Evaluation of image stabilization algorithms

Morimoto, Carlos H.; Chellappa, Rama

doi:10.1109/icassp.1998.678102

Cited by 151 publications

(88 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Harris Corner Detection is one of the fastest algorithms to find corner values. Edward Rosten et.al proposed faster and better machine learning approach to corner detection [4]. This algorithm also used principle of identifying Interest points in an image.…”

Section: Literature Surveymentioning

confidence: 99%

“…In the second phase parameters of estimated motion are sent to motion smoothening, where it removes the high-frequency distortion and calculates the global transformation. [4] Next, warping will be done for motion compensation to get stabilized video. These three-step frameworks are the essential steps in most of the video stabilization algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stabilization of Jittery Videos Using Feature Point Matching Technique

Kulkarni

Bormane

Nalbalwar

2017

Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016)

View full text Add to dashboard Cite

Abstract:Video capturing by non-professionals will lead to unanticipated effects. such as image distortion, image blurring etc. Many researchers focused on these drawbacks to enhance the quality of videos. In this paper an algorithm based on s-R-t transform is proposed to stabilize jittery videos .A stable output video is obtained without the effect of jitter which is caused due to shaking of handheld camera during video recording. In this technique firstly, salient points from each frame from the input video are identified using FAST algorithm. Camera motion is corrected by affine transform and motion compensation is performed by s-R-t transform which gives stabilized video. Optimization includes the quality of the video stabilization. This method has shown good result in terms of stabilization and it discarded distortion from the output videos recorded in different circumstances.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Stabilization of Jittery Videos Using Feature Point Matching Technique

Kulkarni

Bormane

Nalbalwar

2017

Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016)

View full text Add to dashboard Cite

show abstract

“…Two-dimensional stabilization methods estimate a homography sequence from the input video, dampen this sequence, and warp video frames based on the smoothed sequence [9], [10], [11], [12], [13], [14]. A recent method achieves aggressive smoothing using L1 optimization [8], in which the gradient of the camera motion at each frame can be strongly suppressed, to produce very high-quality results.…”

Section: Related Workmentioning

confidence: 99%

Spatially and Temporally Optimized Video Stabilization

Wang

Liu

Hsu

et al. 2013

IEEE Trans. Visual. Comput. Graphics

100

View full text Add to dashboard Cite

Abstract-Properly handling parallax is important for video stabilization. Existing methods that achieve the aim require either 3D reconstruction or long feature trajectories to enforce the subspace or epipolar geometry constraints. In this paper, we present a robust and efficient technique that works on general videos. It achieves high-quality camera motion on videos where 3D reconstruction is difficult or long feature trajectories are not available. We represent each trajectory as a Bé zier curve and maintain the spatial relations between trajectories by preserving the original offsets of neighboring curves. Our technique formulates stabilization as a spatialtemporal optimization problem that finds smooth feature trajectories and avoids visual distortion. The Bé zier representation enables strong smoothness of each feature trajectory and reduces the number of variables in the optimization problem. We also stabilize videos in a streaming fashion to achieve scalability. The experiments show that our technique achieves high-quality camera motion on a variety of challenging videos that are difficult for existing methods.

show abstract

“…Most video stabilization methods follow a three-step framework consisting of three steps: motion estimation, motion compensation (also called motion smoothing or motion filtering) and image composition [15]. Motion estimation estimates the motion between frames.…”

Section: Introductionmentioning

confidence: 99%

Video stabilization using robust feature trajectories

Lee

Chuang

Chen

et al. 2009

2009 IEEE 12th International Conference on Computer Vision

View full text Add to dashboard Cite

This paper proposes a new approach for video stabilization. Most existing video stabilization methods adopt a framework of three steps, motion estimation, motion compensation and image composition. Camera motion is often estimated based on pairwise registration between frames. Thus, these methods often assume static scenes or distant backgrounds. Furthermore, for scenes with moving objects, robust methods are required for finding the dominant motion. Such assumptions and judgements could lead to errors in motion parameters. Errors are compounded by motion compensation which smoothes motion parameters. This paper proposes a method to directly stabilize a video without explicitly estimating camera motion, thus assuming neither motion models nor dominant motion. The method first extracts robust feature trajectories from the input video. Optimization is then performed to find a set of transformations to smooth out these trajectories and stabilize the video. In addition, the optimization also considers quality of the stabilized video and selects a video with not only smooth camera motion but also less unfilled area after stabilization. Experiments show that our method can deal with complicated videos containing near, large and multiple moving objects.

show abstract

Evaluation of image stabilization algorithms

Cited by 151 publications

References 7 publications

Stabilization of Jittery Videos Using Feature Point Matching Technique

Stabilization of Jittery Videos Using Feature Point Matching Technique

Spatially and Temporally Optimized Video Stabilization

Video stabilization using robust feature trajectories

Contact Info

Product

Resources

About