%0 Journal Article %1 R_2015 %A Khot, Vaishali R. %A S.Tamboli, A. %D 2015 %I Auricle Technologies, Pvt., Ltd. %J International Journal on Recent and Innovation Trends in Computing and Communication %K Conditional Extraction Field Motion Object Random Saliency Smoothing Video Visual filter %N 3 %P 1688--1691 %R 10.17762/ijritcc2321-8169.1503172 %T Parallel Processing Of Visual And Motion Saliency From Real Time Video %U http://dx.doi.org/10.17762/ijritcc2321-8169.1503172 %V 3 %X Extracting moving and salient objects from videos is important for many applications like surveillance and video retargeting .The proposed framework extract foreground objects of interest without any user interaction or the use of any training data(Unsupervised Learning) .To separate foreground and background regions within and across video frames, the proposed method utilizes visual and motion saliency information extracted from the input video. The Smoothing filter is extremely helpful in characterizing fundamental image constituents, i.e. salient edges and can simultaneously reduce insignificant details, thus producing more accurate boundary information. Our proposed model uses smoothing filter to reduce the effect of noise and achieve a better performance. Proposed system uses real time video data input as well as offline data to process using parallel processing technique. A conditional random field can be applied to effectively combine the saliency induced features. To evaluate the performance of saliency detection methods, the precision-recall rate and F-measures are utilized to reliably compare the extracted saliency information.

@article{R_2015, abstract = {Extracting moving and salient objects from videos is important for many applications like surveillance and video retargeting .The proposed framework extract foreground objects of interest without any user interaction or the use of any training data(Unsupervised Learning) .To separate foreground and background regions within and across video frames, the proposed method utilizes visual and motion saliency information extracted from the input video. The Smoothing filter is extremely helpful in characterizing fundamental image constituents, i.e. salient edges and can simultaneously reduce insignificant details, thus producing more accurate boundary information. Our proposed model uses smoothing filter to reduce the effect of noise and achieve a better performance. Proposed system uses real time video data input as well as offline data to process using parallel processing technique. A conditional random field can be applied to effectively combine the saliency induced features. To evaluate the performance of saliency detection methods, the precision-recall rate and F-measures are utilized to reliably compare the extracted saliency information.}, added-at = {2015-08-13T08:39:35.000+0200}, author = {Khot, Vaishali R. and S.Tamboli, A.}, biburl = {https://www.bibsonomy.org/bibtex/23e51abe4261d4e66ec2b3f338b72d822/ijritcc}, doi = {10.17762/ijritcc2321-8169.1503172}, interhash = {39d95cfa940c6ed8584609218fc71dd6}, intrahash = {3e51abe4261d4e66ec2b3f338b72d822}, journal = {International Journal on Recent and Innovation Trends in Computing and Communication}, keywords = {Conditional Extraction Field Motion Object Random Saliency Smoothing Video Visual filter}, month = {march}, number = 3, pages = {1688--1691}, publisher = {Auricle Technologies, Pvt., Ltd.}, timestamp = {2015-08-13T08:39:35.000+0200}, title = {Parallel Processing Of Visual And Motion Saliency From Real Time Video}, url = {http://dx.doi.org/10.17762/ijritcc2321-8169.1503172}, volume = 3, year = 2015 }