Comparison of Motion Smoothing Strategies for Video Stabilization using Parametric Models

Abstract

This paper is devoted to a rigorous implementation and to an exhaustive comparison of video stabilization techniques. These techniques aim at removing the undesirable effects of camera shake. They first estimate a global transform from frame to frame, which can be a translation, a similarity, an affine map or a homography. This generates a signal that can be smoothed and used to compensate the noisy transform signal. This paper compares all classic smoothing methods and their boundary conditions. It also analyzes two algorithms to crop the video after stabilization. The stabilization results are displayed in a scale-space form permitting to extract valuable information about ego-motion such as its frequencies and its general tendencies. Source CodeThe reviewed source code and documentation for this algorithm are available from the web page of this article 1 . Compilation and usage instructions are included in the README.txt file of the archive.

Single-Camera Basketball Tracker through Pose and Semantic Feature Fusion

“…Taking into account that its inclusion represents extra computations, in this paper, an ablation study is provided to discuss the extend of its advantages. When enclosed, the camera stabilization method and implementation in [17] is used. It estimates a set of homographies, each of which associated to a frame of the video and allowing to stabilize it.…”

Object removal from complex videos using a few annotations

“…Video stabilization. In general, patch-based video inpainting techniques require good video stabilization as a pre-processing step to compensate for patch deformations due to camera motions [85,86]. This video stabilization is usually done by calculating a homography between pairs of consecutive frames using keypoint matching followed by an RANSAC algorithm to remove outliers [87].…”

An Analysis and Implementation of the Harris Corner Detector

“…• Finally, we may also select a set of corners equally distributed on the image, which is interesting for several applications such as camera calibration, panorama stitching [3] or video stabilization [18]. In that case, the user specifies a number of cells and the total number of points to be detected.…”

“…The Harris corner detector [9] is a standard technique for locating interest points on an image. Despite the appearance of many feature detectors in the last decade [11,1,17,24,23], it continues to be a reference technique, which is typically used for camera calibration, image matching, tracking [21] or video stabilization [18].…”