Computational time-lapse video

Huang³

et al. 2013

IEEE Trans. Multimedia

A large amount of short, single-shot videos are created by personal camcorder every day, such as the small video clips in family albums, and thus a solution for presenting and managing these video clips is highly desired. From the perspective of professionalism and artistry, long-take/shot video, also termed oneshot video, is able to present events, persons or scenic spots in an informative manner. This paper presents a novel video composition system "Video Puzzle" which generates aesthetically enhanced long-shot videos from short video clips. Our task here is to automatically composite several related single shots into a virtual long-take video with spatial and temporal consistency. We propose a novel framework to compose descriptive long-take video with content-consistent shots retrieved from a video pool. For each video, frame-by-frame search is performed over the entire pool to find start-end content correspondences through a coarse-to-fine partial matching process. The content correspondence here is general and can refer to the matched regions or objects, such as human body and face. The content consistency of these correspondences enables us to design several shot transition schemes to seamlessly stitch one shot to another in a spatially and temporally consistent manner. The entire long-take video thus comprises several single shots with consistent contents and fluent transitions. Meanwhile, with the generated matching graph of videos, the proposed system can also provide an efficient video browsing mode. Experiments are conducted on multiple video albums and the results demonstrate the effectiveness and the usefulness of the proposed scheme. Index Terms-Image retrieval, one-shot video, video authoring, video transition. I. INTRODUCTION W ITH the popularity of personal digital devices, the amount of home video data is growing explosively. These digital videos have several characteristics: (1) compared Manuscript

Section: A Video Summarizationmentioning

confidence: 99%

Section: An Overview Of the Schemementioning

confidence: 99%

VideoPuzzle: Descriptive One-Shot Video Composition

Chen

Huang³

et al. 2013

IEEE Trans. Multimedia

“…Existing methods can be classified into two categories, i.e., dynamic representation and static representation. Dynamic representation generates a video sequence that is composed of a series of sub-clips extracted from one or multiple video sequences or generated from a collection of photos [10], [22], [30], whereas static representation generally generates one or multiple images from video key-frames to facilitate not only viewing but also transmission and storage [4], [7], [8], [17], [27], [35]. In comparison with the conventional video abstraction methods that mainly target at reducing the redundancy in video streams, our work focuses on the better transformation from movies to comics instead of redundancy reduction.…”

Section: Related Workmentioning

confidence: 99%

“…The users are asked to freely browse the comics generated by different paradigms. Then, they are asked to make a comparison 4 . When comparing two paradigms, each user can make a "better", "much better", and "comparable" choice.…”

Section: ) Comprehensive Comparison Of Different Paradigmsmentioning

confidence: 99%

Movie2Comics: Towards a Lively Video Content Presentation

Hong

Yuan

et al. 2012

IEEE Trans. Multimedia

119

As a type of artwork, comics is prevalent and popular around the world. However, despite the availability of assistive software and tools, the creation of comics is still a labor-intensive and time-consuming process. This paper proposes a scheme that is able to automatically turn a movie clip to comics. Two principles are followed in the scheme: 1) optimizing the information preservation of the movie; and 2) generating outputs following the rules and the styles of comics. The scheme mainly contains three components: script-face mapping, descriptive picture extraction, and cartoonization. The script-face mapping utilizes face tracking and recognition techniques to accomplish the mapping between characters' faces and their scripts. The descriptive picture extraction then generates a sequence of frames for presentation. Finally, the cartoonization is accomplished via three steps: panel scaling, stylization, and comics layout design. Experiments are conducted on a set of movie clips and the results have demonstrated the usefulness and the effectiveness of the scheme.

“…The factorization allows a user to easily relight the scene, recover a portion of the scene geometry, and perform advanced image editing operations. Bennett and McMillan [13] proposed a non-uniform sampling algorithm, which optimizes the summarization of the input video-rate footage to match the desired duration and visual output characteristics. In this paper, we implement a real-time exposure control system benefiting from the high computationally efficiency of GPU.…”

Section: Video Post-processingmentioning

confidence: 99%

Active entropy camera

Machine Vision and Applications

2011

Automatic exposure control (AEC) is traditionally based on the sampled intensity level in an image frame. However in certain situations, such intensity-based AEC does not achieve the desired results (with a maximum entropy) as shown in several examples in this paper. In most cases, maximizing entropy is the goal of a machine-vision system. We want the imaging system that captures the most amount of information, so that as many feature points as possible are presented in the captured image. To solve this problem, we propose an entropy-based exposure control technique. This technique adjusts the camera exposure setting to maximize the amount of information captured in the image frame. The amount of information is measured by Shannon entropy. The proposed entropy calculation is accelerated by graphics processing units (GPUs) to achieve a real-time performance. Experimental results show that under a number of conditions our AEC performs better than the traditional intensity-based AEC, preserving more detail, and capturing more information.