Well-produced videos provide a convenient and effective way to archive lectures. In this article, we offer a new way to create lecture videos that retains many of the advantages of well-composed recordings, without the cost and intrusion of a video production crew. We present an automated system called Virtual Videography that employs the art of videography to mimic videographerproduced videos, while unobtrusively recording lectures. The system uses the data recorded by unattended video cameras and microphones to produce a new edited video as an offline postprocess. By producing videos offline, our system can use future information when planning shot sequences and synthesizing new shots. Using simple syntactic cues gathered from the original video and a novel shot planning algorithm, the system makes cinematic decisions without any semantic understanding of the lecture.

The fast evolution of digital video has brought many new applications. Consequently, research and development of new technologies are greatly needed which will lower the costs of video archiving, cataloging and indexing, as well as improve the efficiency and accessibility of stored videos. Among all possible research areas, video abstraction is one of the most important topics, which helps to enable a quick browsing of a large collection of video data and to achieve efficient content access and representation. There are two fundamentally different types of video abstracts: still- and moving-image abstracts. The stillimage abstract, also known as a static storyboard, is a small collection of salient images extracted or generated from the underlying video source. The moving-image abstract, also known as moving storyboard, consists of a collection of image sequences, as well as the corresponding audio abstract extracted from the original sequence and is thus itself a video clip but of considerably shorter length. In this report, we present an overview of major technologies employed by each type of video abstraction, respectively. A list of important players in this research area, from both universities and the industry, is also provided.

This paper presents an automatic and novel approach in detecting the transitions of slides for video sequences of technical lectures. Our approach adopts a foreground vs background segmentation algorithm to separate a presenter from the projected electronic slides. Once a background template is generated, text captions are detected and analyzed. The segmented caption regions as well as background templates together provide salient visual cues to decide whether a slide is flipped and replaced. The partitioning of videos according to slide changes not only structure the content of video according to topics, but also facilitate the synchronization of video, audio and electronic slides for effective indexing, browsing and retrieval. 1.

Presentations are becoming an increasingly more common means of communication in working environments, and slides are often the necessary supporting material on which the presentations rely. In this paper, we describe a slide indexing and retrieval system in which the slides are captured as images (through a framegrabber) at the moment they are displayed during a presentation and then transcribed with an OCR system. In this context, we show that such an approach presents several advantages over the use of commercial software (API based) to obtain the slide transcriptions. We report a set of retrieval experiments conducted on a database of 26 real presentations (570 slides) collected at a workshop. The experiments show that the overall retrieval performance is close to that obtained using either a manual transcription of the slides or the API software. Moreover, the experiments show that the OCR based approach outperforms significantly the API in extracting the text embedded in images and figures.

We propose a method for segmentation of written regions on a blackboard in the lecture room using a video image. We firstly detect static edges of which locations on the image are stationary. And next, we extract several rectangular regions in which these static edges are located densely. Finally by use of fuzzy rules, extracted rectangles are merged as contextual regions, where letters and figures in each contextual region explain each context. And, we apply our method to automatic production of lecture video, and archives system of written regions on the blackboard in lecture rooms. 1. Introduction Recently, universities and other kinds of schools begin to take an interest in a distance learning system, which can perform lectures at various locations far from lecturers at the same time [1]. State of the art low cost wide band communication system makes such systems realistic. On the other hand, usual lecture videos and lecture notes can be used for similar objective. And also lectu...

This paper presents a gesture based driven approach for video editing. Given a lecture video, we adopt novel approaches to automatically detect and synchronize its content with electronic slides. The gestures in each synchronized topic (or shot) are then tracked and recognized continuously. By registering shots and slides and recovering their transformation, the regions where the gestures take place can be known. Based on the recognized gestures and their registered positions, the information in slides can be seamlessly extracted, not only to assist video editing, but also to enhance the quality of original lecture video. 1

This thesis addresses the problem of recovering a locally layered representation of image motion. We develop the "Skin and Bones" model for estimating optical flow that strikes a balance between the flexibility of regularization techniques and the robustness and accuracy of area-based regression techniques. The approach assumes that image motion can be represented by an affine flow model within local image patches. Since some image regions may not have sufficient information to estimate an affine motion model robustly, we define a spatial smoothness constraint on the affine flow parameters of neighboring patches. We refer to this as a "Skin and Bones" model in which the affine patches can be thought of as rigid patches of "bone" connected by a exible "skin." Since local image patches may contain multiple motions we use a layered representation for the affine bones. With the possibility of multiple motions at a given point, standard regularization schemes cannot be used to smooth the multiple sets of affine parameters. We therefore develop a new framework for regularization with transparency that can applied to produce a smoothed layered motion representation. The motion estimation problem, with layered locally affine patches and transparent

Abstract — Our objective is to find a small set of images that summarize a robot’s visual experience along a path. We present a novel on-line algorithm for this task. This algorithm is based on a new extension to the classical Secretaries Problem. We also present an extension to the idea of Bayesian Surprise, which we then use to measure the fitness of an image as a summary image. I.

Abstract — A saliency-based method for generating video summaries is presented, which exploits coupled audiovisual information from both media streams. Efficient and advanced speech and image processing algorithms to detect key frames that are acoustically and visually salient are used. Promising results are shown from experiments on a movie database. Keywords—saliency; saliency curves; attention modeling; event detection; key-frame selection; video summarization; audiovisual Topic area—Multimedia:methods and systems (indexing and search of multimedia) I.

In instructional videos of chalk board presentations, the visual content refers to the text and figures written on the boards. Existing methods on video summarization are not effective for this video domain because they are mainly based on low-level image features such as color and edges. In this work, we present a novel approach to summarizing the visual content in instructional videos using middle-level features. We first develop a robust algorithm to extract content text and figures from instructional videos by statistical modelling and clustering. This algorithm addresses the image noise, non-uniformity of the board regions, camera movements, occlusions, and other challenges in the instructional videos that are recorded in real classrooms. Using the extracted text and figures as the middle level features, we retrieve a set of key frames that contain most of the visual content. We further reduce content redundancy and build a mosaicked summary image by matching extracted content based on K-th Hausdorff distance and connected component decomposition. Performance evaluation on four full-length instructional videos shows that our algorithm is highly effective in summarizing instructional video content.