Patch-based Background Initialization
A. Colombari, A. Fusiello, and V. Murino
Department of Computer Science
University of Verona, Verona - Italy
Overview
In this paper we propose a patch-based technique for robust background
initialization (PBI) that exploits both spatial and temporal
consistency of the static background. The proposed technique is able
to cope with heavy clutter, i.e, foreground objects that stand still
for a considerable portion of time. It can process sequences
acquired with either a stationary camera or a moving camera,
provided that one can compensate for camera motion with respect to
the background, as in the case of mosaicing. First the sequence is
subdivided in patches that are clustered along the time-line in
order to narrow down the number of background candidates. Then, a
tessellation is grown incrementally by selecting at each step the
best continuation of the current background. The method rests on
sound principles in all its stages, and only few, intelligible
parameters are needed.
PBI algorithm
- In the case of moving camera, compute the projective transformations
between frames and compensate for the camera motion.
- Estimate the image noise as the (robust) sample variance of
frames difference.
- Subdivide the spatial domain into overlapping windows
(footprints).
- On each footprint, cluster image patches along the timeline using
single linkage agglomerative clustering, using SSD as the distance and
a cutoff based on the Chi-square test.
- Compute cluster representative by averaging.
- Select the clusters of maximal length, insert their
representatives in the background B.
- Select a patch in B, select a neighbouring footprint which is not
represented in B.
- For each cluster representative in the selected footprint
evaluate the degree of overlap with B (using SSD) and select
candidate patches for insertion in B.
- The candidate patches enter a round robin tournament, where the
comparison between two of them is done according to cost of the cut
defined by their binarized difference. The higher cost wins. The
winner of the tournament in inserted in B.
- Repeat from step 7 until the background image is complete.
Results
Two images case
| Starting images |
Median background |
PBI result |
Extracted object |
Background growing |
 |
 |
 |
 |
 |
 |
 |
Stationary camera case
| Original sequence |
Median background |
PBI result |
Moving objects |
Background growing |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
Moving camera case
| Original sequence |
Compensated sequence |
Median background |
PBI result |
Moving objects |
Background growing |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
Papers
- A. Colombari,
A. Fusiello, and V. Murino.
Background initialization in cluttered sequences.
In 5th Workshop on Perceptual Organization in Computer Vision,
CVPR 2006 Workshops, pages 197–202, New York, NY, 17 - 22 June 2006. IEEE
Computer Society.
(PDF)
(doi:10.1109/CVPRW.2006.40)
- Andrea
Colombari, Andrea Fusiello, and Vittorio Murino.
Video objects segmentation by robust background modeling.
In International Conference on Image Analysis and Processing (ICIAP
2007), pages 155–164, Modena, Italy, 10-14 September 2007. IEEE
Computer Society.
(PDF)
(doi:10.1109/ICIAP.2007.4362773)
