A CME Automatic Detection Method Based on Adaptive Background Learning Technology

Qiang, Zhenping; Bai, Xianyong; Lin, Hong

doi:10.1155/2019/6582104

Cited by 3 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To that end, it is necessary to design a processing pipeline and corresponding methods for selecting services/ modules [41]. It is also necessary to evaluate its impact on other motion detection methods [42], which will be used later. To do this, you can use Wavelet analysis [43], machine learning [44], time series analysis [45], or the forecasting method [46] to calculate qualitative indicators.…”

Section: Discussion Of Results Of Investigating the Accuracy Of Ident...mentioning

confidence: 99%

Improving the accuracy of identifying objects in digital frames of one series through the procedure of preliminary identification of measurements

Khlamov,

Savanevych,

Vlasenko

et al. 2023

EEJET

View full text Add to dashboard Cite

The object of this study is images of various objects of the Solar System on a series of digital frames. The variety and quality of shooting conditions make it difficult to identify a frame with the corresponding part of the sky. This fact significantly reduces the quality indicators of detection and estimation of the position of objects of the Solar System using already known computational methods and international astronomical astrometric and photometric catalogs. To solve this problem, a procedure for preliminary identification of measurements of digital frames of one series was devised. This procedure is based on the determination of the shift parameters between the dimensions of a frame and the forms of a catalog or another frame. Also, taking into account the possibility of forming false measurements has made it possible to increase the accuracy of identification and resistance to various kinds of destabilizing factors. Based on this, the final estimation of the shift parameters between frames was performed. Due to these features, the use of the devised preliminary identification procedure makes it possible to improve identification with reference astronomical objects and reduce the number of false detections. The study showed that when identifying frames, the fitting gives the best accuracy of binding to the starry sky. Also, the standard deviation of frame identification errors in this case is 7–10 times less than without using the devised procedure. The procedure developed for preliminary identification of measurements of digital frames of one series was tested in practice within the framework of the CoLiTec project. It has been incorporated into the Lemur software for automated detection of new and tracking of known objects. Owing to the use of the Lemur software and the proposed procedure implemented in it, more than 700,000 measurements of various astronomical objects under study were successfully identified

show abstract

Section: Discussion Of Results Of Investigating the Accuracy Of Ident...mentioning

confidence: 99%

Improving the accuracy of identifying objects in digital frames of one series through the procedure of preliminary identification of measurements

Khlamov,

Savanevych,

Vlasenko

et al. 2023

EEJET

View full text Add to dashboard Cite

show abstract

“…By employing the CORonal SEgmentation Technique (Goussies et al 2010) for STEREO/COR2 observations, a dualviewpoint CME catalog was established (Vourlidas et al 2017). Qiang et al (2019) presented an adaptive background learning method, where CMEs are moving foreground objects in the background. Zhang et al (2017) employed a machinelearning approach known as the extreme learning machine to identify suspicious CME regions based on the brightness and texture features within the images.…”

Section: Introductionmentioning

confidence: 99%

CAMEL. II. A 3D Coronal Mass Ejection Catalog Based on Coronal Mass Ejection Automatic Detection with Deep Learning

Shan 单,

Zhang 张,

Lu 卢

et al. 2024

ApJS

View full text Add to dashboard Cite

Coronal mass ejections (CMEs) are major drivers of geomagnetic storms, which may cause severe space weather effects. Automating the detection, tracking, and three-dimensional (3D) reconstruction of CMEs is important for operational predictions of CME arrivals. The COR1 coronagraphs on board the Solar Terrestrial Relations Observatory spacecraft have facilitated extensive polarization observations, which are very suitable for the establishment of a 3D CME system. We have developed such a 3D system comprising four modules: classification, segmentation, tracking, and 3D reconstructions. We generalize our previously pretrained classification model to classify COR1 coronagraph images. Subsequently, as there are no publicly available CME segmentation data sets, we manually annotate the structural regions of CMEs using Large Angle and Spectrometric Coronagraph C2 observations. Leveraging transformer-based models, we achieve state-of-the-art results in CME segmentation. Furthermore, we improve the tracking algorithm to solve the difficult separation task of multiple CMEs. In the final module, tracking results, combined with the polarization ratio technique, are used to develop the first single-view 3D CME catalog without requiring manual mask annotation. Our method provides higher precision in automatic 2D CME catalog and more reliable physical parameters of CMEs, including 3D propagation direction and speed. The aforementioned 3D CME system can be applied to any coronagraph data with the capability of polarization measurements.

show abstract

“…The Coronal Image Processing (CORIMP) algorithm separates quiescent and dynamic coronal structures observed in coronagraph images using deconvolution and detects CMEs structure using a multi-scale edge detection method (Morgan, Byrne, and Habbal, 2012;Byrne et al, 2012) taking in to account CME kinematics and morphology changes. In a recent work Zhenping et al (2019) developed an algorithm based on adaptive background learning to detect CMEs in LASCO/C2 images considering CMEs to be dynamic foreground features in running difference images.…”

Section: Introductionmentioning

confidence: 99%

Automated Detection of Accelerating Solar Eruptions Using Parabolic Hough Transform

et al. 2021

View full text Add to dashboard Cite

show abstract

A CME Automatic Detection Method Based on Adaptive Background Learning Technology

Cited by 3 publications

References 21 publications

Improving the accuracy of identifying objects in digital frames of one series through the procedure of preliminary identification of measurements

Improving the accuracy of identifying objects in digital frames of one series through the procedure of preliminary identification of measurements

CAMEL. II. A 3D Coronal Mass Ejection Catalog Based on Coronal Mass Ejection Automatic Detection with Deep Learning

Automated Detection of Accelerating Solar Eruptions Using Parabolic Hough Transform

Contact Info

Product

Resources

About