DocumentCode :
3406087
Title :
Study on the detection method of SUSAN Opertor and K-means clustering clgorithm fusion
Author :
Zhi-Qiang, Kang ; Shi Xiu-hua ; Qi, Li ; Bin, Feng
Author_Institution :
Sch. of Marine Eng., Northwestern Polytech. Univ., Xi´´an, China
fYear :
2010
fDate :
24-28 Oct. 2010
Firstpage :
817
Lastpage :
820
Abstract :
To quickly detect the defection of moving object, base on the experiments and analysis of the advantages and disadvantages of the classical operator, a new detection method of SUSAN Operator and K-means clustering algorithm fusion is presented in this paper. This method integrates the advantages of the high precision of edge detection of the SUSAN Operator and the accurate online detection of K-Means clustering, the surface defect of the moving target can be detected effectively and accurately.
Keywords :
edge detection; image fusion; image motion analysis; object detection; pattern clustering; K-means clustering algorithm; SUSAN opertor; edge detection; image fusion; moving object detection; Clustering algorithms; Computer vision; Image edge detection; Machine learning; Noise; Pixel; SUSAN operator; detection; surface defect; the K-Means clustering;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing (ICSP), 2010 IEEE 10th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-5897-4
Type :
conf
DOI :
10.1109/ICOSP.2010.5655937
Filename :
5655937
Link To Document :
بازگشت