Enhancing Wildlife Protection: Poacher Detection Using Machine Learning Models

Wildlife conservation is a pressing global concern, with illegal poaching posing a severe threat to many endangered species. In recent years, advanced technologies like machine learning and digital signal processing have shown significant potential in supporting conservation efforts by detecting and preventing illegal poaching. This work explores the integration of these technologies into wildlife conservation strategies, focusing on their role in identifying and combating poachers. Two datasets are utilized: ‘Poacher Detection 3 Classes” and “Illegal Poacher Detection”. Several machine learning models including Support Vector Machines (SVM), Random Forest (RF), Decision Trees (DT), and Convolutional Neural Networks (CNN) are applied to detect illegal activities in these datasets. For the first dataset, the SVM model achieved the best accuracy of ${9 3 \%}$, while the CNN model performed best on the second dataset, achieving accuracy of $75 \%$. In the final phase, both datasets were combined, and augmented images were introduced to increase data diversity. On the combined dataset, the Random Forest model achieved the highest accuracy of ${8 3 \%}$. These results demonstrate the effectiveness of machine learning in improving wildlife conservation efforts.