Back to Search
Start Over
SAR: Single-Stage Anchor-Free Rotating Object Detection
- Source :
- IEEE Access, Vol 8, Pp 205902-205912 (2020)
- Publication Year :
- 2020
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2020.
-
Abstract
- As object detection is widely adopted in aerial images, scene texts and other fields, rotating object detection plays an important role and draws attention since it can provide highly accurate orientation and scale information. In this article, we propose a novel and simple baseline to effectively conduct rotating object detection. First, we design a brand-new representation for rotating objects by using a circle cut horizontal rectangle (CCH). The CCH ensures that the regression parameters will not exceed the defined domain and avoids vertex sorting, thus solving some problems in current common representations, including the boundary problem and order problem, and improving the robustness. Second, we design a lightweight head based on the CCH to add the rotating regression to classic benchmark in an almost cost-free manner and propose a single-stage anchor-free rotating (SAR) object detection convolutional neural network. Finally, we demonstrate the details of our method by applying it to data sets with different scenarios. The experiments confirm that our method achieves competitive accuracy and state-of-the-art speed in aerial image and scene text detection.
- Subjects :
- General Computer Science
representation
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
0211 other engineering and technologies
02 engineering and technology
Convolutional neural network
Robustness (computer science)
0202 electrical engineering, electronic engineering, information engineering
General Materials Science
Computer vision
Aerial image
021101 geological & geomatics engineering
Single stage
business.industry
circle cut horizontal
General Engineering
Rotating object detection
Object detection
single-stage
020201 artificial intelligence & image processing
lcsh:Electrical engineering. Electronics. Nuclear engineering
Artificial intelligence
business
lcsh:TK1-9971
anchor-free
Subjects
Details
- ISSN :
- 21693536
- Volume :
- 8
- Database :
- OpenAIRE
- Journal :
- IEEE Access
- Accession number :
- edsair.doi.dedup.....0f07ef7b2aacb9b16d5cadd650ac6bf1