{"title":"面向点提示对象检测的语义分割模型","authors":"Xuran Lu, Zhisong Bie","doi":"10.1049/ell2.70254","DOIUrl":null,"url":null,"abstract":"<p>Remote sensing object detection traditionally relies on bounding boxes supervision, which demands significant human effort for precise annotation. Recently, the segment anything model (SAM) has shown the ability to segment objects using simple point prompts without fine-tuning. However, due to the inherent uncertainty of single-point prompts, the mask proposals generated by SAM often introduce ambiguity. In this study, we propose a novel approach that aims to select the most suitable mask from the proposals based on point annotations and object categories. By utilizing our approach, the circumscribed rectangle of the estimated pseudo mask can be used to supervise the training of a rotated object detection network. Experiments conducted on the DOTA dataset demonstrate the effectiveness of the proposed method.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70254","citationCount":"0","resultStr":"{\"title\":\"Semantic Segmentation Everything Model for Point-Prompted Oriented Object Detection\",\"authors\":\"Xuran Lu, Zhisong Bie\",\"doi\":\"10.1049/ell2.70254\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Remote sensing object detection traditionally relies on bounding boxes supervision, which demands significant human effort for precise annotation. Recently, the segment anything model (SAM) has shown the ability to segment objects using simple point prompts without fine-tuning. However, due to the inherent uncertainty of single-point prompts, the mask proposals generated by SAM often introduce ambiguity. In this study, we propose a novel approach that aims to select the most suitable mask from the proposals based on point annotations and object categories. By utilizing our approach, the circumscribed rectangle of the estimated pseudo mask can be used to supervise the training of a rotated object detection network. Experiments conducted on the DOTA dataset demonstrate the effectiveness of the proposed method.</p>\",\"PeriodicalId\":11556,\"journal\":{\"name\":\"Electronics Letters\",\"volume\":\"61 1\",\"pages\":\"\"},\"PeriodicalIF\":0.8000,\"publicationDate\":\"2025-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70254\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electronics Letters\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/ell2.70254\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronics Letters","FirstCategoryId":"5","ListUrlMain":"https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/ell2.70254","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Semantic Segmentation Everything Model for Point-Prompted Oriented Object Detection
Remote sensing object detection traditionally relies on bounding boxes supervision, which demands significant human effort for precise annotation. Recently, the segment anything model (SAM) has shown the ability to segment objects using simple point prompts without fine-tuning. However, due to the inherent uncertainty of single-point prompts, the mask proposals generated by SAM often introduce ambiguity. In this study, we propose a novel approach that aims to select the most suitable mask from the proposals based on point annotations and object categories. By utilizing our approach, the circumscribed rectangle of the estimated pseudo mask can be used to supervise the training of a rotated object detection network. Experiments conducted on the DOTA dataset demonstrate the effectiveness of the proposed method.
期刊介绍:
Electronics Letters is an internationally renowned peer-reviewed rapid-communication journal that publishes short original research papers every two weeks. Its broad and interdisciplinary scope covers the latest developments in all electronic engineering related fields including communication, biomedical, optical and device technologies. Electronics Letters also provides further insight into some of the latest developments through special features and interviews.
Scope
As a journal at the forefront of its field, Electronics Letters publishes papers covering all themes of electronic and electrical engineering. The major themes of the journal are listed below.
Antennas and Propagation
Biomedical and Bioinspired Technologies, Signal Processing and Applications
Control Engineering
Electromagnetism: Theory, Materials and Devices
Electronic Circuits and Systems
Image, Video and Vision Processing and Applications
Information, Computing and Communications
Instrumentation and Measurement
Microwave Technology
Optical Communications
Photonics and Opto-Electronics
Power Electronics, Energy and Sustainability
Radar, Sonar and Navigation
Semiconductor Technology
Signal Processing
MIMO