A Robust Image Alignment Algorithm for Video Stabilization Purposes

Puglisi, Giovanni; Battiato, Sebastiano

doi:10.1109/tcsvt.2011.2162689

Cited by 83 publications

(59 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model is applied well in a situation with no or little forward speed [1,40], but it is unsuitable for high forward speed. High forward speed will result in considerable motion during imaging.…”

Section: Rt Model Analysismentioning

confidence: 99%

“…The proposed method is compared with a standard technique [3], and two state-of-the-art algorithms [1,40]. Algorithms described in [1,3] are reimplemented according to the detail of the documents, and the algorithm proposed in [40] is reimplemented by employing optical flow provided by Opencv. Indoor1 video is utilised to test the performance of the methods when homogeneous regions exist in the scene.…”

Section: Experiments 1 -Real Datamentioning

confidence: 99%

“…Feature-based approaches employ sparse features to estimate the motion parameters of the adjacent frames so that their computation is not heavy, but the features are easily polluted. The global motion is recovered from many motion vectors between adjacent two frames based on some criteria [1,24,25]. Every method recovers global motion from different views.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Video stabilisation based on modelling of motion imaging

Wang

et al. 2016

IET Image Processing

View full text Add to dashboard Cite

This study proposes a novel digital video stabilisation scheme based on modelling of motion imaging (MI). The modelling of MI eliminates the speed motion as a result of a moving car, which is ignored in other models such as rotation + translation model, and estimates movement parameters of the background in video sequences captured from cameras mounted on moving cars. The authors first analyse the MI to understand the principle of the effects of car motion on MI, and select the matching method according to the proposed model. Then, they employ symmetric points to remove the speed motion. Finally, unwanted motion vector is stimulated by employing adaptive step-length filter, and the boundary compensating approach is employed to suppress the image jitter effectively. Their major contribution is the elimination of the effect of carrier's speed in motion estimation. Other contributions include new robust block matching approach and adaptive-step selection for motion filtering. They conduct experiments on real videos and artificial data. Experiments on real videos show that the proposed model can remove the effect of car motion, whereas the experiments on artificial data are conducted for theoretical analysis.

show abstract

Section: Rt Model Analysismentioning

confidence: 99%

Section: Experiments 1 -Real Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Video stabilisation based on modelling of motion imaging

Wang

et al. 2016

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…9 Estimation methods able to cope with outliers have hence to be considered. [10][11][12][13] Specifically, in this work a robust algorithm based on a voting approach has been employed.…”

Section: Voting-based Curve Fittingmentioning

confidence: 99%

Image sensor noise profiling by voting based curve fitting

et al. 2014

View full text Add to dashboard Cite

The output quality of an image filter for reducing noise without damaging the underlying signal, strongly depends on the accuracy of the noise model in characterizing the noise introduced by the acquisition device. In this paper we provide a solution for characterizing signal dependent noise injected at shot time by the image sensor. Different fitting models describing the behavior of noise samples are analyzed, with the aim of finding a model that offers the most accurate coverage of the sensor noise under any of its operating conditions. The noise fitting equation minimizing the residual error is then identified. Moreover, a novel algorithm able to obtain the noise profile of a generic image sensor without the need of a controlled environment is proposed. Starting from a set of heterogeneous CFA images, by using a voting based estimator, the parameters of the noise model are estimated.

show abstract

“…By considering the estimation of camera motion, 2D methods can be further subdivided into two categories [32]: (i) intensity-based approaches [37,38], which directly use the texture of the images as motion vector, and (ii) keypoint-based approaches [39,40], which locate a set of corresponding points in adjacent frames. Since keypoint-based approaches have a lower computational cost, they are most commonly used [22].…”

Section: Introductionmentioning

confidence: 99%

Digital video stabilization based on adaptive camera trajectory smoothing

Souza¹,

Pedrini²

2018

J Image Video Proc.

View full text Add to dashboard Cite

The development of multimedia equipments has allowed a significant growth in the production of videos through professional and amateur cameras, smartphones, and other mobile devices. Examples of applications involving video processing and analysis include surveillance and security, telemedicine, entertainment, teaching, and robotics. Video stabilization refers to the set of techniques required to detect and correct glitches or instabilities caused during the video acquisition process due to vibrations and undesired motion when handling the camera. In this work, we propose and evaluate a novel approach to video stabilization based on an adaptive Gaussian filter to smooth the camera trajectories. Experiments conducted on several video sequences demonstrate the effectiveness of the method, which generates videos with adequate trade-off between stabilization rate and amount of frame pixels. Our results were compared to YouTube's state-of-the-art method, achieving competitive results.

show abstract

A Robust Image Alignment Algorithm for Video Stabilization Purposes

Cited by 83 publications

References 34 publications

Video stabilisation based on modelling of motion imaging

Video stabilisation based on modelling of motion imaging

Image sensor noise profiling by voting based curve fitting

Digital video stabilization based on adaptive camera trajectory smoothing

Contact Info

Product

Resources

About