An efficient semi-automatic labeling method for remote sensing image target detection dataset construction

By introducing a pre-trained YOLOv8 model and HBM and SFS algorithms, the problems of high manpower requirements and low efficiency in the annotation process of remote sensing image target detection datasets are solved, realizing efficient and low-cost dataset production, which is suitable for high-quality annotation of large datasets.

CN118411723BActive Publication Date: 2026-07-21BEIHANG UNIV +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIHANG UNIV
Filing Date
2024-04-15
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

The existing remote sensing image target detection dataset annotation process suffers from problems such as high manpower requirements, long annotation time, difficulty in guaranteeing quality, and difficulty in efficiently processing the annotation of a large number of small targets.

Method used

A pre-trained YOLOv8 model is introduced for fully automatic annotation. Harmonic Background Modelling (HBM) and Seed-filling Foreground Segmentation (SFS) algorithms are used to supplement missed targets and delete erroneous annotations. The model is optimized through multiple rounds of iterative training to reduce manual intervention.

Benefits of technology

It significantly improves the efficiency of dataset annotation, reduces production costs and time, outputs high-quality large datasets, is suitable for current large model training, and frees up the workload of manual annotation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118411723B_ABST
    Figure CN118411723B_ABST
Patent Text Reader

Abstract

The application discloses a kind of high-efficiency semi-automatic labeling methods for remote sensing image target detection dataset construction.The specific steps are as follows: 1, computer data acquisition and pretreatment;2, complete the pre-training of YOLOv8 model;3, complete the pre-labeling of part of image using YOLOv8 model;4, artificial inspection and semi-automatic fine labeling of labeling;5, complete the retraining of YOLOv8 model;6, complete the dataset output after multiple iterations.The application uses the efficiency and excellent generalization of YOLO model to assist human operators to complete the dataset labeling task, and proposes efficient operation harmonic background suppression algorithm to further reduce the workload of artificial fine labeling according to the specific characteristics of target detection problem, to provide a solution for the high-quality labeling of massive data.
Need to check novelty before this filing date? Find Prior Art