Object Detection With Component-Graphs in Multi-Band Images: Application to Source Detection in Astronomical Images

Thanh Xuan Nguyen, Giovanni Chierchia, Oleksandra Razim, Reynier F. Peletier, Laurent Najman, Hugues Talbot, Benjamin PerretIEEE Access 2021 · DOI · OpenReview

Abstract

In the context of mathematical morphology, component-graphs are complex but powerful structures for multi-band image modeling, processing, and analysis. In this work, we propose a novel multi-band object detection method relying on the component-graphs and statistical hypothesis tests. Our analysis shows that component-graphs are better at capturing image structures compared to the classical component-trees, with significantly higher detection capacity. Besides, we introduce two filtering algorithms to identify duplicated and partial nodes in the component-graphs. The proposed method, applied to the detection of sources on astronomical images, demonstrates a significant improvement in detecting faint objects on both multi-band simulated and real astronomical images compared to the state of the art.
BibTeX
@article{nguyen2021object,
  author = {Thanh Xuan Nguyen and Giovanni Chierchia and Oleksandra Razim and Reynier F. Peletier and Laurent Najman and Hugues Talbot and Benjamin Perret},
  title = {{Object Detection With Component-Graphs in Multi-Band Images: Application to Source Detection in Astronomical Images}},
  journal = {IEEE Access},
  year = {2021},
  doi = {10.1109/access.2021.3128519},
}

Loading related content...

Figure