Action Recognition Using Multi-class Boosting
Date Issued
2006
Date
2006
Author(s)
Chen, Ying-Chung
DOI
en-US
Abstract
In this thesis we use volumetric feature combined with spatial and temporal alignment to deal with action recognition problem. We use the adaptive background mixture model to extract the human body out of the image sequence, normalize and align them in the center of the frame according to the centroid of figure. After that we use Dynamic Time Warping to achieve the temporal alignment, by using of a simplified version of Shape Context. Then we apply the volumetric feature inspired by 2D rectangle feature in object detection on static images. To solve the multi-class learning problem, we apply an multi-class approach of Adaboost by using error-correcting code, which is more effective than one-against-all approach. In the experiment, we demonstrate the using of spatial and temporal alignment can avoid the time-scale and space-scale issue thus improve the accuracy rate.
Subjects
AdaBoost
錯誤稱正碼
動作
識別
體積特徵
Error-correct code
action
recognition
Volumetric feature
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-95-R93944003-1.pdf
Size
23.31 KB
Format
Adobe PDF
Checksum
(MD5):da00539b29f516eb9a0e2d9e77198e57