Published Paper Details:

Object detection plays a vital role in modern computer vision applications by enabling automated understanding of visual scenes. This paper presents an efficient deep learning-based human detection system using a YOLO-based object detection architecture. The proposed model is trained on a large-scale, single-class annotated dataset to ensure robustness against variations in scale, position, and environmental conditions. Data preprocessing and augmentation techniques are employed to improve generalization and reduce overfitting. The model's performance is evaluated using standard metrics including Precision, Recall, mAP@0.5, and mAP@0.5-0.95. Experimental results demonstrate steady loss convergence and consistent improvement in detection accuracy across training epochs, indicating reliable learning behavior. The framework achieves accurate localization of human instances while maintaining computational efficiency, making it suitable for real-time applications such as surveillance, crowd monitoring, and intelligent vision systems. The proposed approach provides a scalable foundation for future extensions to multi-class detection and deployment on edge-based platforms.