Abstract
The paper presents a method for video anonymization and replacing real human silhouettes with virtual 3D figures rendered on the screen. Video stream is processed to detect and to track objects, whereas anonymization stage employs fast blurring method. Substitute 3D figures are animated accordingly to behavior of detected persons. Their location, movement speed, direction, and person height are taken into account during the animation and rendering phases. This approach requires a calibrated camera, and utilizes results of visual object tracking. In the paper a procedure for transforming objects visual features and bounding boxes into a script for animated figures is presented. This approach is validated subjectively, by assessing a correspondence between real image and the augmented one. Conclusions and future work perspectives are provided.
Citations
-
4
CrossRef
-
0
Web of Science
-
3
Scopus
Author (1)
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- materiały konferencyjne indeksowane w Web of Science
- Title of issue:
- 7th International Conference on Multimedia Communications, Services and Security (MCSS) strony 229 - 241
- Language:
- English
- Publication year:
- 2014
- Bibliographic description:
- Szczuko P..: Augmented Reality for Privacy-Sensitive Visual Monitoring, W: 7th International Conference on Multimedia Communications, Services and Security (MCSS), 2014, Springer,.
- DOI:
- Digital Object Identifier (open in new tab) 10.1007/978-3-319-07569-3_19
- Verified by:
- Gdańsk University of Technology
seen 114 times
Recommended for you
Modelling and computer animation of geodetic field work
- B. Wieczorek,
- A. Sobieraj-Żłobińska,
- K. Pająk