A brand new application of visual-audio fingerprints: Estimating the position of the pirate in a theater - A case study

作者：

Highlights：

• Brand-new application of Video fingerprinting to record illegal capture location

• Base frames selection algorithm using Hashing to get temporal frame alignments.

• Stable key-point pairs selection algorithm to extract most similar key point pairs

• First attempt using visual-audio features to estimate pirate position in a theater

• In-theater experiments estimate positions with a MAE of (38.25, 22.45, 11.11) cm.

摘要

•Brand-new application of Video fingerprinting to record illegal capture location•Base frames selection algorithm using Hashing to get temporal frame alignments.•Stable key-point pairs selection algorithm to extract most similar key point pairs•First attempt using visual-audio features to estimate pirate position in a theater•In-theater experiments estimate positions with a MAE of (38.25, 22.45, 11.11) cm.

论文关键词：Camcorder piracy,Content-Based video Copy Detection (CBCD),Visual fingerprints,Audio signatures,SURF,Projective geometry,Geometric distortions

论文评审过程：Received 21 June 2016, Revised 22 May 2018, Accepted 5 June 2018, Available online 28 June 2018, Version of Record 28 June 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.06.001