supporting efficient image classification. CNN’s performance was evaluated by training and testing the dataset by increasing the number of training and testing images. The dataset includes 5000 images of elephants. The trained model is designed for identifying the elephants. The conclusions drawn from work prove that the achievement percentage is 92% accuracy.