A runtime reconfigurable very-large-scale integration （VLSI） architecture for image and video scaling by arbitrary factors with good antialiasing performance is presented in this paper. Video scal- ing is used in a ...A runtime reconfigurable very-large-scale integration （VLSI） architecture for image and video scaling by arbitrary factors with good antialiasing performance is presented in this paper. Video scal- ing is used in a wide range of applications from broadcast, medical imaging and high-resolution video effects to video surveillance, and video conferencing. Many algorithms have been proposed for these applications, such as piecewise polynomial kernels and windowed sinc kernels. The sum of three shifted versions of a B-spline function, whose weights can be adjusted for different applications, is adopted as the main filter. The proposed algorithm is confirmed to be effective on image scaling ap- plications and also verified by many widely acknowledged image quality measures. The reconfigu- rable hardware architecture constitutes an arbitrary scaler with low resource consumption and high performance targeted for field programmable gate array （FPGA） devices. The scaling factor can be changed on-the-fly, and the filter can also be changed during runtime within a unifying framework.展开更多
Video synopsis is an effective and innovative way to produce short video abstraction for huge video archives,while keeping the dynamic characteristic of activities in the original video.Abnormal activity,as the critic...Video synopsis is an effective and innovative way to produce short video abstraction for huge video archives,while keeping the dynamic characteristic of activities in the original video.Abnormal activity,as the critical event,is always the main concern in video surveillance context.However,in traditional video synopsis,all the normal and abnormal activities are condensed together equally,which can make the synopsis video confused and worthless.In addition,the traditional video synopsis methods always neglect redundancy in the content domain.To solve the above-mentioned issues,a novel video synopsis method is proposed based on abnormal activity detection and key observation selection.In the proposed algorithm,activities are classified into normal and abnormal ones based on the sparse reconstruction cost from an atomically learned activity dictionary.And key observation selection using the minimum description length principle is conducted for eliminating content redundancy in normal activity.Experiments conducted in publicly available datasets demonstrate that the proposed approach can effectively generate satisfying synopsis videos.展开更多
基金Supported by the National Natural Science Foundation of China(No.60972126)the Joint Funds of the National Natural Science Foundation of China(No.U0935002/L05)+1 种基金the Beijing Municipal Natural Science Foundation(No.4102060)the State Key Program of the National Natural Science of China(No.61032007)
文摘A runtime reconfigurable very-large-scale integration （VLSI） architecture for image and video scaling by arbitrary factors with good antialiasing performance is presented in this paper. Video scal- ing is used in a wide range of applications from broadcast, medical imaging and high-resolution video effects to video surveillance, and video conferencing. Many algorithms have been proposed for these applications, such as piecewise polynomial kernels and windowed sinc kernels. The sum of three shifted versions of a B-spline function, whose weights can be adjusted for different applications, is adopted as the main filter. The proposed algorithm is confirmed to be effective on image scaling ap- plications and also verified by many widely acknowledged image quality measures. The reconfigu- rable hardware architecture constitutes an arbitrary scaler with low resource consumption and high performance targeted for field programmable gate array （FPGA） devices. The scaling factor can be changed on-the-fly, and the filter can also be changed during runtime within a unifying framework.
基金Supported by the National Natural Science Foundation of China(No.61402023)Beijing Technology and Business' University Youth Fund(No.QNJJ2014-23)Beijing Natural Science Foundation(No.4162019)
文摘Video synopsis is an effective and innovative way to produce short video abstraction for huge video archives,while keeping the dynamic characteristic of activities in the original video.Abnormal activity,as the critical event,is always the main concern in video surveillance context.However,in traditional video synopsis,all the normal and abnormal activities are condensed together equally,which can make the synopsis video confused and worthless.In addition,the traditional video synopsis methods always neglect redundancy in the content domain.To solve the above-mentioned issues,a novel video synopsis method is proposed based on abnormal activity detection and key observation selection.In the proposed algorithm,activities are classified into normal and abnormal ones based on the sparse reconstruction cost from an atomically learned activity dictionary.And key observation selection using the minimum description length principle is conducted for eliminating content redundancy in normal activity.Experiments conducted in publicly available datasets demonstrate that the proposed approach can effectively generate satisfying synopsis videos.
