Object Recognition and Tracking based on
Object Feature Extracting

Yong-Hwan Lee¹⁺, Hyochang Ahn², Han-Jin Cho¹, and June-Hwan Lee¹

¹Far East University, Eumseong Chungbuk, 27601, Republic of Korea

²Dankook University, Yongin-si, Gyeonggi-do, 448-701, Republic of Korea
hwany1458@empal.com, hanjincho@hotmail.com, rainbow@kdu.ac.kr, youcu92@dankook.ac.kr

Abstract

Object recognition and tracking is one of the most important task in the field of computer vision and surveillance system. Among many proposed, object tracking using a feature matching method is popular and accurate, however, it has a room to improve on high computational complexity and weak robustness in various environments. This paper proposes a robust object recognition and tracking method, which uses an advanced feature matching for the use of real time environment. The proposed method enables to recognize an object using invariant features, with reducing the dimension of feature descriptor, compared to the existing algorithm. The experimental results show that the proposed recognition and tracking method outperforms the conventional tracking approaches in terms of tracking accuracy and computing time.

Keywords: Object Recognition, Object Tracking, Feature-Matching Approach, Feature Extraction

+: Corresponding author: Yong-Hwan Lee
Department of Smart Mobile, Far East University, Gamgok Eumseong Chungbuk, 27601, Republic of Korea

Tel: +82-10-3072-1458

Journal of Internet Services and Information Security (JISIS), 5(3): 48-57, August 2015 [pdf]