Farm Watch: AI-Enhanced Animal Detection for Farm Protection

Crop protection against wild animal intrusion has become a pressing challenge with significant social and economic implications, particularly in agricultural-dependent nations like India. In response, we present an innovative AI-driven surveillance system designed to detect and determine potential threats posed by animals to farm environments. Leveraging advanced computer vision techniques and machine learning algorithms including Support Vector Machines, K-Means clustering, Random Forest, Decision Trees, and Logistic Regression, the system accurately identifies and classifies animals in farm images. By analyzing a diverse dataset comprising various animal species, the model generalizes effectively. Key features such as accuracy, precision, recall, F1-score, and confusion matrices are employed to assess model performance comprehensively. The results showcase high accuracy across multiple algorithms. The proposed system offers a promising solution to protect crops, minimizing losses, and fostering harmonious coexistence between farming and wildlife. The results demonstrate good accuracy for a variety of algorithms: 92.75% for Logistic Regression, 86.47% for Decision Trees, 95.65% for Random Forests, and 94.20% for Support Vector Machines. This highlights how reliable the system is in classifying animals, providing a viable way to safeguard crops, reduce losses, and promote peaceful cohabitation between agriculture and wildlife.