Other

Technische Unversität Berlin

Ecodisc Technology Ag

Ronald Glasberg

Thomas Sikora

Pascal Kelm

Hüseyin Oguz

Sebastian Schmiedeke

Martin Mocigemba

Cengiz Tas

An exemplary embodiment of the invention relates to a method for classifying a video sequence (VS), characterized by the steps of analyzing the video sequence using a plurality of genre-specific detector modules (M-M), each genre-specific detector module providing a probability value (P-P) indicating the probability that the video sequence belongs to the genre assigned to the genre-specific detector module; and analyzing the probability values of the plurality of genre-specific detector modules using a combiner (CM) which analyzes said probability values and generates a classification signal (SC) classifying the video sequence as belonging to a specific genre (g).

Video-genre classification

Systems, methods, and devices for detecting a commercial in a video data stream by evaluating descriptor information provided from a plurality of visual descriptors indicative of commercial or non-commercial features. The descriptor information provided from the plurality of descriptors may be evaluated in an entropy based decision process.

Method for detecting a commercial in a video data stream by evaluating descriptor information

Growing community of inventors

Berlin, Germany

Ronald Glasberg