Published Paper Details:

Automatic target detection holds a pivotal purpose in military operations, involving the recognition of military assets from captured imagery. The core idea in the realm of automatic target detection in warfare is to recognize military assets within the acquired images. To achieve this, efficient utilization of Convolutional Neural Network (CNN) architectures is employed for object recognition in the given images. Due to legal constraints and security considerations associated with military data usage, we have accessed diverse datasets obtained from platforms such as Kaggle, ImageNet, GitHub, and Roboflow. To enhance the automatic target detection process, the integration of the YOLO (You Only Look Once) algorithm is employed. YOLO, a real-time object detection algorithm, is utilized efficiently to processes images, allowing for the rapid identification and localization of military objects within the captured scenes. This integration of YOLO algorithm enhances the speed and accuracy of military object recognition, contributing to the overall effectiveness of automatic target detection in war operations. Training a deep learning model involves feeding it data and adjusting its parameters so that it can make accurate predictions. Train mode in ultralytics YOLOv8 is engineered for effective and efficient training of object detection models, fully utilizing modern hardware capabilities.