AI Image Analysis in Era of Short-Time Viewing
In the era when short videos are preferred, broadcasting stations have been enhancing momentums to distribute summary videos of broadcast content on social media. Therefore, we have developed automatic generation systems for news and program summary videos. Using a video summarization artificial intelligence (AI) that has learned the image composition and camerawork typical of important scenes, it is possible to automatically generate summary videos with a high quality close to videos edited by actual program production staff. Our systems include functions enabling users to easily modify the automatically generated summary videos. These systems have been on trial/practical use in many Japan Broadcasting Corp. (NHK) broadcasting stations. The generated summary videos are posted daily on social media. Furthermore, considering a program website is also important content that could boost viewer contact rates, we developed a support system for program website creation using an AI to extract thumbnails automatically. AI-generated thumbnail images can be used to develop program websites wit minimal effort. These technologies can streamline the production of internet content such as summary videos and program websites. Moreover, they will significantly boost internet deployments of various broadcasting programs.
- Print ISSN
- 1545-0279
- Electronic ISSN
- 2160-2492
- Published
- 2024-04
- Content type
- Original Research
- Keywords
- video summarization, thumbnail extraction, neural network, ai
- DOI
- 10.5594/JMI.2024/BZSK5411