Human Action Recognition Based on Foreground Trajectory and Motion Difference Descriptors
Aimed at the problems of high redundancy of trajectory and susceptibility to background interference in traditional dense trajectory behavior recognition methods, a human action recognition method based on foreground trajectory and motion difference descriptors is proposed. First, the motion magnitu...
Main Authors: | Suge Dong, Daidi Hu, Ruijun Li, Mingtao Ge |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-05-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/9/10/2126 |
Similar Items
-
Students’ foregrounds: Hope, despair, uncertainty
by: Ole Skovsmose
Published: (2012-08-01) -
Action Classification for Partially Occluded Silhouettes by Means of Shape and Action Descriptors
by: Katarzyna Gościewska, et al.
Published: (2021-09-01) -
Parsing 3D motion trajectory for gesture recognition
by: Yang, Jianyu, et al.
Published: (2017) -
Robust Pan/Tilt Compensation for Foreground–Background Segmentation
by: Gianni Allebosch, et al.
Published: (2019-06-01) -
Human Action Recognition Using Adaptive Local Motion Descriptor in Spark
by: Md Azher Uddin, et al.
Published: (2017-01-01)