Synchronized digital video subsampling to achieve temporal resolution independence Export

@proceedings{San2007isie, abstract = {In this paper, we present a selective video sub-sampling algorithm to achieve temporal resolution independence in applications with hard requirements on frame sequentiality, especially targeted to video identification systems based on fingerprint strings. The algorithm extracts video entropy, and based on the resulting series, a set of intervals and frames for each interval are selected. The same exact intervals and frames can be repeatedly extracted for any other variation of the original content, which is especially desirable when variations have undergone dramatic quality and frame rate reduction in their distribution. Different from basic subsampling techniques, the proposed method is not just able to get a frame set of equal length for different frame rate variations, but the generated set includes more frames when events are going on in the video, while less frames are chosen when the video content remains steady. This fact provides a significant improve of performance in terms of recall and precision values in video identification applications.}, author = {San Pedro and Dominguez}, booktitle = {Industrial Electronics, 2007. ISIE 2007. IEEE International Symposium on}, citeulike-article-id = {4207461}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/ISIE.2007.4374876}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4374876}, doi = {10.1109/ISIE.2007.4374876}, journal = {Industrial Electronics, 2007. ISIE 2007. IEEE International Symposium on}, keywords = {detection, duplicate, hash, identification, video, visual}, pages = {1785--1790}, posted-at = {2009-03-22 17:21:18}, priority = {2}, title = {Synchronized digital video subsampling to achieve temporal resolution independence}, url = {http://dx.doi.org/10.1109/ISIE.2007.4374876}, year = {2007} }

TY - CONF ID - San2007isie L3 - citeulike-article-id:4207461 N2 - In this paper, we present a selective video sub-sampling algorithm to achieve temporal resolution independence in applications with hard requirements on frame sequentiality, especially targeted to video identification systems based on fingerprint strings. The algorithm extracts video entropy, and based on the resulting series, a set of intervals and frames for each interval are selected. The same exact intervals and frames can be repeatedly extracted for any other variation of the original content, which is especially desirable when variations have undergone dramatic quality and frame rate reduction in their distribution. Different from basic subsampling techniques, the proposed method is not just able to get a frame set of equal length for different frame rate variations, but the generated set includes more frames when events are going on in the video, while less frames are chosen when the video content remains steady. This fact provides a significant improve of performance in terms of recall and precision values in video identification applications. JF - Industrial Electronics, 2007. ISIE 2007. IEEE International Symposium on EP - 1790 TI - Synchronized digital video subsampling to achieve temporal resolution independence T2 - Industrial Electronics, 2007. ISIE 2007. IEEE International Symposium on SP - 1785 KW - detection KW - duplicate KW - hash KW - identification KW - video KW - visual AU - San Pedro AU - Dominguez PY - 2007/// UR - http://dx.doi.org/10.1109/ISIE.2007.4374876 ER -