A novel approach for robust surveillance video content abstraction

Authors:
LiMin Wang;Yirui Wu;Zhiyuan Tian;Zailiang Sun;Tong Lu
Affiliations:
State Key Lab. for Novel Software Technology, Nanjing University, China;State Key Lab. for Novel Software Technology, Nanjing University, China;State Key Lab. for Novel Software Technology, Nanjing University, China;State Key Lab. for Novel Software Technology, Nanjing University, China;State Key Lab. for Novel Software Technology, Nanjing University, China and Jiangyin Institute of Information Technology of Nanjing University, China
Venue:
PCM'10 Proceedings of the Advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II
Year:
2010

Citing 11
Cited 0

An integrated scheme for object-based video abstraction

MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
Exploring Video Structure Beyond The Shots

ICMCS '98 Proceedings of the IEEE International Conference on Multimedia Computing and Systems
Multi-Level Video Representation with Application to Keyframe Extraction

MMM '04 Proceedings of the 10th International Multimedia Modelling Conference
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Schematic storyboarding for video visualization and editing

ACM SIGGRAPH 2006 Papers
Using Dependent Regions for Object Categorization in a Generative Framework

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Video Mosaics for Virtual Environments

IEEE Computer Graphics and Applications
Event Detection and Clustering for Surveillance Video Summarization

WIAMIS '08 Proceedings of the 2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services
A new approach for overlay text detection and extraction from complex video scene

IEEE Transactions on Image Processing
A novel video key-frame-extraction algorithm based on perceived motion energy model

IEEE Transactions on Circuits and Systems for Video Technology
A comprehensive method for multilingual video text detection, localization, and extraction

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Efficient video content analysis is an unsolved problem, especially for real-life surveillance videos due to their low resolution and illustration variations. A novel framework to efficiently and robustly convert a surveillance video clip into one abstraction image containing the integrated contour of interested objects is proposed. It has the following novelties: 1) an improved w-SIFT algorithm for Y-axis frames offset calculation, 2) a trapezoid-based compensation algorithm for X-axis perspective distortion correction, and 3) an incremental video content integration approach. Experimental results show that our method is robust for real-life low resolution videos and efficient for real-time analysis.