Advancing Wild Animal Conservation Through Autonomous Systems Leveraging YOLOV7 With SGD Optimization Technique

Abstract

In the field of conserving wildlife, the utilization of autonomous systems equipped with computer vision holds tremendous promise. This research explores the potential of integrating YOLO v7, a cutting-edge object recognition model, with stochastic gradient descent (SGD) optimization techniques to bolster wild animal conservation efforts. The primary objective is to enhance the precision, accuracy, and scalability of autonomous systems in detecting and monitoring wild animals across diverse habitats. The experimental results showcase substantial advancements, demonstrating the efficacy of the YOLOv7-SGD amalgamation in autonomous systems. The model exhibits superior detection accuracy and robustness in identifying a multitude of wild animal species across diverse landscapes.