• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference on Independent Component Analyses, Wavelets, and Neural Networks Apr 22-25, 2003 Orlando, Florida, USA >Aerial Target Recognition Using MRA, GVF Snakes and Polygon Approximation
【24h】

Aerial Target Recognition Using MRA, GVF Snakes and Polygon Approximation

机译：使用MRA，GVF蛇和多边形逼近的空中目标识别

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A new algorithm for Aerial Target Recognition is proposed in this paper. Combining MRA, GVF Snakes and polygon approximation, image denoising, contour extraction and features extraction are discussed. In contour extraction, two dimensional Bubble wavelet is used to remove noises and weaken false edges. GVF snakes is used to track and extract accurate body boundary. Polygon approximation is used to extract a polygon with pre-specified vertex number so it can be used to match the target feature template. A seven step algorithm is applied to aerial target images of a helicopter and a F22 aircraft, the contour extraction and polygon approximation results show that targets can be matched and recognized successfully. This paper mainly focuses on contour extraction and polygon approximation in the recognition area.
机译：提出了一种新的空中目标识别算法。结合MRA，GVF Snakes和多边形逼近，讨论了图像去噪，轮廓提取和特征提取。在轮廓提取中，二维Bubble小波用于去除噪声并减弱虚假边缘。 GVF蛇用于跟踪和提取准确的身体边界。多边形逼近用于提取具有预先指定的顶点编号的多边形，以便可以将其与目标要素模板匹配。将七步算法应用于直升机和F22飞机的空中目标图像，轮廓提取和多边形逼近结果表明目标可以成功匹配和识别。本文主要关注识别区域中的轮廓提取和多边形逼近。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号