Detection of Small Anomalies on Moving Background

Axel Davy, Agnès Desolneux, Jean-Michel Morel

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.
BibTeX
@inproceedings{davy2019detection,
  author = {Axel Davy and Agnès Desolneux and Jean-Michel Morel},
  title = {{Detection of Small Anomalies on Moving Background}},
  booktitle = {ICIP},
  year = {2019},
  doi = {10.1109/icip.2019.8803176},
}

Loading related content...

Figure