H.264/SVC SCENE MOTION ANALYSIS

被引：1

作者：

Kaes, Christian ^{[1
]}

Nicolas, Henri ^{[1
]}

机构：

[1] Univ Bordeaux 1, LaBRI, F-33405 Talence, France

来源：

2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS | 2009年

关键词：

H.264/SVC; compressed domain; scene analysis; trajectory estimation;

D O I：

10.1109/ICASSP.2009.4959744

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

We present a simple and lightweight approach to scene analysis in the H.264/SVC domain. The method is entirely based on the motion vectors found in the compressed stream. Motion segmentation and object detection is performed after the estimation of the camera motion. Important object proper-ties are calculated, which are used for object matching and trajectory estimation. The relative distance to the camera is estimated, resulting in a pseudo 3-D representation of the object trajectories.

引用

页码：957 / 960

页数：4

共 10 条

[1] Aggarwal A, 2006, LECT NOTES COMPUT SC, V3852, P121
[2] Motion segmentation and pose recognition with motion history gradients
Bradski, GR
Davis, JW
[J]. MACHINE VISION AND APPLICATIONS, 2002, 13 (03) : 174 - 184
[3] CHEN H, 2001, PCM 01, P1066
[4] DEBRUYNE S, 2007, PCM-PREM PERS COMPUT, P177
[5] Object tracking for retrieval applications in MPEG-2
Favalli, L
Mecocci, A
Moschetti, F
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2000, 10 (03) : 427 - 432
[6] HESSELER W, 2006, EURASIP J APPL SIG P, V2, P1
[7] Lie WN, 2002, PROCEEDINGS OF THE 2002 IEEE WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING, P237
[8] MANERBA F, 2008, EURASIP J ADV SIG PR, P1
[9] PARK SM, 2003, 4 PAC RIM C MULT SIN, V2, P748
[10] RADHAKRISHNA ASV, 2002, IEEE INT C MULT EXP

← 1 →