Restoration of out-of-focus lecture video by automatic slide matching

Cheung, Ngai-Man; Chen, David; Chandrasekhar, Vijay; Tsai, Shiou‐Chuan; Takacs, Gabriel; Halawa, Sherif; Girod, Bernd

doi:10.1145/1873951.1874108

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method uses the iterative scanline algorithm to map every pixel of a video frame to the slide area and then determines the average of the corresponding slide pixels. Automated matching of the slides to video frames and the accurate computation of H has been developed by Fan et al and others [10][11][12][13][14][15]. We observed that while backprojection requires accurate homographies for all frames, most of the transformations in a typical video can be approximated using affine transformations.…”

Section: Backprojectionmentioning

confidence: 88%

Client-side backprojection of presentation slides into educational video

Kharitonova

Tung

Danehy

et al. 2012

Proceedings of the 20th ACM International Conference on Multimedia

View full text Add to dashboard Cite

A significant part of many videos of lectures is presentation slides that occupy much of the field of view. Further, for a student studying the lecture, having the slides sharply displayed is especially important, compared with the speaker, background, and audience. However, even if the original capture supports it, the bandwidth required for real time viewing is substantive, especially in the context of mobile devices. Here we propose reconstructing the video on the client side by backprojecting high resolution slide images into the video stream with the slide area blacked out. The high resolution slide deck can be sent once, and inserted into the video on the client side based on the transformation (a homography) computed in advance. We further introduce the idea that needed homography transformations can be approximated using affine transformations, which allows it to be done using built-in capabilities of HTML 5. We find that it is possible to significantly reduce bandwidth by compressing the modified video, while improving the slide area quality, but leaving the non-slide area roughly the same.

show abstract

Section: Backprojectionmentioning

confidence: 88%

Client-side backprojection of presentation slides into educational video

Kharitonova

Tung

Danehy

et al. 2012

Proceedings of the 20th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…For advertisement monitoring, users can find all points in time in a video where a particular logo or object was shown. In education, users might use a slide to find the point in time in a lecture video where a certain concept was explained [4]. For content linking, users could use an image in an article to find related video stories.…”

Section: Introductionmentioning

confidence: 99%

Real-time query-by-image video search system

Araujo

Chen

Vajda

et al. 2014

Proceedings of the 22nd ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

We demonstrate a novel multimedia system that continuously indexes videos and enables real-time search using images, with a broad range of potential applications. Television shows are recorded and indexed continuously, and iconic images from recent events are discovered automatically. Users can query an uploaded image or an image in the web. When a result is served, the user can play the video clip from the beginning or from the point in time where the retrieved image was found.

show abstract

Implementation of high-definition lecture recording system for daily use

Nagai

Toyota

Nagoya

et al. 2013

2013 IEEE Global Engineering Education Conference (EDUCON)

View full text Add to dashboard Cite

The recording of lecture videos and disseminating them is becoming popular. However, recording and postprocessing daily lectures still demands much human effort and financial resources. Our goal is to develop a cost-effective and labor-saving video processing system that can record lectures in high-definition and process them for additional analysis and publishing. Our main idea is that high-definition recording itself is labor-saving. A stationary high-definition camcorder can record a lecturer and an entire classroom clearly so that notes can be read on a whiteboard and projector screen. Therefore, no camera operator is necessary during recording. We succeeded in implementing a cost-effective system without expensive hardware components for capturing a high-definition video signal. In this contribution, we describe the design and operational results of our system, which has recorded about 20 lectures every school week since 2010.

show abstract

Restoration of out-of-focus lecture video by automatic slide matching

Cited by 3 publications

References 11 publications

Client-side backprojection of presentation slides into educational video

Client-side backprojection of presentation slides into educational video

Real-time query-by-image video search system

Implementation of high-definition lecture recording system for daily use

Contact Info

Product

Resources

About