Global spatiotemporal representations and feature extraction in video sequences
碩士 === 元智大學 === 工業工程與管理學系 === 100 === This research evaluates the global motion representations of video sequences based on optical flow and motion history methods. The two most important motion features in a scene, moving speed and moving direction, are extracted from the spatiotemporal representat...
Main Authors: | Men-Han Lee, 李孟翰 |
---|---|
Other Authors: | Du-MingTsai |
Format: | Others |
Language: | zh-TW |
Online Access: | http://ndltd.ncl.edu.tw/handle/12381059601580158106 |
Similar Items
-
Active Trace: A Sparse Spatiotemporal Representation for Videos
by: Zhi Han, et al.
Published: (2017-01-01) -
Spatiotemporal Representation Learning for Video Anomaly Detection
by: Zhaoyan Li, et al.
Published: (2020-01-01) -
Unsupervised Learning of Spatiotemporal Features by Video Completion
by: Nallabolu, Adithya Reddy
Published: (2017) -
No-reference Video Quality Metric Computation Using Spatial, Temporal, Transform, and Spatiotemporal Features
by: LEE, YI-SHENG, et al.
Published: (2018) -
Badminton Video Analysis based on Spatiotemporal and Stroke Features
by: SAMUEL INDRA GUNAWAN SITUMEANG, et al.
Published: (2017)