2012
DOI: 10.1007/978-3-642-33783-3_45
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Abstract. The use of video segmentation as an early processing step in video analysis lags behind the use of image segmentation for image analysis, despite many available video segmentation methods. A major reason for this lag is simply that videos are an order of magnitude bigger than images; yet most methods require all voxels in the video to be loaded into memory, which is clearly prohibitive for even medium length videos. We address this limitation by proposing an approximation framework for streaming hier… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
197
1

Year Published

2013
2013
2021
2021

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 192 publications
(200 citation statements)
references
References 25 publications
2
197
1
Order By: Relevance
“…Note that following the merging sequence, we have an exact control on the desired number of regions unlike methods like GBH or Meanshift. SWA [8] GB [3] GBH [4] MeanShift [6] Nytström [7] StreamGBH [32] TBPT Figure 5. Results on the dataset of [31].…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Note that following the merging sequence, we have an exact control on the desired number of regions unlike methods like GBH or Meanshift. SWA [8] GB [3] GBH [4] MeanShift [6] Nytström [7] StreamGBH [32] TBPT Figure 5. Results on the dataset of [31].…”
Section: Resultsmentioning
confidence: 99%
“…Moreover, there are situations where the entire video is not available and batch processing is needed. We leave this task as future work noting that the Trajectory BPT algorithm can easily be adapted to a streaming scheme as the one discussed in [32], processing chunks of frames in a causal order to deal with video sequences of arbitrary length. Moreover, one of our future objectives is to develop efficient graph cut techniques to be used on the Trajectory BPT.…”
Section: Discussionmentioning
confidence: 99%
“…It iteratively merged nodes in a region graph to produce a hierarchical segmentation. To process arbitrary long video, Xu et al [5] proposed a streaming hierarchical video segmentation framework and instantiated HGB within this framework (SHGB). This method enforced a Markov assumption on the video stream, which leveraged ideas from data streams.…”
Section: Trends In Engineering and Technology (Nctet-2k17) Internatiomentioning
confidence: 99%
“…Some of the proposed approaches are unsupervised, e.g. region tracking [1], hierarchical graph model [2,3], multiple hypothesis tracking [4] and spatio-temporal based segmentation [5,6]. Unsupervised methods can only perform low-level video segmentation and can not provide semantic labels for the segments.…”
Section: Related Workmentioning
confidence: 99%