Background segmentation of dynamic scenes based on dual model

Yin, Baocai; Zhang, Jing; Wang, Zengfu

doi:10.1049/iet-cvi.2013.0319

Cited by 16 publications

(7 citation statements)

References 38 publications

(152 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several common factors which affect indoor segmentation efficacy: 1) image noise, 2) camera jitter and movement, 3) automatic camera settings, 4) illumination and shadows, 5) background initialization, 6) color camouflage, and 7) ghost images, sleeping foregrounds, and dynamic backgrounds [10] , [11] , [12] .…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Testing dataset for head segmentation accuracy for the algorithms in the ‘BGSLibrary’ v3.0.0 developed by Andrews Sobral

et al. 2020

View full text Add to dashboard Cite

This dataset consists of video files that were created to test the accuracy of background segmentation algorithms contained in the C ++ wrapper ‘BGSLibrary’ v3.0.0 developed by Andrews Sobral. The comparison is based on segmentation accuracy of the algorithms on a series of indoor color-depth video clips of a single person's head and upper body, each highlighting a common factor that can influence the accuracy of foreground-background segmentation. The algorithms are run on the color image data, while the ‘ground truth’ is semi-automatically extracted from the depth data. The camera chosen for capturing the videos features paired color-depth image sensors, with the color sensor having specifications typical of mobile devices and webcams, which cover most of the use cases for these algorithms. The factors chosen for testing are derived from a literature review accompanying the dataset as being able to influence the efficacy of background segmentation. The assessment criteria for the results were set based on the requirements of common use cases such as gamecasting and mobile communications to allow the readers to make their own judgements on the merits of each algorithm for their own purposes.

show abstract

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Testing dataset for head segmentation accuracy for the algorithms in the ‘BGSLibrary’ v3.0.0 developed by Andrews Sobral

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Some methods create more than one background model, e.g. a dual model in [5] and a multi-model in [3] and [4]. The former has two models; a self-model for the background of its pixel location, a neighbourhood-model for neighbour pixels around itself.…”

Section: Related Workmentioning

confidence: 99%

Pixel-Based Foreground Detection in Repetitive Time-Series Region

Rattanapitak,

Wangsiripitak

2019

MJCS

View full text Add to dashboard Cite

Currently, many state-of-the-art background subtraction techniques cannot deal properly with the area of periodic changing background, while some continue classifying them as foreground at intervals, others simply mask that area as a non-region of interest. To cope with this issue, a novel method of detecting repetitive temporal patterns based on the image sequences was proposed in this paper. The main emphasis of the proposed approach is on classifying those pixels as a background and identifying foreground objects in their relevant areas. As for the foreground detection, a model of time series pattern found in each pixel is individually built first; and then, any changes beyond the allowance of model periodicity are then determined as foreground objects. The proposed method could be used and run in parallel with any state-of-the-art background subtraction technique, allowing more accurate foreground-background segmentation. Experimental results showed that using Y channel, the proposed method of detecting time-series background area could achieve 92.9% of recall rate with less than 1% false positives. The recall of foreground detection in an area of repetitive time-series pattern was about 87%; while F-measure was about 0.73 on average. The false positives of foreground detection were also less than 1%. Accordingly, the proposed time-delay detection technique could significantly help to suppress the foreground error on time series background area, especially during the change from one sub-pattern to another which causes a camera sensor to capture both sub-pattern values in one frame. Performance comparison with state-of-the-art methods showed that our proposed method was able to reduce 80% of the average false alarm and improve F-measure to 28% while the computational efficiency was reduced by only 1%.

show abstract

“…After colour images are captured by the camera and changed to their greyscale forms, a background modelling is built, and according to the principle of consistency of time, a short image sequence is used to generate the initial background model

B {(x, y)}_{0}

as follows:

B {(x, y)}_{0} = (}{, I_{1} ()(, x, y), \dots, I_{1 + ()(, N - 2) \times K} ()(, x, y), I_{1 + ()(, N - 1) \times K} ()(, x, y)),

where N is the number of observed image ALTF in the background model and K is the specified frame interval of taking a sample from the video,

I_{1} ()(, x, y)

is the ALTF sample at a location

false(x, y false)

in the first frame, and

I_{1 + ()(, N - 1) \times K} ()(, x, y)

is the ALTF sample in the

1 + ()(, N - 1) \times K th

frame. To avoid the generation of a ghost, the Pixel‐Based Adaptive Segmentation [32] and dual sample consensus model [33] initialise the background model with the image values at each pixel in the first N frames. However, those methods also lead to ghost in urban traffic scenes due to slow‐moving or temporarily stopped vehicles.…”

Section: Texture‐based Background Modelling Using Sample Consensusmentioning

confidence: 99%

Vehicles detection for illumination changes urban traffic scenes employing adaptive local texture feature background model

Zhang

Zhao

Shi

et al. 2018

IET Intelligent Transport Systems

View full text Add to dashboard Cite

Background segmentation of dynamic scenes based on dual model

Cited by 16 publications

References 38 publications

Testing dataset for head segmentation accuracy for the algorithms in the ‘BGSLibrary’ v3.0.0 developed by Andrews Sobral

Testing dataset for head segmentation accuracy for the algorithms in the ‘BGSLibrary’ v3.0.0 developed by Andrews Sobral

Pixel-Based Foreground Detection in Repetitive Time-Series Region

Vehicles detection for illumination changes urban traffic scenes employing adaptive local texture feature background model

Contact Info

Product

Resources

About