Foreground object segmentation for moving camera sequences based on foreground-background probabilistic models and prior probability maps

Jaime Gallego 1 Pascal Bertolino 1
1 GIPSA-AGPIG - AGPIG
GIPSA-DIS - Département Images et Signal
Abstract : This paper deals with foreground object segmentation in the context of moving camera sequences. The method that we propose com-putes a foreground object segmentation in a MAP-MRF framework between foreground and background classes. We use region-based models to model the foreground object and the background region that surrounds the object. Moreover, the global background of the sequence is also included in the classification process by using pixel-wise color GMM. We compute the foreground segregation for each one of the frames by using a Bayesian classification and a graph-cut regularization between the classes, where the prior probability maps for both, foreground and background, are included in the for-mulation, thus using the cumulative knowledge of the object from the segmentation obtained in the previous frames. The results pre-sented in the paper show how the false positive and false negative detections are reduced, meanwhile the robustness of the system is improved thanks to the use of the prior probability maps in the clas-sification process.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01080559
Contributor : Pascal Bertolino <>
Submitted on : Wednesday, November 5, 2014 - 3:34:39 PM
Last modification on : Friday, July 27, 2018 - 1:50:01 PM
Long-term archiving on : Friday, February 6, 2015 - 10:40:12 AM

File

ICIP2014_gipsa-5.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01080559, version 1

Citation

Jaime Gallego, Pascal Bertolino. Foreground object segmentation for moving camera sequences based on foreground-background probabilistic models and prior probability maps. 21st IEEE International Conference on Image Processing (ICIP 2014), IEEE, Oct 2014, Paris, France. ⟨hal-01080559⟩

Share

Metrics

Record views

460

Files downloads

844