Back to Search
Start Over
Local descriptors for spatio-temporal recognition
- Source :
- Spatial Coherence for Visual Motion Analysis ISBN: 9783540325338, SCVMA
- Publication Year :
- 2006
- Publisher :
- KTH, Datorseende och robotik, CVAP, 2006.
-
Abstract
- This paper presents and investigates a set of local space-time descriptors for representing and recognizing motion patterns in video. Following the idea of local features in the spatial domain, we use the notion of space-time interest points and represent video data in terms of local space-time events. To describe such events, we define several types of image descriptors over local spatio-temporal neighborhoods and evaluate these descriptors in the context of recognizing human activities. In particular, we compare motion representations in terms of spatio-temporal jets, position dependent histograms, position independent histograms, and principal component analysis computed for either spatio-temporal gradients or optic flow. An experimental evaluation on a video database with human actions shows that high classification performance can be achieved, and that there is a clear advantage of using local position dependent histograms, consistent with previously reported findings regarding spatial recognition. QC 20111003
- Subjects :
- Computer and Information Sciences
Human Movement
business.industry
Computer science
Optical flow
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Image processing
Context (language use)
Data- och informationsvetenskap
Motion (physics)
Representation
Position (vector)
Computer Science::Computer Vision and Pattern Recognition
Motion estimation
Histogram
Principal component analysis
Computer Science::Multimedia
Computer vision
Artificial intelligence
business
Subjects
Details
- Language :
- English
- ISBN :
- 978-3-540-32533-8
- ISBNs :
- 9783540325338
- Database :
- OpenAIRE
- Journal :
- Spatial Coherence for Visual Motion Analysis ISBN: 9783540325338, SCVMA
- Accession number :
- edsair.doi.dedup.....e992a8166037a6174a8f4a26cbae1203