Patent
Video segmentation techniques
Adam Carlson,Douglas Ryan Gray,Ashutosh Vishwas Kulkarni,Colin Jon Taylor +3 more
- 02 Sep 2016
24
TL;DR: In this article, a video segmentation system can be used to automate segmentation of digital video content by extracting features corresponding to visual, audio, and/or textual content of the video.
read more
Abstract: A video segmentation system can be utilized to automate segmentation of digital video content. Features corresponding to visual, audio, and/or textual content of the video can be extracted from frames of the video. The extracted features of adjacent frames are compared according to a similarity measure to determine boundaries of a first set of shots or video segments distinguished by abrupt transitions. The first set of shots is analyzed according to certain heuristics to recognize a second set of shots distinguished by gradual transitions. Key frames can be extracted from the first and second set of shots, and the key frames can be used by the video segmentation system to group the first and second set of shots by scene. Additional processing can be performed to associate metadata, such as names of actors or titles of songs, with the detected scenes.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Method for forming a tubular medical device
Raymond W. Buckman,Udayan Patel,Joseph G. Furst +2 more
- 25 Feb 2013
TL;DR: In this paper, a method and process for at least partially forming a medical device that is at least part formed of a metal alloy which improves the physical properties of the medical device is presented.
24
Patent
Method and apparatus for providing image contents
Soon-mook Jeong,Ji-hong Kang,Jae-min Soh,Ji-Hyo Lee,Jin-Wuk Choi +4 more
- 06 Aug 2015
TL;DR: In this article, a method for providing image contents is proposed, which divides the image contents into a plurality of scenes and classifies image frames for each scene depending on each of the plurality of characters appearing in the images.
7
Patent
Method of identifying key time point in video, computer equipment and storage medium
Wu Tao,Xu Xuyuan,Gong Guoping +2 more
- 13 Nov 2018
TL;DR: In this paper, the authors proposed a method of identifying a key time point in a video by processing each image frame in the video by an image classification model to obtain at least one video segment.
7
Patent
Video caption processing method, mobile terminal and computer readable storage medium
Zhang Jiabo
- 17 Jul 2018
TL;DR: In this article, a video caption processing method is presented, which comprises the following process: when a video file is started, acquiring a preset length of audio data from the video file according to a preset rule; identifying corresponding characters from the acquired audio data; generating captions via the recognized characters; and importing the captions into the video files for playing.
7
Patent
Anchorperson shot detection method and device
Liu Nan
- 22 Aug 2017
TL;DR: In this paper, the anchorperson shot detection method comprises the steps of acquiring a video comprising a plurality of video frames; according to the similarity among the video frames, partitioning all video frames into a plurality and extracting key frames of all the shots; and respectively using the key frame of each shot as an input of an anchorperson classifier to obtain an image figure attitude category of each key frame so as to determine an anchor person shot.
5
References
A feature-based algorithm for detecting and classifying production effects
TL;DR: The algorithm proposed withstands JPEG and MPEG artifacts, even at high compression rates, and can detect and classify production effects that are difficult to detect with previous approaches.
Patent
Method and system for segmentation, classification, and summarization of video images
Yihong Gong,Xin Liu +1 more
- 18 Aug 2006
TL;DR: In this paper, the singular value decomposition (SVDC) is used for video segmentation, classification, and summarization based on a metric to measure the amount of information contained in each video shot of the input video sequence.
154
Patent
System and method for visual search in a video media player
Jonathan David Barsook,Joven Matias,Cyrus J. Hoomani,Arun Ramagopal +3 more
- 23 Sep 2008
TL;DR: In this article, a system and method for visual search in a video media player is presented, where a user can visually select objects as search terms using a user interface on the display, initiate a search using the search terms, obtain search results comprising time offsets and play durations within the video files, each play duration containing at least one frame corresponding to the search term, and display navigational controls in the user interface for presenting the search results.
131
Patent
Video description system and method
Seungyup Paek,Ana B. Benitez,Shih-Fu Chang,Alexandros Elefteriadis,Atul Puri,Qian Huang,Chung-Sheng Li,Charlie Judice +7 more
- 05 Nov 1999
TL;DR: In this paper, video objects are further defined by a number of features organized in classes, which in turn are further connected by feature descriptors (36, 38 and 40) and relationships between and among the objects in the object set are defined by the object hierarchy and entity relation graphs.
121
Patent
Method and system for video indexing and video synopsis
Shmuel Peleg,Yael Pritch,A. Rav-Acha,Avital Gutman +3 more
- 09 Dec 2007
TL;DR: In this article, a system and method for generating a synopsis video from a source video, at least three different source objects are selected according to one or more defined constraints, each source object being a connected subset of image points from at least 3 different frames of the source video.
115
Related Papers (5)
C. Petersohn
- 27 Jun 2007
Omar Javed,Zeeshan Rasheed,Mubarak Shah +2 more
- 07 Jul 2001
Tao Wang,Yimin Zhang +1 more
- 26 Sep 2007
Bai Shuang
- 14 Sep 2018