Open AccessA Method of Making Video Trailer Based on Artificial Intelligence
Author(s) -
Li Na,
LI Lan-you
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1314/1/012152
Subject(s) - computer science , trailer , character (mathematics) , loudness , artificial intelligence , speech recognition , optical flow , computer vision , face (sociological concept) , cascade , image (mathematics) , engineering , mathematics , computer network , social science , geometry , chemical engineering , sociology
Based on the flownet2 optical flow algorithm, cascade CNN face detection and facenet face recognition algorithm, the method of automatically generating video trailers by using the sum of the optical flow vector sum per second and the absolute value of the audio loudness amplitude per second and the character duration information is proposed. It can effectively edit the visual essence clip, the video essence clip corresponding to the audio, the main character clip and the story outline to generate a trailer.