Capture and Representation of Human Walking in Live Video Sequences

被引：32

作者：

Cheng, Jia-Ching ^{[1
]}

Moura, Jose M. F. ^{[1
]}

机构：

[1] Carnegie Mellon Univ, Dept Elect & Comp Engn, Pittsburgh, PA 15213 USA

来源：

IEEE TRANSACTIONS ON MULTIMEDIA | 1999年 / 1卷 / 02期

关键词：

Capture; cyclic motion; human walkers in real video; motion; recognition; stick model; video contents;

D O I：

10.1109/6046.766736

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Extracting human representations from video has vast applications. In this paper, we present a knowledge-based framework to capture metarepresentations for real-life video with human walkers. The system models the human body as an articulated object and the human walking as a cyclic activity with highly correlated temporal patterns. We extract for each of the body parts its motion, shape, and texture. Once available, this structural information can be used to manipulate or synthesize the original video sequence, or animate the walker with a different motion in a new synthesized video.

引用

页码：144 / 156

页数：13

共 18 条

[1]

Asada H., 1986, ROBOT ANAL CONTROL

[2]

Barrow Harry G., 1977, P IMAGE UNDERSTANDIN

[3] A COMPUTATIONAL APPROACH TO EDGE-DETECTION [J].

CANNY, J .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1986, 8 (06) :679-698

[4] Automatic recognition of human walking in monocular image sequences [J].

Cheng, JC ;

Moura, JMF .

JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 1998, 20 (1-2) :107-120

[5]

CHENG JC, 1997, P IEEE 1 WORKSH MULT, P268

[6]

CHENG JC, 1997, P IEEE INT C IM PROC, V1, P137

[7]

CHENG JC, 1998, THESIS CARNEGIE MELL

[8] 3-D model-based tracking of humans in action: A multi-view approach [J].

Gavrila, DM ;

Davis, LS .

1996 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1996, :73-80

[9]

HOGG D, 1983, IMAGE VISION COMPUT, V1, P5, DOI DOI 10.1016/0262-8856(83)90003-3

[10]

JASINSCHI RS, 1998, Patent No. 5854856

← 1 2 →