Large-scale Remote Sensing Image Target Recognition and Automatic Annotation

TL;DR

This paper introduces LRSAA, a scalable remote sensing image recognition and annotation method that combines ensemble learning with segmentation and optimized training to improve accuracy and efficiency.

Contribution

It presents a novel integration of YOLOv11 and MobileNetV3-SSD with segmentation and EIOU metric for enhanced remote sensing image analysis.

Findings

Achieves a good balance between accuracy and speed.

Reduces computational resource requirements.

Provides publicly available source code.

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.