Instance Segmentation of Auroral Images for Automatic Computation of Arc Width

Niu, Chuang; Yang, Qiuju; Ren, Shenghan; Hu, Hongping; Han, Desheng; Hu, Zejun; Liang, Jinling

doi:10.1109/lgrs.2019.2901803

Cited by 7 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This difference makes it challenging for the Mask R-CNN to accurately segment each auroral arc, particularly when dealing with multiple arcs. To overcome these challenges, we refer to the approach proposed by Niu et al (2019), where the image is rotated to approximately align the auroral arcs with the horizontal direction. By doing so, the instance segmentation network can effectively detect and segment each auroral arc using the horizontal bounding box.…”

Section: Instance Segmentation Of Auroral Arcsmentioning

confidence: 99%

See 1 more Smart Citation

Statistical Characteristics of Multi‐Scale Auroral Arc Width Based on Machine Learning

Yang,

Xie,

et al. 2024

JGR Space Physics

Self Cite

View full text Add to dashboard Cite

Arc width is important for understanding the generation mechanism of auroral arcs. However, the continuity or discreteness of the distribution of small and meso‐large scale auroral arc widths has not been determined in previous studies. This study employs machine learning techniques to investigate the distribution of arc widths across multiple scales using multi‐field‐of‐view (multi‐FOV) auroral observations. Based on the 180°, 47°, and 19° auroral observations at the Antarctic Zhongshan Station from February to October 2012, the statistical results demonstrate that the auroral arc width spectrum is continuously distributed across small, meso, and large scales, suggesting that the mechanisms responsible for their generation are capable of producing arcs at all scales. Furthermore, the arc width distribution at each FOV can be well fitted with a log‐normal function. We also find that the main widths observed at different FOVs depend on the spatial resolution of the instruments. Our work provides new observational evidence for the generation mechanism of auroral arcs.

show abstract

Section: Instance Segmentation Of Auroral Arcsmentioning

confidence: 99%

“…By doing so, the instance segmentation network can effectively detect and segment each auroral arc using the horizontal bounding box. The entire inference process can be summarized into two stages, as described by Niu et al (2019).…”

Section: Instance Segmentation Of Auroral Arcsmentioning

confidence: 99%

Statistical Characteristics of Multi‐Scale Auroral Arc Width Based on Machine Learning

Yang,

Xie,

et al. 2024

JGR Space Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this section, we propose a dedicated network architecture to collaboratively detect lung nodules from more than one projections and output their locations in both 2D and 3D. Over past years, many object detection networks (12)(13)(14) were proposed for various applications (15)(16)(17).…”

Section: Collaborative Detection Networkmentioning

confidence: 99%

X-ray Dissectography Improves Lung Nodule Detection

Niu¹,

Dasegowda²,

Yan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Although radiographs are the most frequently used worldwide due to their cost-effectiveness and widespread accessibility, the structural superposition along the x-ray paths often renders suspicious or concerning lung nodules difficult to detect. In this study, we apply "X-ray dissectography" to dissect lungs digitally from a few radiographic projections, suppress the interference of irrelevant structures and improve lung nodule detectability. For this purpose, a collaborative detection network is designed to localize lung nodules in 2D dissected projections and 3D physical space. Our experimental results show that our approach can significantly improve the average precision by 20+% in comparison with the common baseline that detects lung nodules from original projections using a popular detection network. Potentially, this approach could help re-design the current X-ray imaging protocols and workflows and 1

show abstract

“…By now, no predecessor has ever combined object detection, semantic segmentation and linear fitting in antenna parameter measurement. For the first time, this paper validated a fully automatic antenna parameter measurement method based on instance segmentation [29][30][31], least squares, frame sequence analysis and UAV [32][33][34][35], which enjoys remarkable preciseness, rapid recognition and outstanding performance.…”

Section: Related Workmentioning

confidence: 99%

Mobile Communication Base Station Antenna Measurement Using Unmanned Aerial Vehicle

Zhai

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Traditional base station antenna measurement methods conducted with professional worker climbing towers tend to raise safety and inefficiency concerns in practical application. Designed to address the above problems, this paper proposes an intelligent and fully automatic antenna measurement unmanned aerial vehicle (UAV) system for mobile communication base station. Firstly, an antenna database, containing 19,715 images, named UAV-Antenna is constructed by image capturing with the help of UAVs flying around various base stations. Secondly, Mask R-CNN is adopted to train an optimal instance segmentation model on UAV-Antenna. Then, pixel coordinates and threshold are utilized for measuring antenna quantity and separate all antenna data for further measuring. Finally, a least squares method is employed for measuring antenna parameters. Experimental results show that the proposed method can not only satisfy the industry application standards, but also guarantee safety of labors and efficiency of performance.

show abstract

Instance Segmentation of Auroral Images for Automatic Computation of Arc Width

Cited by 7 publications

References 21 publications

Statistical Characteristics of Multi‐Scale Auroral Arc Width Based on Machine Learning

Statistical Characteristics of Multi‐Scale Auroral Arc Width Based on Machine Learning

X-ray Dissectography Improves Lung Nodule Detection

Mobile Communication Base Station Antenna Measurement Using Unmanned Aerial Vehicle

Contact Info

Product

Resources

About