LRSAA: Large-scale Remote Sensing Image Target Recognition and Automatic Annotation

TL;DR

LRSAA introduces an ensemble learning approach combining YOLOv11 and MobileNetV3-SSD for efficient, accurate object recognition and automatic annotation in large-scale remote sensing images, optimizing resource use and balancing speed with accuracy.

Contribution

It presents a novel ensemble method integrating multiple detection algorithms with segmentation and optimization techniques for remote sensing image annotation.

Findings

Enhanced detection accuracy and speed.

Reduced computational resource requirements.

Open-source implementation available.

Abstract

This paper presents a method for object recognition and automatic labeling in large-area remote sensing images called LRSAA. The method integrates YOLOv11 and MobileNetV3-SSD object detection algorithms through ensemble learning to enhance model performance. Furthermore, it employs Poisson disk sampling segmentation techniques and the EIOU metric to optimize the training and inference processes of segmented images, followed by the integration of results. This approach not only reduces the demand for computational resources but also achieves a good balance between accuracy and speed. The source code for this project has been made publicly available on https://github.com/anaerovane/LRSAA.