A Lightweight Detection Method for Poppy Plants in Complex Backgrounds

The detection of poppy plants in complex backgrounds presents significant challenges due to variations in lighting, scale, and environmental clutter. This project introduces a lightweight detection method for identifying poppy plants using YOLOv12, a state-of-the-art deep learning model optimized for real-time object detection. The method is specifically designed to operate efficiently in environments where poppy plants are camouflaged among diverse backgrounds. The model is trained on a dataset consisting of images containing only one class—poppy— and is evaluated based on key metrics such as precision, recall, F1-score, and mean average precision (mAP). With an F1-score of 0.713 and precision of 0.747, the YOLOv12-based detector demonstrates strong performance in accurately identifying poppy plants while minimizing false positives. This lightweight approach ensures rapid deployment on devices with limited computational resources, making it suitable for real-time field applications such as agriculture, forestry, and environmental monitoring. The project emphasizes the integration of deep learning with efficient model architecture to address complex detection tasks in cluttered environments, paving the way for practical solutions in plant monitoring and detection.

Keywords: Poppy Plant Detection, YOLOv12, Deep Learning, Object Detection, Real-Time Detection, Complex Backgrounds, Machine Learning, Precision, Recall, F1-Score, Environmental Monitoring, Lightweight Model.