.png){kind=icon}
Return
Tracking objects using shape context matching
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2011.11.012.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper we propose a novel tracking method, which provides accurately segmented object boundaries. The first step of the proposed method is to model the object and background using Gaussian mixture model (GMM), and extract a rough contour according to the object edge features. And then the states of the object, including translation. rotation and scale, are estimated using shape context matching. Finally, we take an elastic shape matching method to extract the exact contour. The proposed method is robust enough for tracking object with translation, rotation, scale change and partial occlusion, and it can also be used for real-time tracking applications. Experiments on both synthetic and real world video sequences demonstrate the effectiveness of the proposed method. (C) 2011 Elsevier B.V. All rights reserved.
Keywords:
Object tracking
Shape context
Gaussian mixture model
Shape prior
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
ShareSaveTracking non-rigid objects using probabilistic Hausdorff distance matching.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveShareSaveShareSave
ShareSave
View more