Background subtraction using spatio-temporal continuities

Varadarajan, Srenivas; Karam, Lina J.; Florêncio, Dinei

doi:10.1109/euvip.2010.5699142

Cited by 6 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(a) (b) (c) (d) Figure 5: (a) Recovered background using [1] with hysteresis thresholding as described in [2]; (b) Recovered background using algorithm in [5] in first iteration without user intervention; (c) Consensus image obtained using proposed algorithm, the holes formed after foreground extraction are shown in black; (d) Recovered background using proposed algorithm. results using methods of [1] and using the algorithm of [1] along with hysteresis thresholding as explained in [2], respectively. The employed hysteresis thresholding [2] improves the performance of the method of [1].…”

Section: Resultsmentioning

confidence: 97%

“…The holes are then filled in using parts from the other image that reduce the boundary cost. In [2] the authors suggest the use of hysteresis thresholding. It allows slight differences in the pixel values but is still not robust to illumination changes.…”

Section: Related Workmentioning

confidence: 98%

“…The pixel-based algorithms compare the corresponding pixel locations to model the background or the foreground objects. The algorithms in [1] and [2] are pixel based algorithms. In [1], the author assumes perfectly registered images and compares the pixel values at the corresponding location across the images.…”

Section: Related Workmentioning

confidence: 99%

“…For a given grid position U, among all the candidate patches for that position, the patch that belongs to the highest ranked image is selected to fill the background. This can be performed successively for each pair of patches (P,Q) at corresponding locations in two different images, as follows: (2) After selecting the best patch for each grid position U from the candidate patches, a consensus background image is formed, but holes corresponding to removed foreground objects are still present in that image and need to be filled in order to recover the complete background.…”

Section: Foreground Removalmentioning

confidence: 99%

“…A similar cost function as in [1] is used to handle ghosting that might arise due to the motion of the foreground objects. The algorithm proposed in [2] is used for the recovery of background in videos and hence assumes statio-temporal continuities. While spatio-temporal continuity constraints can be exploited for video sequences, these do not hold for static views of a scene that are taken at different times.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Background recovery from multiple images

Shrotre

Karam

2013

2013 IEEE Digital Signal Processing and Signal Processing Education Meeting (DSP/SPE)

Self Cite

View full text Add to dashboard Cite

In this paper we propose an algorithm to extract the background by removing unwanted objects from multiple images of a scene with varying illumination conditions captured by a stationary camera. The variations in illumination from scene to scene are due to the possible presence of different illumination sources and different foreground objects causing different shadows and reflections in each scene. While this causes the background to be non-stationary when considering pixel intensities, the algorithm exploits the fact that the background is static while the foreground is non-stationary in a given feature space. The extracted foreground regions are treated as holes and are filled from one of the available images where the background at the corresponding position is un-occluded. The background pixels for filling the holes are selected based on a cost function that attempts to maximize the naturalness and perceived quality of the reconstructed background.

show abstract