This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
SPA: Annotating Small Object with a Single Point in Remote Sensing Images
by
Wenjie Zhao
Wenjie Zhao 1,2,
Zhenyu Fang
Zhenyu Fang 1,2,*,
Jun Cao
Jun Cao 3 and
Zhangfeng Ju
Zhangfeng Ju 4
1
School of Computer Software, Northwestern Polytechnical University, Xi’an 710060, China
2
Yangtze River Delta Research Institute of NPU, Taicang 210044, China
3
Nanjing RuiYue Technology Ltd., Nanjing 210044, China
4
North Automatic Control Technology Research Institute, Taiyuan 140100, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2024, 16(14), 2515; https://doi.org/10.3390/rs16142515 (registering DOI)
Submission received: 19 May 2024
/
Revised: 27 June 2024
/
Accepted: 28 June 2024
/
Published: 9 July 2024
Abstract
Detecting oriented small objects is a critical task in remote sensing, but the development of high-performance deep learning-based detectors is hindered by the need for large-scale and well-annotated datasets. The high cost of creating these datasets, due to the dense and numerous distribution of small objects, significantly limits the application and development of such detectors. To address this problem, we propose a single-point-based annotation approach (SPA) based on the graph cut method. In this framework, user annotations act as the origin of positive sample points, and a similarity matrix, computed from feature maps extracted by deep learning networks, facilitates an intuitive and efficient annotation process for building graph elements. Utilizing the Maximum Flow algorithm, SPA derives positive sample regions from these points and generates oriented bounding boxes (OBBOXs). Experimental results demonstrate the effectiveness of SPA, with at least a 50% improvement in annotation efficiency. Furthermore, the intersection-over-union (IoU) metric of our OBBOX is 3.6% higher than existing methods such as the “Segment Anything Model”. When applied in training, the model annotated with SPA shows a 4.7% higher mean average precision (mAP) compared to models using traditional annotation methods. These results confirm the technical advantages and practical impact of SPA in advancing small object detection in remote sensing.
Share and Cite
MDPI and ACS Style
Zhao, W.; Fang, Z.; Cao, J.; Ju, Z.
SPA: Annotating Small Object with a Single Point in Remote Sensing Images. Remote Sens. 2024, 16, 2515.
https://doi.org/10.3390/rs16142515
AMA Style
Zhao W, Fang Z, Cao J, Ju Z.
SPA: Annotating Small Object with a Single Point in Remote Sensing Images. Remote Sensing. 2024; 16(14):2515.
https://doi.org/10.3390/rs16142515
Chicago/Turabian Style
Zhao, Wenjie, Zhenyu Fang, Jun Cao, and Zhangfeng Ju.
2024. "SPA: Annotating Small Object with a Single Point in Remote Sensing Images" Remote Sensing 16, no. 14: 2515.
https://doi.org/10.3390/rs16142515
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.