Name
Abstract | ||
|---|---|---|
Object detection with a learned classifier has been applied successfully to difficult tasks such as detecting faces and pedestrians. Systems using this approach usually learn the classifier offline with manually labeled training data. We present a framework that learns the classifier online with automatically labeled data for the specific case of detecting moving objects from video. Motion information is used to automatically label training examples collected directly from the live detection task video. An online learner based on the Winnow algorithm incrementally trains a taskspecific classifier with these examples. Since learning occurs online and without manual help, it can continue in parallel with detection and adapt the classifier over time. The framework is demonstrated on a person detection task for an office corridor scene. In this task, we use background subtraction to automatically label training examples. After the initial manual effort of implementing the labeling method, the framework runs by itself on the scene video stream to gradually train an accurate detector. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/CVPR.2004.1315181 | CVPR (2) |
Keywords | Field | DocType |
live detection task video,training example,training data,online learner,scene video stream,object detection,person detection task,classifier online,taskspecific classifier,difficult task,computer vision,unsupervised learning,background subtraction,image classification | Background subtraction,Computer vision,Object detection,Viola–Jones object detection framework,Object-class detection,Pattern recognition,Computer science,Unsupervised learning,Artificial intelligence,Winnow,Contextual image classification,Classifier (linguistics) | Conference |
ISSN | Citations | PageRank |
1063-6919 | 75 | 3.73 |
References | Authors | |
14 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Vinod Nair | 1 | 1658 | 134.40 |
| James J. Clark | 2 | 402 | 86.34 |