Keypoint-Based Object Tracking Using Modified Median Flow

被引：0

作者：

Dattathreya ^{[1
]}

Han, Sangpil ^{[2
]}

Kim, Min-jae ^{[2
]}

Maik, Vivek ^{[1
]}

Paik, Joonki ^{[2
]}

机构：

[1] Oxford Coll Engn, Dept Elect & Commun, Bangalore 68, Karnataka, India

[2] Chung Ang Univ, Grad Sch Adv Imaging Sci & Film, Image Proc & Intelligent Syst Lab, Seoul, South Korea

来源：

2016 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-ASIA (ICCE-ASIA) | 2016年

关键词：

Object tracking; median flow tracker; error estimation; optical flow;

D O I：

暂无

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 proposed robust object tracking using error filter. Proposed method consists of four steps: i) execution of tracking algorithm based on key point, ii) estimation of key point using error filter, iii) selection of key point as filtering outliers using Random Sample Consensus (RANSAC), and determination of object movement. The proposed method can track when object is occluded, abruptly change of appearance. As a result, the proposed methods can be applied to various application such as advanced driver assistance system, surveillance system.

引用

页数：2

共 4 条

[1]

[Anonymous], 2001, INTEL CORPORATION

[2]

Kalal Zdenek, 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, P1417, DOI 10.1109/ICCVW.2009.5457446

[3] P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints [J].

Kalal, Zdenek ;

Matas, Jiri ;

Mikolajczyk, Krystian .

2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, :49-56

[4]

SHI JB, 1994, 1994 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, P593, DOI 10.1109/CVPR.1994.323794

← 1 →