kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Localized trajectories for 2D and 3D action recognition
Show others and affiliations
2019 (English)In: Sensors, E-ISSN 1424-8220, Vol. 19, no 16, article id 3503Article in journal (Refereed) Published
Abstract [en]

The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides an advanced discriminative representation of actions. Moreover, we generalize Localized Trajectories to 3D by using the depth modality. One of the main advantages of 3D Localized Trajectories is that they describe radial displacements that are perpendicular to the image plane. Extensive experiments and analysis were carried out on five different datasets.

Place, publisher, year, edition, pages
MDPI AG , 2019. Vol. 19, no 16, article id 3503
Keywords [en]
Action recognition, Dense Trajectories, Local Bag-of-Words, Spatiotemporal features
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:kth:diva-286976DOI: 10.3390/s19163503ISI: 000484407200060PubMedID: 31405153Scopus ID: 2-s2.0-85071281414OAI: oai:DiVA.org:kth-286976DiVA, id: diva2:1506109
Note

QC 20201216

Available from: 2020-12-02 Created: 2020-12-02 Last updated: 2023-08-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Ottersten, Björn

Search in DiVA

By author/editor
Ottersten, Björn
In the same journal
Sensors
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 30 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf