YOLO-SAT: A Data-based and Model-based Enhanced YOLOv12 Model for Desert Waste Detection and Classification

TL;DR

YOLO-SAT is a novel lightweight real-time detection framework that combines data augmentation and model optimization to improve desert waste detection accuracy and efficiency on resource-limited aerial drones.

Contribution

This work introduces YOLO-SAT, integrating Self-Adversarial Training and specialized data augmentation into a pruned YOLOv12 model for enhanced desert waste detection.

Findings

Significant improvements in precision, recall, and mAP on DroneTrashNet dataset.

Low latency and compact model suitable for aerial drone deployment.

Outperforms existing lightweight YOLO variants in accuracy and efficiency.

Abstract

The global waste crisis is escalating, with solid waste generation expected to increase tremendously in the coming years. Traditional waste collection methods, particularly in remote or harsh environments like deserts, are labor-intensive, inefficient, and often hazardous. Recent advances in computer vision and deep learning have opened the door to automated waste detection systems, yet most research focuses on urban environments and recyclable materials, overlooking organic and hazardous waste and underexplored terrains such as deserts. In this work, we propose YOLO-SAT, an enhanced real-time object detection framework based on a pruned, lightweight version of YOLOv12 integrated with Self-Adversarial Training (SAT) and specialized data augmentation strategies. Using the DroneTrashNet dataset, we demonstrate significant improvements in precision, recall, and mean average precision (mAP), while achieving low latency and compact model size suitable for deployment on resource-constrained aerial drones. Benchmarking YOLO-SAT against state-of-the-art lightweight YOLO variants further highlights its optimal balance of accuracy and efficiency. Our results validate the effectiveness of combining data-centric and model-centric enhancements for robust, real-time waste detection in desert environments.