DocumentCode
3046369
Title
Incremental Tree Induction for Detection of the Rescue Target in the Marine Casualty
Author
Ran, Xin ; Zhang, Yongxin
Author_Institution
Merchant Marine Coll., Shanghai Maritime Univ., Shanghai, China
Volume
4
fYear
2009
fDate
19-21 May 2009
Firstpage
432
Lastpage
435
Abstract
In the case that a marine casualty occurs, the detection of the rescue target such as life rafts is surely required to carry out the prompt rescue of human life.To detect the small target in the wide views over the sea, we have proposed a new method including the feature extraction techniques based on the color information and the system learning method based on incremental tree induction. The color information derived from the image data is used to construct the incremental tree which can update online to adapt well to the real time circumstance. The experimental results show that the proposed method is efficient to detect the small target in cluttered natural scene.
Keywords
decision trees; feature extraction; image colour analysis; learning (artificial intelligence); marine accidents; marine safety; cluttered natural scene; color information; decision tree; feature extraction technique; image data; incremental tree induction; machine learning; marine casualty; rescue target detection; system learning method; Costs; Decision trees; Eyes; Humans; Image processing; Intelligent systems; Pattern recognition; Radio access networks; Real time systems; Sea surface; Incremental tree induction; Marine casualty; target detection;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Systems, 2009. GCIS '09. WRI Global Congress on
Conference_Location
Xiamen
Print_ISBN
978-0-7695-3571-5
Type
conf
DOI
10.1109/GCIS.2009.394
Filename
5209265
Link To Document