SIFT features tracking for video stabilization

被引：132

作者：

Battiato, Sebastiano ^{[1
]}

Gallo, Giovanni ^{[1
]}

Puglisi, Giovanni ^{[1
]}

Scellato, Salvatore ^{[2
]}

机构：

[1] Univ Catania, I-95124 Catania, Italy

[2] Scuola Super Catania, Catania, Italy

来源：

14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS | 2007年

关键词：

D O I：

10.1109/ICIAP.2007.4362878

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper presents a video stabilization algorithm based on the extraction and tracking of Scale Invariant Feature Transform features through video frames. Implementation of SIFT operator is analyzed and adapted to be used in a feature-based motion estimation algorithm. SIFT features are extracted from video frames and then their trajectory is evaluated to estimate interframe motion. A modified version of Iterative Least Squares method is adopted to avoid estimation errors and features are tracked as they appear in near by frames to improve video stability. Intentional camera motion is eventually filtered with Adaptive Motion Vector Integration. Results confirm the effectiveness of the method.

引用

页码：825 / +

页数：2

共 16 条

[1] Digital video stabilization architecture for low cost devices [J].