Digital video processing
A new motion histogram to index motion content in video segments
Pattern Recognition Letters
On clustering and retrieval of video shots through temporal slices analysis
IEEE Transactions on Multimedia
Content analysis of video using principal components
IEEE Transactions on Circuits and Systems for Video Technology
Dynamic Programming-Based Reverse Frame Selection for VBR Video Delivery Under Constrained Resources
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
In this paper, we present a new motion feature, viz. MotionCurve, and an o(n) algorithm for video adaptation. This new feature is based on motion activity in each video frame. The motion activity in each frame is represented by a Pixel Change Map(PCM) [7, 6]. A variational filter is applied on the PCM sequence to remove the noise and smooth “motion curve” for video adaptation. In our framework, the video adaptation is formulated as an optimization problem. The adaptation cost between any pair of frames is defined as the result of integration along the motion curves. With this cost function, video adaptation becomes a problem of selecting the optimal set of frames such that the summation of the cost of jumps on the Motion Curve is minimal. Experimental results on various videos demonstrate the effectiveness of our proposed ”motion curve” feature.