A motion-tolerant dissolve detection algorithm

Su, Chih-Wen; Tyan, Hsiao-Rong; Liao, Hongbo; Chen, L.H.

doi:10.1109/icme.2002.1035555

Cited by 27 publications

(46 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We compared our algorithm with four popular approaches for gradual transition detection: Edge Change Ratio (ECR) [1], Standard Deviation of Pixel Intensities [2], Effective Average Gradient (EAG) [3], and Monotonous Intensity Change [4]. Table 1 shows results of them for the employed test set.…”

Section: Methodsmentioning

confidence: 99%

“…This is a criterion proposed in [4], where it is hypothesized that in a gradual transition, pixel intensities vary monotonously. The percentage of pixels with monotonously varying intensities is calculated and if it exceeds a certain threshold, a dissolve/fade transition is detected.…”

Section: Monotonous Intensity Changementioning

confidence: 99%

“…Values higher than a threshold indicate that the corresponding frames are identified as belonging to a transition area. A simple threshold estimation procedure, similarly to [4], can be followed to determine the required threshold value.…”

Section: Color Coherence Changementioning

confidence: 99%

“…C.W. Su et al [4] proposed a model to overcome the above problem. A sliding window that covers a number of frames is used, in order to observe the change of pixel intensities.…”

Section: Introductionmentioning

confidence: 99%

“…t and D G t were computed as described in section 2 and appropriate thresholds were estimated as in [4]. It should be noted that the results shown in Table 1 have been estimated considering gradual transitions only.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Gradual transition detection using color coherence and other criteria in a video shot meta-segmentation framework

Tsamoura

Mezaris

Kompatsiaris

2008

2008 15th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

Shot segmentation provides the basis for almost all high-level video content analysis approaches, validating it as one of the major prerequisites for efficient video semantic analysis, indexing and retrieval. The successful detection of both gradual and abrupt transitions is necessary to this end. In this paper a new gradual transition detection algorithm is proposed, that is based on novel criteria such as color coherence change that exhibit less sensitivity to local or global motion than previously proposed ones. These criteria, each of which could serve as a standalone gradual transition detection approach, are then combined using a machine learning technique, to result in a meta-segmentation scheme. Besides significantly improved performance, advantage of the proposed scheme is that there is no need for threshold selection, as opposed to what would be the case if any of the proposed features were used by themselves and as is typically the case in the relevant literature. Performance evaluation and comparison with four other popular algorithms reveals the effectiveness of the proposed technique.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Monotonous Intensity Changementioning

confidence: 99%

Section: Color Coherence Changementioning

confidence: 99%

“…C.W. Su et al [4] proposed a model to overcome the above problem. A sliding window that covers a number of frames is used, in order to observe the change of pixel intensities.…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations