A fast shot matching strategy for detecting duplicate sequences in a television stream

In this paper, we propose a new method to search different instances of a video sequence inside a long video and/or video collection. The proposed method is robust to view point and illumination changes which may occur since the sequences are captured in different times with different cameras, and to the differences in the order and the number of frames in the sequences which may occur due to editing. The algorithm does not require any query to be given for searching, and finds all repeating video sequences inside a long video in a fully automatic way. First, the frames in a video are ranked according to their similarity on the distribution of salient points and colour values. Then, a tree based approach is used to seek for the repetitions of a video sequence if there is any. Results are provided on a full length feature movie, Run Lola Run and on commercials of TRECVID 2004 news video corpus.

show abstract

“…al. [18] propose a method based on signatures generated from DCT of frames and hashing. First of all, shots are extracted from videos.…”

Section: Related Workmentioning

confidence: 99%

Searching for repeated video sequences

Can

Duygulu

2007

Proceedings of the International Workshop on Workshop on Multimedia Information Retrieval

View full text Add to dashboard Cite

show abstract

“…Current methods for solving the video retrieval/localization problem can be grouped in two main groups with distinct approaches: (i) computation of video signatures after temporal video segmentation, as described in [5], [6]; and (ii) use of matching algorithms after transformation of the video frame content into a feature vector or symbolic representation, as described in [4], [7].…”

Section: Introductionmentioning

confidence: 99%

Searching for Near-Duplicate Video Sequences from a Scalable Sequence Aligner

Sestrem¹,

Patrocínio²,

Guimarães

et al. 2013

2013 IEEE International Symposium on Multimedia

View full text Add to dashboard Cite

Abstract-Near-duplicate video sequence identification consists in identifying real positions of a specific video clip in a video stream stored in a database. To address this problem, we propose a new approach based on a scalable sequence aligner borrowed from proteomics. Sequence alignment is performed on symbolic representations of features extracted from the input videos, based on an algorithm originally applied to bio-informatics. Experimental results demonstrate that our method performance achieved 94% recall with 100% precision, with an average searching time of about 1 second.

show abstract

“…Alike the method proposed in this paper, their major approach is to take a two step detection strategy; fast but rough detection in the first step, and slow but accurate confirmation in the second step. Sekimoto hash indices of features represented by DCT coefficients [5]. Yamagishi et al proposes a method that compares frames by normalized cross correlation (NCC) of their intensity histograms, accelerated by the SR-Tree indexing method [6].…”

Section: Introductionmentioning

confidence: 99%

Genre-Adaptive Near-Duplicate Video Segment Detection

Ide

Noda

Takahashi

et al. 2007

Multimedia and Expo, 2007 IEEE International Conference On

View full text Add to dashboard Cite

This paper proposes a fast and accurate method to detect all nearduplicate segments in a video stream. To reduce the computation time while ensuring the detection accuracy equivalent to that by brute-force frame-by-frame comparison, a two-step detection method is proposed; a fast but rough detection applied in a compressed feature vector space spanned by the result of a PCA, followed by confirmation of candidates in the original high dimension space. The results show that the proposed method accelerates the detection by more than 1,000 times while maintaining the detection accuracy. We also propose an entropy-based pixel selection scheme to generate feature vectors optimized for comparison of video segments within programs with mostly common pictures. The results show that the proposed scheme eliminates the false positives drastically, which should lead to even faster detection.

show abstract

A fast shot matching strategy for detecting duplicate sequences in a television stream

Cited by 31 publications

References 11 publications

Searching for repeated video sequences

Searching for repeated video sequences

Searching for Near-Duplicate Video Sequences from a Scalable Sequence Aligner

Genre-Adaptive Near-Duplicate Video Segment Detection

Contact Info

Product

Resources

About