Multi‐camera video synopsis of a geographic scene based on optimal virtual viewpoint

GAN based efficient foreground extraction and HGWOSA based optimization for video synopsis generation

Digital Signal Processing ◽

10.1016/j.dsp.2021.102988 ◽

2021 ◽

Vol 111 ◽

pp. 102988

Author(s):

Subhankar Ghatak ◽

Suvendu Rup ◽

Himansu Didwania ◽

M.N.S. Swamy

Keyword(s):

Foreground Extraction ◽

Video Synopsis

Download Full-text

Multicamera Joint Video Synopsis

IEEE Transactions on Circuits and Systems for Video Technology ◽

10.1109/tcsvt.2015.2430692 ◽

2016 ◽

Vol 26 (6) ◽

pp. 1058-1069 ◽

Cited By ~ 13

Author(s):

Jianqing Zhu ◽

Shengcai Liao ◽

Stan Z. Li

Keyword(s):

Video Synopsis

Download Full-text

Spectrum Analysis-Based Traffic Video Synopsis

Journal of Signal Processing Systems ◽

10.1007/s11265-018-1345-z ◽

2018 ◽

Vol 90 (8-9) ◽

pp. 1257-1267 ◽

Cited By ~ 1

Author(s):

Zhe Chen ◽

Guofang Lv ◽

Li Lv ◽

Tanghuai Fan ◽

Huibin Wang

Keyword(s):

Spectrum Analysis ◽

Video Synopsis ◽

Traffic Video

Download Full-text

Video Synopsis Generation Using GPGPU

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.433-435.297 ◽

2013 ◽

Vol 433-435 ◽

pp. 297-300

Author(s):

Zong Yue Wang

Keyword(s):

Parallel Computing ◽

Original Video ◽

Generation Efficiency ◽

Generation Algorithm ◽

Video Representation ◽

Gpu Parallel Computing ◽

Video Synopsis ◽

Video Summaries

Video summaries provide a compact video representation preserving the essential activities of the original video, but the summaries may be confusing when mixing different activities together. Summaries Clustered methodology, showing similar activities simultaneously, enables to view much easier and more efficiently. However, it is very time consuming in generating summaries, especially in calculating motion distance and collision cost. To improve the efficiency of generating summaries, a parallel video synopsis generation algorithm is proposed based on GPGPU. The experiment result shows generation efficiency is improved greatly through GPU parallel computing. The acceleration radio can reach at 5.75 when data size is above 1600*960*30000.

Download Full-text

Object-Based Surveillance Video Synopsis Using Genetic Algorithm

Applied Video Processing in Surveillance and Monitoring Systems - Advances in Multimedia and Interactive Technologies ◽

10.4018/978-1-5225-1022-2.ch009 ◽

2017 ◽

pp. 193-219

Author(s):

Shefali Gandhi ◽

Tushar V. Ratanpara

Keyword(s):

Genetic Algorithm ◽

Background Subtraction ◽

Moving Objects ◽

Time Lapse ◽

Original Video ◽

Surveillance Video ◽

Time Activity ◽

Video Synopsis ◽

Object Based ◽

Poisson Image Editing

Video synopsis provides representation of the long surveillance video, while preserving the essential activities of the original video. The activity in the original video is covered into a shorter period by simultaneously displaying multiple activities, which originally occurred at different time segments. As activities are to be displayed in different time segments than original video, the process begins with extracting moving objects. Temporal median algorithm is used to model background and foreground objects are detected using background subtraction method. Each moving object is represented as a space-time activity tube in the video. The concept of genetic algorithm is used for optimized temporal shifting of activity tubes. The temporal arrangement of tubes which results in minimum collision and maintains chronological order of events is considered as the best solution. The time-lapse background video is generated next, which is used as background for the synopsis video. Finally, the activity tubes are stitched on the time-lapse background video using Poisson image editing.

Download Full-text