Summarisation of surveillance videos by key-frame selection

Yang, Yan; Dadgostar, Farhad; Sanderson, Conrad; Lovell, Brian C.

doi:10.1109/icdsc.2011.6042925

Cited by 14 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lue et al use this idea to create a visualization of news videos to summarize the important stories in a day [40]. Similarly, Yang et al identify key frames in surveillance videos to quickly summarise the events in a video [74]. In our work, we identify key frames in a cell's development to summarize it.…”

Section: Image Snippetsmentioning

confidence: 99%

Aardvark: Composite Visualizations of Trees, Time-Series, and Images

Lange,

Judson-Torres,

Zangle

et al. 2024

Preprint

View full text Add to dashboard Cite

How do cancer cells grow, divide, proliferate and die? How do drugs influence these processes? These are difficult questions that we can attempt to answer with a combination of time-series microscopy experiments, classification algorithms, and data visualization. However, collecting this type of data and applying algorithms to segment and track cells and construct lineages of proliferation is error-prone; and identifying the errors can be challenging since it often requires cross-checking multiple data types. Similarly, analyzing and communicating the results necessitates synthesizing different data types into a single narrative.State-of-the-art visualization methods for such data use independent line charts, tree diagrams, and images in separate views. However, this spatial separation requires the viewer of these charts to combine the relevant pieces of data in memory.To simplify this challenging task, we describe design principles for weaving cell images, time-series data, and tree data into a cohesive visualization. Our design principles are based on choosing a primary data type that drives the layout and integrates the other data types into that layout. We then introduce Aardvark, a system that uses these principles to implement novel visualization techniques. Based on Aardvark, we demonstrate the utility of each of these approaches for discovery, communication, and data debugging in a series of case studies.

show abstract

Section: Image Snippetsmentioning

confidence: 99%

Aardvark: Composite Visualizations of Trees, Time-Series, and Images

Lange,

Judson-Torres,

Zangle

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Local maxima are extracted using an iterative frame deleting strategy. The remaining frames are treated as key-frame [2]. …”

Section: …(4)mentioning

confidence: 99%

“…Suppose T 2 is the global threshold, compare C i with T 2 , if C i > T 2 , it means that this frame changes a lot in relation to the reference frame. If C i < T 2 , it means that the current frame is similar to the reference frame. Take the next frame as the current frame and repeat steps above until the last frame.…”

Section: …(32)mentioning

confidence: 99%

Review of Keyframe Extraction Techniques for Video Summarization

Deshpande¹,

Bamnote²,

Patil³

et al. 2018

IJCA

View full text Add to dashboard Cite

Video summarization methods tries to capture main parts, scenes and objects from specified video to have better video analysis. Two main goals of video summarization are deletion of redundant frames and extracting key frames from video. Video summarization can use different statistical measures such as mean, kurtosis and skewness for comparing each frame with next frame to calculate key frame. Key frames are crucial frames in the video. There are different methods to extract key frames from video and some of them are compared in this paper. The frame which satisfies threshold value will be considered as key frame and such key frames will then combined to form short summary.

show abstract

“…Proposed system presentsefficient video knowledge extraction, especially forsurveillance cases. Yang,Dadgostar [10] et al proposed two novel techniques for automaticsummarisation of lengthy surveillance videos, based on selectionof frames containing scenes most informative for rapid perusaland interpretation by humans.Almeida, Torres [11] et al suggested that themethod is based on bothexploiting visual features extracted from the video stream andon using a simple and fast algorithm to summarize the videocontent.Panchal, Merchant [12] et al introduce a proposed method to detect scene based on motionvector and occurrence rate of shot boundaries in video. Inwhich, motion vectors weights and directions addresses exactscene of video with prior action on occurrence rate of shotboundaries of video, it is possible to differentiate two scenes in amovie or video.…”

Section: Related Workmentioning

confidence: 99%

An Effective Method of Video Segmentation and Summarization for Surveillance

Pranjal¹,

Lakhdive²,

Vasave³

et al. 2014

IJCA

View full text Add to dashboard Cite

In today's world, video surveillance has become an integral part of investigation system. Video Segmentation and Summarization plays a crucial role in the field of Video analysis. The paper presents an approach that helps in extracting the movable segments from a large stable video.The system takes the video as input and extracts the movements from the video and identifies the time-intervals. Initially frames (images) are extracted from the video and compared consecutively. If some movements are detected then the movement signatures (start timeend time) are stored. Based on signaturesthe segmented and summarized video is generated. The result shows substantial improvement in video summarization process.

show abstract

Summarisation of surveillance videos by key-frame selection

Cited by 14 publications

References 22 publications

Aardvark: Composite Visualizations of Trees, Time-Series, and Images

Aardvark: Composite Visualizations of Trees, Time-Series, and Images

Review of Keyframe Extraction Techniques for Video Summarization

An Effective Method of Video Segmentation and Summarization for Surveillance

Contact Info

Product

Resources

About