The Preprocessing for Infrared Sea-Surface Target Image

2012 ◽  
Vol 433-440 ◽  
pp. 4512-4515
Author(s):  
Shu Li Lou ◽  
Jian Cun Ren ◽  
Yan Li Han ◽  
Xiao Hu Yuan ◽  
Xiao Dong Zhou
Keyword(s):  
Feature Extraction ◽  
Target Recognition ◽  
Infrared Image ◽  
Automatic Target Recognition ◽  
Experimental Results ◽  
Sea Surface ◽  
Practical Application ◽  
Target Image

The preprocessing for infrared sea-surface target image is very important to automatic target recognition and tracking. The preprocessing can reduce noise and enhance target, and it is the base of feature extraction and target recognition. The scene model of infrared sea-surface target image was established. The characteristics of infrared image are analyzed, and several methods of preprocessing nowadays were analyzed and compared. According to the different characteristic of infrared image, a preprocessing scheme is proposed. The experimental results indicate that in practical application appropriate methods should be chosen for different purpose. In order to get good preprocessing effects, these methods can be assembled into multi- process.

An Automatic Target Recognition Algorithm Based on Support Vector Machine

2014 ◽  
Vol 496-500 ◽  
pp. 1873-1876
Author(s):  
He Zhang ◽  
Jie Li ◽  
Bei Bei Xu
Keyword(s):  
Support Vector Machine ◽  
Feature Extraction ◽  
Support Vector Machine Model ◽  
Target Recognition ◽  
Automatic Target Recognition ◽  
Recognition Algorithm ◽  
Support Vector ◽  
Machine Model ◽  
Fast Recognition ◽  
High False Alarm Rate

To improve the performance of automatic target recognition technology and solve the problems of traditional methods, such as high false alarm rate and poor adaptability to environment changes, a new algorithm based on support vector machine is proposed. We have realized the feature extraction of the target and the parameter optimization of the support vector machine to get the support vector machine model applied to the target recognition of unknown images. Experiment results show that the algorithm has a good recognition effect, a fast recognition speed and certain anti-interference abilities based on sufficient samples training.

Automatic target recognition based on local feature extraction

2013 ◽  
Vol 21 (7) ◽  
pp. 1898-1905 ◽  
Author(s):  
贾平 JIA Ping ◽  
徐宁 XU Ning ◽  
张叶 ZHANG Ye
Keyword(s):  
Feature Extraction ◽  
Target Recognition ◽  
Automatic Target Recognition ◽  
Local Feature ◽  
Local Feature Extraction
Sign in / Sign up

Export Citation Format

Share Document