Video Summarisation for Surveillance and News Domain

Damnjanovic, Uros; Piatrik, Tomas; Djordjevic, Divna; Izquierdo, Ebroul

doi:10.1007/978-3-540-77051-0_11

Cited by 9 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Having a fixed constant cluster count is also not a good idea. Existing techniques [9], [13], and [14] based on eigengap will show similar poor performance. As shown in Table II, [3] does not work well when the scene is gradually changing although the performance is reasonable for cut transition as shown in Table III.…”

Section: A Quantitative Evaluation Of Cluster Detectionmentioning

confidence: 96%

“…Since normalized cuts [7] require prior information about the number of clusters and since the number of clusters is not fixed, we use eigengap [12] to automatically detect the number of clusters. Comparing with [7] is thus equivalent to comparing with [9], [10], and [13].…”

Section: A Quantitative Evaluation Of Cluster Detectionmentioning

confidence: 99%

“…However, these methods require prior information about the number of clusters, which is not always available and varies largely across different videos. Eigengap [12] can be used to predict the number of clusters [9], [13], [14]. However, this measure is not robust.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Framework for Robust Online Video Contrast Enhancement Using Modularity Optimization

Choudhury

Medioni

2012

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

We address the problem of video contrast enhancement. Existing techniques either do not exploit temporal information at all or do not exploit it correctly. This results in inconsistency that causes undesirable flash and flickering artifacts. Our method analyzes video streams and cluster frames that are similar to each other. Our method does not have omniscient information about the entire video sequence. It is an online process with a fixed delay. A sliding window mechanism successfully detects shot boundaries "on-the-fly" in a video. A graph-based technique called "modularity" performs automatic clustering of video frames without a priori information about clusters. For every cluster in the video, we extract key frames belonging to each cluster using eigen analysis and estimate enhancement parameters for only the key frame, then use these parameters to enhance frames belonging to that cluster, thus making our method robust. We evaluate the clustering method on video sequences from the TRECVid 2001 dataset and compare it with existing methods. We show reduction of flash artifacts in enhanced videos. We show statistically significant improvement in perceived video quality and validate that by conducting experiments on human observers. We show application of our clustering process to perform robust video segmentation.

show abstract

Section: A Quantitative Evaluation Of Cluster Detectionmentioning

confidence: 96%

Section: A Quantitative Evaluation Of Cluster Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Robust Online Video Contrast Enhancement Using Modularity Optimization

Choudhury

Medioni

2012

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…First, we compare proposed ATS algorithm with Spectral clustering (SC) and Hierarchical Agglomerative clustering (HAC) methods in the scene detection task using news and surveillance videos. Both methods have been successfully used for summarisation of video content and they were implemented in a same fashion as in [5] and [17]. The obtained results are compared with a manually created ground truth of semantic events appeared in videos.…”

Section: Experimental Evaluationmentioning

confidence: 99%

Hierarchical Summarisation of Video Using Ant-Tree Strategy

Piatrik

Izquierdo

2009

2009 Seventh International Workshop on Content-Based Multimedia Indexing

Self Cite

View full text Add to dashboard Cite

Video summarisation approaches have various fields of application, specifically related to organising, browsing and accessing large video databases. In this paper, the appropriateness of biologically inspired models to tackle these problems is discussed and suitable strategy for unsupervised video summarisation is derived. In our proposal, we model the ability of ants to build live structures with their bodies in order to discover, in a distributed and unsupervised way, a tree-structured organization and summarisation of the video data. An experimental evaluation validating the feasibility and the robustness of this novel approach is presented.

show abstract

“…For example, Shipman et al [2007] analyse low-level audio features to identify applause, cheering, excited speech, normal speech and music to plot a level of importance curve to represent the summarised content of the video. Damnjanovic et al [2007] segment video by analysing the image stream. Initially scenes are identified by means of shot change detection, and then the level of motion activity measured and equated with level of importance.…”

Section: Introductionmentioning

confidence: 99%

Elvis

Money

Agius

2010

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

Video summaries present the user with a condensed and succinct representation of the content of a video stream. Usually this is achieved by attaching degrees of importance to low-level image, audio and text features. However, video content elicits strong and measurable physiological responses in the user, which are potentially rich indicators of what video content is memorable to or emotionally engaging for an individual user. This paper proposes a technique which exploits such physiological responses to a given video stream by a given user to produce Entertainment-Led VIdeo Summaries (ELVIS). ELVIS is made up of five analysis phases which correspond to the analyses of five physiological response measures: electro-dermal response (EDR), heart rate (HR), blood volume pulse (BVP), respiration rate (RR), and respiration amplitude (RA). Through these analyses, the temporal locations of the most entertaining video sub-segments, as they occur within the video stream as a whole, are automatically identified. We also demonstrate how ELVIS can be integrated into video summary applications by presenting a media player that utilises ELVIS. The effectiveness of the ELVIS technique is verified through a statistical analysis of data collected during a set of user trials. Our analysis shows that ELVIS is significantly more effective than random selection in identifying the most entertaining video subsegments for content in the comedy, horror/comedy, and horror genres.

show abstract

Video Summarisation for Surveillance and News Domain

Cited by 9 publications

References 15 publications

A Framework for Robust Online Video Contrast Enhancement Using Modularity Optimization

A Framework for Robust Online Video Contrast Enhancement Using Modularity Optimization

Hierarchical Summarisation of Video Using Ant-Tree Strategy

Elvis

Contact Info

Product

Resources

About