Abstract
We consider the problem of detecting small targets in videos where the textured background is also possibly moving. The proposed method is based on a two steps statistical framework. In a first step, the optical flow is computed using a pyramidal scheme incorporating statistical tests for a result with reliability guarantees. In the second step, the detection of targets is changed into a problem of anomaly detection in noise, and statistical testing ensures a control of the number of false detections.
| Original language | English |
|---|---|
| Title of host publication | 2019 IEEE International Conference on Image Processing, ICIP 2019, Proceedings |
| Publisher | IEEE |
| Pages | 2015-2019 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781538662496 |
| ISBN (Print) | 9781538662502 |
| DOIs | |
| Publication status | Published - 2019 |
| Externally published | Yes |
Publication series
| Name | Proceedings - International Conference on Image Processing, ICIP |
|---|---|
| Volume | 2019-September |
| ISSN (Print) | 1522-4880 |
Bibliographical note
Publisher Copyright:© 2019 IEEE.
Funding
Work supported by IDEX Paris-Saclay IDI 2016, ANR-11-IDEX-0003-02, ONR grant N00014-17-1-2552, CNES MISS project, DGA Astrid ANR-17-ASTR-0013-01, DGA ANR-16-DEFA-0004-01.
Keywords
- Anomaly Detection
- Optical Flow
Fingerprint
Dive into the research topics of 'Detection of Small Anomalies on Moving Background'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver