DocumentCode
245387
Title
Biased boosting using weighted template matching for pedestrian detection
Author
Shih-Shinh Huang ; Shih-Han Ku
fYear
2014
fDate
26-28 May 2014
Firstpage
221
Lastpage
222
Abstract
The main objective of this work is to alleviate this problem by imposing the matching results from a classifier based on a set of constructed weighted templates to the boosting framework. The integration of global contour templates and local HOGs is through the adjustment of the hyperplane from the support vector machine. The concept behind is to bias the hyperplane and make it consistent with the template-based classifier at each round of boosting stage.
Keywords
image classification; image matching; integration; object detection; pedestrians; support vector machines; biased boosting framework; boosting stage; global contour template integration; hyperplane adjustment; local HOG integration; pedestrian detection; support vector machine; template-based classifier; weighted template matching result; Boosting; Detectors; Feature extraction; Shape; Support vector machines; Testing; Training;
fLanguage
English
Publisher
ieee
Conference_Titel
Consumer Electronics - Taiwan (ICCE-TW), 2014 IEEE International Conference on
Conference_Location
Taipei
Type
conf
DOI
10.1109/ICCE-TW.2014.6904068
Filename
6904068
Link To Document