World Library  


Add to Book Shelf
Flag as Inappropriate
Email this Book

Human Action Poselets Estimation Via Color G-surf in Still Images : Volume Xl-5/W6, Issue 1 (18/05/2015)

By Favorskaya, M.

Click here to view

Book Id: WPLBN0004015566
Format Type: PDF Article :
File Size: Pages 8
Reproduction Date: 2015

Title: Human Action Poselets Estimation Via Color G-surf in Still Images : Volume Xl-5/W6, Issue 1 (18/05/2015)  
Author: Favorskaya, M.
Volume: Vol. XL-5/W6, Issue 1
Language: English
Subject: Science, Isprs, International
Collections: Periodicals: Journal and Magazine Collection (Contemporary), Copernicus Publications
Historic
Publication Date:
2015
Publisher: Copernicus Publications, Göttingen, Germany
Member Page: Copernicus Publications

Citation

APA MLA Chicago

Novikov, D., Savitskaya, Y., & Favorskaya, M. (2015). Human Action Poselets Estimation Via Color G-surf in Still Images : Volume Xl-5/W6, Issue 1 (18/05/2015). Retrieved from http://kindle.worldlibrary.net/


Description
Description: Institute of Informatics and Telecommunications, Siberian State Aerospace University, 31 Krasnoyarsky Rabochy av., Krasnoyarsk, 660014 Russian Federation. Human activity is a persistent subject of interest in the last decade. On the one hand, video sequences provide a huge volume of motion information in order to recognize the human active actions. On the other hand, the spatial information about static human poses is valuable for human action recognition. Poselets were introduced as latent variables representing a configuration for mutual locations of body parts and allowing different views of description. In current research, some modifications of Speeded-Up Robust Features (SURF) invariant to affine geometrical transforms and illumination changes were tested. First, a grid of rectangles is imposed on object of interest in a still image. Second, sparse descriptor based on Gauge-SURF (G-SURF) invariant to color/lighting changes is constructed for each rectangle separately. A common Spatial POselet Descriptor (SPOD) aggregates the SPODs of rectangles with following random forest classification in order to receive fast classification results. The proposed approach was tested on samples from PASCAL Visual Object Classes (VOC) Dataset and Challenge 2010 providing accuracy 61-68% for all possible 3D poses locations and 82-86% for front poses locations regarding to nine action categories.

Summary
HUMAN ACTION POSELETS ESTIMATION VIA COLOR G-SURF IN STILL IMAGES

 

Click To View

Additional Books


  • Use of Assisted Photogrammetry for Indoo... (by )
  • Procedures and Methods of Digital Modeli... (by )
  • Sar Image Segmentation Using Morphologic... (by )
  • 2D/3D Semantic Annotation Towards a Set ... (by )
  • Why the Horizon is Important for Airborn... (by )
  • Study on the Standard Architecture for G... (by )
  • The Role of Remote Sensing for Sustainab... (by )
  • A Quality Assessment Method for 3D Road ... (by )
  • Topological 3D Modeling Using Indoor Mob... (by )
  • The Pros and Cons About the Digital Reco... (by )
  • Bringing it All Together: Networking Her... (by )
  • Project Photofly: New 3D Modeling Online... (by )
Scroll Left
Scroll Right

 



Copyright © World Library Foundation. All rights reserved. eBooks from World eBook Library on the Kindle are sponsored by the World Library Foundation,
a 501c(4) Member's Support Non-Profit Organization, and is NOT affiliated with any governmental agency or department.