Real-time detection of partial video copy on TV workstation

Abstract

A system for the real-time copy detection of live TV videos is presented. A TV workstation supports the real-time and multichannel processing. Real-time NCC features are used for matching. A key-frame selection method ensures the robustness, the response and processing time optimization. Experiments are reported for time processing and accuracy on a public dataset against competitive methods.

A Large-scale TV Dataset for Partial Video Copy Detection

“…Our component (C1) [14] captures the TV programs with a workstation [3,14,13]. This workstation can record daily video files on 8 TV channels simultaneously.…”

“…We have considered the Zero-mean Normalized Cross-Correlation (ZNCC) for matching as a learning-free method [20]. The ZNCC fits well with the detection problem as it is robust to noise and contrast-invariant [4,13].…”

“…It is a well-known topic in the computer vision field [12]. The recent works investigate the detection methods robust to the spatial & temporal deformations [6,5,15] or real-time [4,13,19]. A key aspect for any computer vision task is to design public datasets for performance evaluation.…”

A large-scale TV video and metadata database for French political content analysis and fact-checking

“…In our work, we have used the TV workstation depicted in [20]. This workstation has been mainly used for the task of realtime video processing [20][21][22]. We detail here how we have adapted it for the video capture of political TV programs.…”