Keyframe extraction based on kmeas results to adjacent DC images similarity

Guo, Xiaojun

doi:10.1109/icsps.2010.5555457

Cited by 7 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the performance of coverage-based approaches is limited by the computation power of underlying hardware. Another category of key frame extraction methods that gains much attention is cluster-based algorithms (Zeng et al, 2008;Shi and Guo, 2010;Cheung and Zakhor, 2005;Peng et al, 2008). Cluster-based algorithms (Peng et al, 2008) require a preprocessing step that transforms frames into points of a feature space, where clustering methods are applied and all points are grouped into a bunch of clusters.…”

Section: Related Workmentioning

confidence: 99%

Within and Between Shot Information Utilisation in Video Key Frame Extraction

Liu

Shyu

Chen

et al. 2011

J. Info. Know. Mgmt.

View full text Add to dashboard Cite

In consequence of the popularity of family video recorders and the surge of Web 2.0, increasing amounts of videos have made the management and integration of the information in videos an urgent and important issue in video retrieval. Key frames, as a high-quality summary of videos, play an important role in the areas of video browsing, searching, categorisation, and indexing. An effective set of key frames should include major objects and events of the video sequence, and should contain minimum content redundancies. In this paper, an innovative key frame extraction method is proposed to select representative key frames for a video. By analysing the differences between frames and utilising the clustering technique, a set of key frame candidates (KFCs) is first selected at the shot level, and then the information within a video shot and between video shots is used to filter the candidate set to generate the final set of key frames. Experimental results on the TRECVID 2007 video dataset have demonstrated the effectiveness of our proposed key frame extraction method in terms of the percentage of the extracted key frames and the retrieval precision.

show abstract

Section: Related Workmentioning

confidence: 99%

Within and Between Shot Information Utilisation in Video Key Frame Extraction

Liu

Shyu

Chen

et al. 2011

J. Info. Know. Mgmt.

View full text Add to dashboard Cite

show abstract

“…Such spatially reduced images, once extracted, can be used for other applications beyond scene change detection, for example, the efficient comparison of video shots, automatic generation of compact documents, and nonlinear video browsing applications. Several fast algorithms to extract DC images from an MPEG compressed video using discrete cosine transform (DCT) DC coefficients in I type frame and motion compensated DCT DC coefficients in P or B type frames have already been proposed [9]- [11]. It has been demonstrated that even at such a low resolution, global image features useful for specific classes for content-based operations on MPEG compressed video streams are well preserved.…”

Section: Introductionmentioning

confidence: 97%

Key frame number assignment measuring content variations

Kim

Kwon

2012

2012 International Conference on ICT Convergence (ICTC)

View full text Add to dashboard Cite

Abstract² We propose a new and fast algorithm for assigning the number of key frames to video shots. After the entire video sequence is segmented into elementary content unit called shots and then the key frame number assignment is performed by calculating the accumulated value of CVF(content variation function). The proposed algorithm is based on the amount of content variations using DC images extracted from compressed video. By assigning the number of key frames to the shot that has the largest value of content function, one key frame is assigned at a time until you run out of given all key frames. The main advantage of our proposed method is that we do not need to use time-exhaustive computations in allocating the key frames over the shot and can perform it fully automatically.

show abstract

“…we know that several previous methods which are based on threshold [9,10] are very hard to estimate the total number of key frames for the entire sequence. Therefore, this method does not provide the controllability of the total key frame number according to the capacity of storage media.…”

Section: Simulationsmentioning

confidence: 99%

“…Such approximation requires only the motion vector information and DC values in the reference frames. Several algorithms to extract DC images from MPEG compressed video by using DCT DC coefficients in I type frame and motion compensated DCT DC coefficients in P or B type frame were already proposed [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Key Frame Assignment for Compr essed Video Based on DC Image Activity

Kim¹,

Lee²,

Kwon³

2011

Journal of Korea Multimedia Society

View full text Add to dashboard Cite

In this paper, we propose a new and fast method for assigning the number of key frames to each shot. At first we segment the entire video sequence into elementary content unit called shots and then the key frame allocation is performed by calculating the accumulated value of AF(activity function).The proposed algorithm is based on the amount of content variation using DC images extracted from compressed video. By assigning the number of key frames to the shot that has the largest value of content function, one key frame is assigned at a time until you run out of given all key frames. The main advantage of our proposed method is that we do not need to use time-exhaustive computations in allocating the key frames over the shot and can perform it fully automatically.

show abstract

Keyframe extraction based on kmeas results to adjacent DC images similarity

Cited by 7 publications

References 5 publications

Within and Between Shot Information Utilisation in Video Key Frame Extraction

Within and Between Shot Information Utilisation in Video Key Frame Extraction

Key frame number assignment measuring content variations

Key Frame Assignment for Compr essed Video Based on DC Image Activity

Contact Info

Product

Resources

About