Real-time single-view video event recognition in controlled environments

2011 ◽  
Author(s):  
J. C. SanMiguel ◽  
M. Escudero-Vinolo ◽  
J. M. Martinez ◽  
J. Bescos
Keyword(s):  
Real Time ◽  
Event Recognition ◽  
Single View ◽  
Video Event ◽  
Controlled Environments

Improved Skeleton Tracking by Duplex Kinects: A Practical Approach for Real-Time Applications

2013 ◽  
Vol 13 (4) ◽  
Author(s):  
Kwok-Yun Yeung ◽  
Tsz-Ho Kwok ◽  
Charlie C. L. Wang
Keyword(s):  
Real Time ◽  
Technical Difficulty ◽  
Human Motion ◽  
Depth Information ◽  
Length Variation ◽  
Single View ◽  
Motion Extraction ◽  
Hard Constraints ◽  
Real Time Applications ◽  
Frame Motion

Recent development of per-frame motion extraction method can generate the skeleton of human motion in real-time with the help of RGB-D cameras such as Kinect. This leads to an economic device to provide human motion as input for real-time applications. As generated by a single-view image plus depth information, the extracted skeleton usually has problems of unwanted vibration, bone-length variation, self-occlusion, etc. This paper presents an approach to overcome these problems by synthesizing the skeletons generated by duplex Kinects, which capture the human motion in different views. The major technical difficulty of this synthesis comes from the inconsistency of two skeletons. Our algorithm is formulated under the constrained optimization framework by using the bone-lengths as hard constraints and the tradeoff between inconsistent joint positions as soft constraints. Schemes are developed to detect and re-position the problematic joints generated by per-frame method from duplex Kinects. As a result, we develop an easy, cheap and fast approach that can improve the skeleton of human motion at an average speed of 5 ms per frame.

Real-time vehicle distance estimation using single view geometry

2020 ◽  
Author(s):  
Ahmed Ali ◽  
Ali Hassan ◽  
Afsheen Rafaqat Ali ◽  
Hussam Ullah Khan ◽  
Wajahat Kazmi ◽  
...  
Keyword(s):  
Real Time ◽  
Distance Estimation ◽  
Single View

A Fusion Approach Based ColorSiFT and Dense Trajectory Features for Video Event Recognition

2016 ◽  
Vol 14 (3) ◽  
pp. 81
Author(s):  
Nguyen Thanh Dieu ◽  
Tran Anh Tuan ◽  
Pham The Bao ◽  
Bui Nogc Nam ◽  
Jin Young Kim
Keyword(s):  
Event Recognition ◽  
Video Event ◽  
Dense Trajectory ◽  
Trajectory Features ◽  
Fusion Approach
Sign in / Sign up

Export Citation Format

Share Document