DetectionOfSFO

 

Research  

 

Detection of stacionary foreground objects using multiple nonparametric background-foreground models on a Finite State Machine

Description


This site contains some supplementary material associated to the detection strategy proposed in [*].

The work [*] proposes an efficient and high-quality strategy to detect stationary foreground objects, which is able to detect not only completely static objects but also partially static ones. Three parallel nonparametric detectors with different absorption rates are used to detect currently moving foreground objects, \mbox{short-term} stationary foreground objects, and long-term stationary foreground objects. The results of the detectors are fed into a novel Finite State Machine that classifies the pixels among background, moving foreground objects, stationary foreground objects, occluded stationary foreground objects, and uncovered background. Results show that the proposed detection strategy is not only able to achieve high quality in several challenging situations but it also improves upon previous strategies.

For any question about the article [*] or about the described test data, please contact Carlos Cuevas at This email address is being protected from spambots. You need JavaScript enabled to view it..

 

Citation


 

[*] C. Cuevas, R. Martínez, D. Berjón, and N. García, "Detection of stationary foreground objects using multiple nonparametric background-foreground models on a Finite State Machine", IEEE Transactions on Image Processing, vol. 26, no. 3, pp. 1127-1142, 2017 (doi: 10.1109/TIP.2016.2642779).

 

Results


 

PETS2006 database:

The original sequences can be downloaded from here.

The ground-truth can be downloaded from here.

Our results can be downloaded from here.

The results obtained with other strategies (without postprocessing stages at region level) can be downloaded from:

LASIESTA database:

The original sequences and the ground-truth can be downloaded from here.

Our results can be downloaded from here.

The results obtained with other strategies (without postprocessing stages at region level) can be downloaded from:

ChangeDetection database:

The original sequences and the ground-truth can be downloaded from here.

Our results can be downloaded from here.

The results obtained with strategy FTSG [4] can be downloaded from here.

i-LIDS database:

The original sequences and the metadata can be downloaded from here.

Our results can be downloaded from here.

 

References


 
1. Y.-L. Tian, M. Lu, and A. Hampapur, “Robust and efficient foreground analysis for real-time video surveillance,” IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 1182–1187, 2005.

2. F. Porikli, “Detection of temporarily static regions by processing video at different frame rates,” IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 236–241, 2007.

3. R. H. Evangelio and T. Sikora, “Static object detection based on a dual background model and a finite-state machine,” EURASIP Journal on Image and Video Processing, vol. 2011, no. 1, p. 858502, 2010.

4. R. Wang, F. Bunyak, G. Seetharaman, and K. Palaniappan, “Static and moving object detection using flux tensor with split gaussian models,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops. IEEE, 2014, pp. 420–424.