pdf

Interest point matching based on improved local invariant features

  • 2013-09-19
  • 807.83KB
  • Points it Requires : 2

This paper proposes a local feature point detection and matching method suitable for target tracking. It makes many improvements based on the Scale Invariant Feature Transform (SIFT) algorithm. Only local maxima are detected in the Gaussian difference scale space to improve the stability of the algorithm. The main direction and descriptor of the point of interest are determined based on the circular neighborhood statistical gradient direction histogram, avoiding the computational cost of image rotation. Finally, the ratio of the nearest neighbor to the next nearest neighbor is used to match the 96-dimensional descriptor. The proposed method not only effectively improves the matching accuracy, but also greatly improves the computing speed, which is suitable for occasions with high real-time requirements.

unfold

You Might Like

Uploader
jujuyaya222
 

Recommended ContentMore

Popular Components

Just Take a LookMore

EEWorld
subscription
account

EEWorld
service
account

Automotive
development
circle

About Us Customer Service Contact Information Datasheet Sitemap LatestNews


Room 1530, 15th Floor, Building B, No.18 Zhongguancun Street, Haidian District, Beijing, Postal Code: 100190 China Telephone: 008610 8235 0740

Copyright © 2005-2024 EEWORLD.com.cn, Inc. All rights reserved 京ICP证060456号 京ICP备10001474号-1 电信业务审批[2006]字第258号函 京公网安备 11010802033920号
×