计算机工程 ›› 2007, Vol. 33 ›› Issue (21): 194-196.doi: 10.3969/j.issn.1000-3428.2007.21.069

• 人工智能及识别技术 • 上一篇    下一篇

红外双色目标识别技术

彭春燕,李赣华,吴琼玉,蔡宣平   

  1. (国防科学技术大学电子科学与工程学院智能感知系统联合研究中心,长沙 410073)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-11-05 发布日期:2007-11-05

Infrared Bicolor Target Recognition

PENG Chun-yan, LI Gan-hua, WU Qiong-yu, CAI Xuan-ping   

  1. (JCISS School of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-11-05 Published:2007-11-05

摘要: 介绍了一种红外双色目标识别算法。该算法将通过二维傅立叶小波变换对图像提取的特征作为特征向量,这组特征向量具有旋转、平移和尺度不变性。利用Dempster-Shafer(D-S)证据理论进行图像融合,并使用神经网络分类器进行分类。实验结果表明,该算法提高了对近似物体的识别能力,能对飞机、舰船等目标进行有效的识别。

关键词: 红外双色, 目标识别, 傅立叶小波变换, 神经网络

Abstract: This paper proposes an algorithm of infrared bicolor target recognition, in which 2D Fourier-wavelet transform is applied to extract the features of image, and the Fourier-wavelet description for the object recognition is regarded as vector characteristics, characterized with invariancy to translations, scaling and rotation. It improves the rate of target recognition by using D-S theory and netural network classifier. Experimental results show this algorithm can identify the aircraft and the warship objects effectively.

Key words: infrared bicolor, target recognition, Fourier-wavelet transform, netural network

中图分类号: