Surveillance Video Synopsis Based on Moving Object Matting Using Non- interactive GrabCut
نویسندگان
چکیده
An algorithm of surveillance video synopsis is presented in this paper. At first, the detection method of moving object for surveillance video is proposed. Then the ROI (Region of Interest) of moving object is extracted and a noninteractive matting algorithm of moving object based on GrabCut is presented. These matting moving objects are placed without overlapping in a background image, so a frame that several moving objects have been placed in a background image can be obtained. Finally, a series of these frame images can be obtained in timeline and a single camera surveillance video synopsis can be formed. The experimental results show that our detection method of moving object is superior to those methods such as Gaussian mixture model, background subtraction, frame difference method and Li’s method. The synopsis obtained contains all objects appeared in surveillance video and is a concise expression for original video.
منابع مشابه
Video Matting Using Motion Extended Grabcut
GrabCut is perhaps the most powerful semi-automatic algorithm for matting presented to date. In its existing form, it is not suitable for video object segmentation. This paper considers major extensions that make it suitable for this purpose. A method for initialising matting without user intervention is presented, followed by a more robust data model using a Mean Shift algorithm to control mod...
متن کاملSurveillance Video Synopsis in GIS
Surveillance videos contain a considerable amount of data, wherein interesting information to the user is sparsely distributed. Researchers construct video synopsis that contain key information extracted from a surveillance video for efficient browsing and analysis. Geospatial–temporal information of a surveillance video plays an important role in the efficient description of video content. Mea...
متن کاملAffinity Matting for Pixel-accurate Fin Shape Recovery from Great White Shark Imagery
The objective of this paper is to obtain pixel-accurate reconstructions of white shark fins given automatically generated coarse pre-segmentations. Reconstruction performance is compared for affinity matting, colour matting and GrabCut against expert annotated ground truth for a test-set of 120 fin images taken in the wild. For the present domain, we find affinity matting able to most accuratel...
متن کاملInteractive Video Object Segmentation in the Wild
In this paper we present our system for human-in-theloop video object segmentation. The backbone of our system is a method for one-shot video object segmentation [3]. While fast, this method requires an accurate pixel-level segmentation of one (or several) frames as input. As manually annotating such a segmentation is impractical, we propose a deep interactive image segmentation method, that ca...
متن کاملThe Role of Avatar in Interactive Fictional World of Video Games
In third-person video games, players are able to move and progress in the interactive world of the game while watching their avatar from an external point of view. The purpose of this paper is to investigate the role of avatar in the interactive imaginary world of video games using double vision theory. This article is based on descriptive-analytical methods and the use of library data and imag...
متن کامل