سیویلیکا را در شبکه های اجتماعی دنبال نمایید.

Hierarchical Least Square Twin Support VectorMachines Based Framework for Human ActionRecognition

Publish Year: 1390
Type: Conference paper
Language: English
View: 1,472

This Paper With 5 Page And PDF Format Ready To Download

Export:

Link to this Paper:

Document National Code:

ICMVIP07_109

Index date: 18 August 2012

Hierarchical Least Square Twin Support VectorMachines Based Framework for Human ActionRecognition abstract

The aim of this paper is presentation of a new humanaction recognition framework. In the proposed framework, localspace-time features extracted by use of Harris detector algorithmand Histogram of Optical Flow (HOF). A new classifier based ontwo non-parallel hyperplanes called Twin Support VectorMachines (TWSVM) is used which is four times faster thanclassical SVM. According to the prior knowledge that two classesof human action recognition (jogging and running) are verysimilar and recognition of these classes are difficult, ahierarchical structure is used for better recognition. We appliedour method to KTH dataset to investigate the performance of theproposed action recognition approach. Our experimental resultshown that our approach improves state-of-the-art results byachieving 98.33%, 96.39% in case of leave-one-out and 10-foldcross validation.

Hierarchical Least Square Twin Support VectorMachines Based Framework for Human ActionRecognition Keywords:

Action Recognition , Twin Support Vector Machines , Histogram of Optical Flow (HOF) , Harris , PCA , KTH dataset ,

Hierarchical Least Square Twin Support VectorMachines Based Framework for Human ActionRecognition authors

Kourosh Mozafari

Department of Electrical and computer EngineeringTarbiat Modares UniversityTehran, Iran

Nasrollah Moghadam Charkari

Department of Electrical and computer EngineeringTarbiat Modares UniversityTehran, Iran

Jalal A. Nasiri

Department of Electrical and computer EngineeringTarbiat Modares UniversityTehran, Iran

Saeed Jalili

Department of Electrical and computer EngineeringTarbiat Modares UniversityTehran, Iran

مراجع و منابع این Paper:

لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :
_ _ _ action recognition; Image _ _ _ _ ...
P. Scovanner, et al., "A 3-dimensional sift descriptor and its ...
_ _ al, "A _ _ _ Conference on, 2007, ...
Conference on, 2009, pp. 128-135. ...
I. Laptev, et al., "Learming realistic human actions from movies, ...
Reviews, IEEE Transactions on, vol. PP, pp. 1-11, 2011. ...
Figure 5. Accuracy rates for various values of penalty factor. ...
Our approach Our approach Our approach Our approach Zhang et ...
(PCA 1000) - (PCA 2000) - (PCA 1000) - (PCA ...
نمایش کامل مراجع