Keypoint-Based Keyframe Selection

Guan, Genliang; Wang, Zhiyong; Lu, Shiyang; Deng, Jeremiah D.; Feng, David Dagan

doi:10.1109/tcsvt.2012.2214871

Cited by 129 publications

(52 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to our experiments, redundant images in different panels annoy users. To avoid this annoying effect, in this work we further adopt the keypoint-based approach [21] to find near-duplicate frames and eliminate redundant keyframes. Finally, the method proposed in [22] was adopted to detect scene change boundaries as an important factor in page allocation.…”

Section: Preprocessingmentioning

confidence: 99%

“…For photos in an album, the keypoint-based approach [21] is also adopted to eliminate redundant photos. To detect photo scene change boundaries, we calculate the shooting time distance between temporally adjacent photos, and adopt the adaptive sliding window approach proposed in [23].…”

Section: Preprocessingmentioning

confidence: 99%

“…Finally, the five factors are linearly combined to jointly evaluate the objective function value (21) where are weights for combination and . With this objective function, the optimal balloon positions in the same page are determined in an integrated optimization framework, and can be efficiently solved.…”

Section: B Balloon Placementmentioning

confidence: 99%

See 2 more Smart Citations

Optimized Comics-Based Storytelling for Temporal Image Sequences

Chu

Wang

2015

IEEE Trans. Multimedia

View full text Add to dashboard Cite

We propose a system to transform any temporal image sequence into a comics-based presentation, as an effective and interesting storytelling manner. Three main components, including page allocation, layout selection, and speech balloon placement, are respectively formulated as optimization problems, and systematic approaches are proposed to find solutions. Page allocation is viewed as a labeling problem, and the best solution is determined by the genetic algorithm. Importance values of images and predefined layouts are both represented in vector forms, and the best layout is selected by finding the best match between vectors. Feasible solutions of speech balloons constitute a solution space, and the best solution that jointly describes the best locations of all balloons in a page is determined by the particle swarm optimization algorithm. Objective evaluation and subjective evaluation are designed from various perspectives to demonstrate effectiveness and superiority of the proposed system.Index Terms-Comics-based storytelling, genetic algorithm, layout selection, page allocation, particle swarm optimization, speech balloon placement.

show abstract

Section: Preprocessingmentioning

confidence: 99%

Section: Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Optimized Comics-Based Storytelling for Temporal Image Sequences

Chu

Wang

2015

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…It has been researched by many researchers and heavy achievements have been made in recent years [2,3,4,5,17,6,7,8,9]. Review the past, video summarization is started by structured videos [18,19,8,20,21], such as news, sports or surveillance videos. Following, consumer videos is studied for video summarization by researchers as a new topic at the time [13,2,3,11,22].…”

mentioning

confidence: 99%

“…Visual attention model is introduced to video summarization in [8], This work employs image signature algorithm and temporal gradients to simulate human being cognition and select keyframes with spatial and temporal contrast. Considering representativeness, a keypoint-based framework 80 is proposed in [9,21] which firstly generates global keypoint pool utilize local features. To ensure the best representation, the keypoints of those keyframes should cover the global keypoint pool as much as possible.…”

mentioning

confidence: 99%

Spatial and temporal scoring for egocentric video summarization

et al. 2016

View full text Add to dashboard Cite

Network video summarization based on key frame extraction via superpixel segmentation

Jin

et al. 2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The spread of insecure online video has been a serious social problem. The video summarization becomes one of key step for automatic filtering the expected video from the Internet. At present, the most existing video summarization methods are based on calculating the image similarity between video frames, so that the key frame can be selected properly. In this article, we introduce a superpixel segmentation based image similarity calculation, and then the metric is applied into video summarization. To identify the video key frames, we introduce superpixel segmentation to cluster the pixels locally by estimating the optical flow displacement field between successive frames, which can extract key frames and reduce video redundancy. On the VSUMM dataset and YouTube dataset, the experimental results demonstrate that the proposed method has clear advantages on both subjectively qualitative analysis and objectively quantitative evaluation comparing with the state of the art methods. INTRODUCTIONWith the popularization of the Internet, network security is becoming more and more important. With the gradual maturity of video capture technologies, huge numbers of digital video has emerged in each day. As the main multimedia information carrier, the digital video appears in all aspects of our daily life in the form of drama, news, sports, and surveillance. These massive videos enable people to obtain information in richer forms and bring great convenience to life. However, it has a huge impact on network security, which is an important issue related to national security, social stability, inheritance, and development of national culture. It also puts tremendous pressure on video storage, transmission, archiving, and retrieval. Facing vast video data, the video summarization technique enables us extracting the key contents without viewing all the video content. This technique is not only just giving us a quick view ability but also helping us on increasing storage density and ensuring network security. [1][2][3] At present, various algorithms are proposed to eliminate the redundancy of the original video by selecting and combining representative and meaningful portions of the video. The video summary problem was first introduced in 1994 at Carnegie Mellon University. 4 Since then, many researchers have joined in video summarization, which has already been improved significantly. According to the output, the current video summary technology can be roughly divided into two categories: dynamic video summary algorithm 5 and static video summary algorithm. 6 This article focuses on the static video summary based on key frames extraction, which is selecting the set of static key frames by optimizing the diversity or representativeness of the output.

show abstract

Keypoint-Based Keyframe Selection

Cited by 129 publications

References 11 publications

Optimized Comics-Based Storytelling for Temporal Image Sequences

Optimized Comics-Based Storytelling for Temporal Image Sequences

Spatial and temporal scoring for egocentric video summarization

Network video summarization based on key frame extraction via superpixel segmentation

Contact Info

Product

Resources

About