Contour detection in Cassini ISS images based on Hierarchical Extreme Learning Machine and Dense Conditional Random Field  

作　　者：Xi-Qi Yang Qing-Feng Zhang Zhan Li 杨悉琪;张庆丰;李展(Department of Computer Science,Jinan University,Guangzhou 510632,China;State Key Lab of CAD&CG,Zhejiang University,Hangzhou 310000,China;Sino-French Joint Laboratory for Astrometry,Dynamics and Space Science,Jinan University,Guangzhou 510632,China)

机构地区：[1]Department of Computer Science,Jinan University,Guangzhou 510632,China [2]State Key Lab of CAD&CG,Zhejiang University,Hangzhou 310000,China [3]Sino-French Joint Laboratory for Astrometry,Dynamics and Space Science,Jinan University,Guangzhou 510632,China

出　　处：《Research in Astronomy and Astrophysics》2020年第1期83-92,共10页天文和天体物理学研究（英文版）

基　　金：partly supported by the National Natural Science Foundation of China(Grant Nos.U1431227 and 11873026);Natural Science Foundation of Guangdong Province,China(Grant No.2016A030313092);the Fundamental Research Funds for the Central Universities(Grant No.21619413)

摘　　要：In Cassini ISS(Imaging Science Subsystem)images,contour detection is often performed on disk-resolved objects to accurately locate their center.Thus,contour detection is a key problem.Traditional edge detection methods,such as Canny and Roberts,often extract the contour with too much interior details and noise.Although the deep convolutional neural network has been applied successfully in many image tasks,such as classification and object detection,it needs more time and computer resources.In this paper,a contour detection algorithm based on H-ELM(Hierarchical Extreme Learning Machine)and Dense CRF(Dense Conditional Random Field)is proposed for Cassini ISS images.The experimental results show that this algorithm’s performance is better than both traditional machine learning methods,such as Support Vector Machine,Extreme Learning Machine and even deep Convolutional Neural Network.The extracted contour is closer to the actual contour.Moreover,it can be trained and tested quickly on the general configuration of PC,and thus can be applied to contour detection for Cassini ISS images.In Cassini ISS(Imaging Science Subsystem) images, contour detection is often performed on disk-resolved objects to accurately locate their center. Thus, contour detection is a key problem. Traditional edge detection methods, such as Canny and Roberts, often extract the contour with too much interior details and noise. Although the deep convolutional neural network has been applied successfully in many image tasks, such as classification and object detection, it needs more time and computer resources. In this paper,a contour detection algorithm based on H-ELM(Hierarchical Extreme Learning Machine) and Dense CRF(Dense Conditional Random Field) is proposed for Cassini ISS images. The experimental results show that this algorithm’s performance is better than both traditional machine learning methods, such as Support Vector Machine, Extreme Learning Machine and even deep Convolutional Neural Network. The extracted contour is closer to the actual contour. Moreover, it can be trained and tested quickly on the general configuration of PC, and thus can be applied to contour detection for Cassini ISS images.

关 键 词：techniques:image processing methods:data analysis ASTROMETRY 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]