Automatic image stabilizing system by full-digital signal processing

Uomori, Kenya; Morimura, A.; Ishii, Hirofumi; Sakaguchi, Taro; Kitamura, Yuri

doi:10.1109/30.103167

Cited by 91 publications

(11 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…TABLE I. THE RMSES BASED ON DIFFERENT SUB-IMAGES TABLE II The proposed method is also compared with some classical DIS techniques: one dimension curve correlation method [2], RPM method [5] and BPM method [8]. The comparison of these approaches is given in Table 2.…”

Section: Resultsmentioning

confidence: 99%

“…In this method, two one dimension characteristic curves are generated to estimate the global motion vectors in horizontal and vertical directions respectively. Representative point matching (RPM) [5][6], edge pattern matching (EPM) [7], and bit-plane matching (BPM) [8] [9] are other representative methods for global motion estimation. DIS algorithms for In-Car applications were studied in [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Central Sub-image Based Global Motion Estimation Method for In-Car Video Stabilization

Zhang

Xie

Tang

2010

2010 Third International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

This paper presents a novel global motion estimation method based on the phase correlation of central sub-image. In this study, we consider the case that the In-Car videos are captured from the cameras placed in front of a car. The backgrounds of these In-Car videos usually vary with the moving car, which result in the inaccuracy of classical image stabilization method. As a result, a central sub-image based image stabilization method is presented in this paper. The simulation results show that the proposed method is efficient in improving the accuracy of detecting global motion vectors of In-Car videos.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Central Sub-image Based Global Motion Estimation Method for In-Car Video Stabilization

Zhang

Xie

Tang

2010

2010 Third International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…IPA is a robust algorithm which has been early used in video stabilization [2,3]. Integral projections are widely known as data primarily in the context of tomographic reconstruction problems [18].…”

Section: Ipa For Initial Translation Estimationmentioning

confidence: 99%

“…GME techniques differ as far as the parametric model of camera motion is concerned and in the way the model parameters are estimated. The following motion models have been used in the past: 2-parameter model corresponding to pan [2], [3], 3-parameter model corresponding to pan and zoom [4], 4-parameter linear model corresponding to pan and zoom [5], 4-parameter similarity model corresponding to pan, zoom and rotation, 6-parameter affine model [6,7,[9][10][11], 8-parameter perspective model [12][13][14][15][16]. There are two main categories of method for estimating global motion: block-based twostage GME algorithms [4][5][6], and pixel-based gradient descent (GD) GME algorithms [1,7,[10][11][12][13]16,17].…”

Section: Introductionmentioning

confidence: 99%

Fast Global Motion Estimation

Liu

Wang

Liu

et al. 2009

2009 2nd IEEE International Conference on Broadband Network &Amp; Multimedia Technology

View full text Add to dashboard Cite

Global motion estimation (GME) plays an important role in many video application systems such as video coding system MPEG-4. However, its computational complexity is very high. Fast algorithms are needed. In this paper, we propose an improvement to the GME algorithm. We achieve this by introduce two techniques. Firstly, integral projection algorithm (IPA) is used to get first translation estimation and reduce block matching algorithm (BMA) search range. Secondly, coarsely block sampling technology directly reduces the computation complexity. GME composite performance experiments prove that our GME method only degrades -0.13dB in PSNR compared with the MPEG-4 verification model (VM), while it gets a 5.93ms per frame speed and is 73.3 times faster than the VM. Global motion compensation (GMC) coding experiments also show no loss of GME accuracy and compression efficiency compared to the MPEG-4 VM GME method.

show abstract

“…Various algorithms have been developed to estimate GMV. These include representative point matching, and edge pattern matching [4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Spatial-temporal noise reduction filter for image devices

Yoo

Jeon

Hwang³

2008

2008 International Conference on Control, Automation and Systems

View full text Add to dashboard Cite

Digital image sequences are prone to high noise levels in low light conditions, due to the increased gains. The presence of noise degrades visual quality and decreases the performance of subsequent processing tasks, such as object tracking, and video compression. We propose a denoising technique for camera systems. Our proposed structure is composed of an edge preserving spatial filter, digital image stabilization and motion adaptive temporal filter. Using spatial and temporal motion data, our proposed motion detector is shown to be efficient in reducing artifacts, such as ghost-tail or blurring caused by recursive temporal filtering methods.

show abstract

Automatic image stabilizing system by full-digital signal processing

Cited by 91 publications

References 1 publication

A Central Sub-image Based Global Motion Estimation Method for In-Car Video Stabilization

A Central Sub-image Based Global Motion Estimation Method for In-Car Video Stabilization

Fast Global Motion Estimation

Spatial-temporal noise reduction filter for image devices

Contact Info

Product

Resources

About