2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Alexandros Andre Chaaraoui ◽  
Francisco Flórez-Revuelta

This paper presents a novel silhouette-based feature for vision-based human action recognition, which relies on the contour of the silhouette and a radial scheme. Its low-dimensionality and ease of extraction result in an outstanding proficiency for real-time scenarios. This feature is used in a learning algorithm that by means of model fusion of multiple camera streams builds a bag of key poses, which serves as a dictionary of known poses and allows converting the training sequences into sequences of key poses. These are used in order to perform action recognition by means of a sequence matching algorithm. Experimentation on three different datasets returns high and stable recognition rates. To the best of our knowledge, this paper presents the highest results so far on the MuHAVi-MAS dataset. Real-time suitability is given, since the method easily performs above video frequency. Therefore, the related requirements that applications as ambient-assisted living services impose are successfully fulfilled.


1999 ◽  
Vol 35 (10) ◽  
pp. 773 ◽  
Author(s):  
S. Celma ◽  
J. Sabadell ◽  
C. Aldea ◽  
P.A. Martínez

2014 ◽  
Vol 644-650 ◽  
pp. 930-933 ◽  
Author(s):  
Yan Li Luo ◽  
Han Lin Wan ◽  
Li Xia Xue ◽  
Qing Bin Gao

This paper proposes an adaptive moving vehicle detection algorithm based on hybrid background subtraction and frame difference. The background image of continuous video frequency is reconstructed by calculating the maximun probability grayscale using grey histogram; Moving regions is gained by frame defference, the initial target image is obtained by background difference method,moving regions image and initial target image AND,XOR and OR operations to get the vehicle moving target images. Experimental results show that the algorithm can response timely to the actual scene changes and improve the quality of moving vehicle detection.


1959 ◽  
Vol 9 ◽  
pp. 390-397 ◽  
Author(s):  
W. C. Erickson ◽  
H. L. Helfer ◽  
H. E. Tatel

Approximately 1000 observations of neutral hydrogen have been obtained with the 54-channel H-line receiver and the Würzburg antenna of the Carnegie Institution of Washington. H-line profiles have been observed at 10-degree intervals along the ±20-, ±30-, and ± 40-degree parallels of galactic latitude; at 20-degree intervals along the ± 50- and ±60-degree parallels; at 40-degree intervals along the ±70- and ±80-degree parallels and at the poles. Approximately two dozen observations have been taken at points near the galactic plane in order to correlate these observations with the Leiden survey [1]. The beamwidth of the Würzburg antenna was about 2 degrees. The observations were taken in two series, one series during the summer of 1957, and the other series during 1958 January. The video frequency bandwidth of the receiver is 12 kc/s. The profiles consist of averages of from two to six scans with integration times from 4.8 to 7.5 minutes.


1986 ◽  
Vol 21 (2) ◽  
pp. 318-323 ◽  
Author(s):  
M. Hotta ◽  
K. Maio ◽  
N. Yokozawa ◽  
T. Watanabe ◽  
S. Ueda
Keyword(s):  

2011 ◽  
Vol 55-57 ◽  
pp. 2163-2168
Author(s):  
Li Wei Chen ◽  
Yong Li Gao

Along with the multimedia technological development and the large-scale database widespread application, the content video retrieval technology obtains the rapid development, at the same time, the algorithms were also proposed. This article has carried on the induction summary to these new theory technologies based on the content video retrieval demonstration system. This article first introduced based on the content video retrieval essential technology including regards the lens the boundary examination and the division, the essential frame selection the characteristic withdraws, the similar match and the video frequency gathers the kind and so on. Simultaneously provided video frequency retrieval essential technology some algorithms,and carried on the summary regarding the recent years based on the content.


Sign in / Sign up

Export Citation Format

Share Document