HOG and color based adaboost pedestrian detection
| Autor: | Qing Liu, Yongyu Qu |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Boosting (machine learning)
business.industry Computer science Pedestrian detection Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Object detection Support vector machine Statistical classification Artificial intelligence AdaBoost business Classifier (UML) |
| Zdroj: | ICNC |
| DOI: | 10.1109/icnc.2011.6022084 |
| Popis: | Pedestrian detection is one of the most important research areas in intelligent video surveillance. How to detect the pedestrian fast and accurately is the main target. This research is based on the feature extraction method proposed in paper[2]. aiming at its defect in speed, we introduce the boosted cascade method to train the classifier, realize the Gentle Adaboost using linear SVM. We only need 3 hours to finish the training procedure, this method not only improves the detection accuracy, it also boosts the detection speed greatly. Our test on INRIA shows the effectiveness of the method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|