Achieving real-time object detection and tracking under extreme conditions

被引：54

作者：

Porikli, Fatih ^{[1
]}

机构：

[1] Merl Technol Lab, Cambridge, MA USA

来源：

JOURNAL OF REAL-TIME IMAGE PROCESSING | 2006年 / 1卷 / 01期

关键词：

Object Detection; Background Model; Tracking Method; Erratic Motion; Graphic Processor Unit;

D O I：

10.1007/s11554-006-0011-z

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this survey, we present a brief analysis of single camera object detection and tracking methods. We also give a comparison of their computational complexities. These methods are designed to accurately perform under difficult conditions such as erratic motion, drastic illumination change, and noise contamination.

引用

页码：33 / 40

页数：8

共 21 条

[1]

[Anonymous], TIME VARYING IMAGE P

[2]

[Anonymous], P WORKSH IM AN MULT

[3]

AVIDAN S, 2005, P IEEE C COMP VIS PA

[4]

Bouaynaya N, 2005, P IEEE INT C AC SPEE

[5]

Boykov Y, 2000, PROC CVPR IEEE, P697, DOI 10.1109/CVPR.2000.854942

[6]

Comaniciu D, 2000, PROC CVPR IEEE, P142, DOI 10.1109/CVPR.2000.854761

[7]

Elgammal A., 2000, LECT NOTES COMPUT SC, V1843, P751, DOI DOI 10.1007/3-540-45053-X_48

[8] CONDENSATION - Conditional density propagation for visual tracking [J].

Isard, M ;

Blake, A .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 29 (01) :5-28

[9]

Javed K., 2002, IEEE WORKSH MOT VID

[10]

McCurry P, 2001, 2001 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, P346, DOI 10.1109/ICIP.2001.958122

← 1 2 3 →