A Disparity-Based Adaptive Multihomography Method for Moving Target Detection Based on Global Motion Compensation

Kim, Soyeon; Yang, Dong Won; Park, Hyun Wook

doi:10.1109/tcsvt.2015.2444711

Cited by 7 publications

(3 citation statements)

References 45 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and is an average of N minimal [18] KDE [34] Wen et al [27] Liao [22] ViBe [38] ICA [28] Kim et al [21] PBAS [11], tensor method [29][30][31][32] Yao and Odobez [20] SOBS [36] Bayes [35] distances between pixel observed value I(x i ) and background observed value B k (x i ) at pixel x i . So, the value of R(x i ) is determined by d¯m in (x i ).…”

Section: Pbas Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Background modelling using discriminative motion representation

Zhong

et al. 2017

IET Computer Vision

View full text Add to dashboard Cite

Robustness is an important factor for background modelling on various scenarios. Current pixel-based adaptive segmentation method cannot effectively tackle diverse objects simultaneously. To address this problem, in this study, a background modelling method using discriminative motion representation is proposed. Instead of simple usage of intensity to construct the background model, the proposed method extracts a new local descriptor which uses a weighted combination of differential excitations for each pixel to enhance the discriminability of pixels. On the basis of this background model, different categories of objects can be quickly identified by a simple but effective classification rule and accurately be represented in background model by a smart selection of updating strategies. Therefore, the authors' background modelling method can generate complete representation for static objects and decrease false detection caused by dynamic background or illumination variations. Extensive experiments have been conducted to demonstrate that the proposed method obtains more advantages of foreground detection than the state-of-the-art methods. In addition, the proposed method provides a computational efficient algorithm for foreground detection tasks.

show abstract

Section: Pbas Methodsmentioning

confidence: 99%

“…It achieves better representation ability for background models under illumination changes. Kim et al [21] employed scale-invariant feature transform feature to detect moving objects based on global motion compensation. However, they cannot obtain satisfactory performances in complex scenarios.…”

Section: Introductionmentioning

confidence: 99%

Background modelling using discriminative motion representation

Zhong

et al. 2017

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Homography estimation is a simple and precise way to obtain appropriate global transformation by overlaying images of the same scene taken from different viewpoints. This technology has been widely researched due to its important applications in the fields of image registration and mosaic [1][2][3], target recognition and tracking [4][5][6][7], 3D reconstruction [8,9], and visual simultaneous localisation and mapping [10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%