Video shot segmentation using singular value decomposition

Cernekova, Zuzana; Kotropoulos, Constantine; Pitas, Ioannis

doi:10.1109/icme.2003.1221613

Cited by 29 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shot boundary detection, sometimes also called as temporal video segmentation, completes the performance of identifying the transition between contiguous shot and subsequently separates a video stream file into different shots. Much work has been reported in this area and highly accurate results have been obtained such as in Albanese and Chianese (2004), Boccignone and Chianese (2005), Cernekova, Kotropoulos, and Pitas (2003), Dimitrova and Zhang (2002), Hanjalic (2002), Yuan, Li, Lin, and Zhang (2005). The second step is the key frame selection.…”

Section: Related Workmentioning

confidence: 96%

Automatic scene detection for advanced story retrieval

Zhu¹,

Liu²

2009

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 96%

Automatic scene detection for advanced story retrieval

Zhu¹,

Liu²

2009

Expert Systems with Applications

View full text Add to dashboard Cite

“…This work was quite complicated as it first detects the objects like faces of the repetitive TV anchors and then detect the stories by recognizing these faces. Other methods detect shots using singular value decomposition [11] and adaptive [12] threshold for similarity between the frames technique, supervised learning based SVM classifier to separate cuts from non-cuts [13]. [14] combine the training information (SVM) with global threshold approach by first detecting the shots using a threshold and then confirming the shots using SVM.…”

Section: Related Workmentioning

confidence: 99%

Semantic description of a video using representative frames

Jindal

Raman

2015

2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)

View full text Add to dashboard Cite

Analysis of a very long video and semantically describe the contents is a challenging task in computer vision. The present approaches such as video shot detection and summarization address this problem partially while maintaining the temporal coherency. To reduce the user efforts for seeing the whole video we have introduced a new technique which combines similar content irrespective of their presence at different time instants. In this approach, we automatically identify only the representative frames corresponding to similar scenes which were captured at different instants of time. We also provide the labels of the objects that are present in the representative frames along with the compact representation for the video. We achieve the task of semantic labelling of frames in a unified framework using a deep learning framework involving pre-trained features through a convolutional neural network. We show that the proposed approach is able to address the semantic labelling effectively as justified by the results obtained for videos of different scenes captured through different modalities.

show abstract

“…We made a performance comparison of our proposed algorithm with the original two-dimensional entropy model (original method), the well-known twin comparison method [4] , the edge change ratio method [5] , and singular value decomposition [12] . The results of performance comparison of shot boundaries detection on the TRECVID data set are given in Table 2, which shows that our proposed algorithm is robust on object and camera movements.…”

Section: System Performance Evaluationsmentioning

confidence: 99%

Two-dimensional entropy model for video shot partitioning

Zhu

Liu

2009

Sci. China Ser. F-Inf. Sci.

View full text Add to dashboard Cite

A shot presents a contiguous action recorded by an uninterrupted camera operation and frames within a shot keep spatio-temporal coherence. Segmenting a serial video stream file into meaningful shots is the first pass for the task of video analysis, content-based video understanding. In this paper, a novel scheme based on improved two-dimensional entropy is proposed to complete the partition of video shots. Firstly, shot transition candidates are detected using a two-pass algorithm: a coarse searching pass and a fine searching pass. Secondly, with the character of two-dimensional entropy of the image, correctly detected transition candidates are further classified into different transition types whereas those falsely detected shot breaks are distinguished and removed. Finally, the boundary of gradual transition can be precisely located by merging the characters of two-dimensional entropy of the image into the gradual transition. A large number of video sequences are used to test our system performance and promising results are obtained.video shot segmentation, two-dimensional entropy model, coarse-to-fine algorithm, content-based indexing and retrieval

show abstract

Video shot segmentation using singular value decomposition

Cited by 29 publications

References 10 publications

Automatic scene detection for advanced story retrieval

Automatic scene detection for advanced story retrieval

Semantic description of a video using representative frames

Two-dimensional entropy model for video shot partitioning

Contact Info

Product

Resources

About