{"title":"Video frame segmentation by using newton's law of gravity","authors":"A. Ghasemi, C. R. Ravi Kumar","doi":"10.1109/CCIP.2016.7802847","DOIUrl":null,"url":null,"abstract":"In this paper, a novel video frame segmentation algorithm based on Newton's law of gravity is presented, which is called as Object feature based Gravitational Video Segmentation Algorithm (OGVSA).The proposed OGVSA uses spatial information, color and texture information of video frame to partition the object in video frame into homogenous and semi-compact segments. We introduce new operator called “escape” such that it is the concept of escape velocity in physics and moreover the proposed algorithm has the ability to search the object for finding the best regions that are suitable for that object. Experiments on standard dataset as well as SIVA reported show that OGVSA outperforms the reported algorithms.","PeriodicalId":354589,"journal":{"name":"2016 Second International Conference on Cognitive Computing and Information Processing (CCIP)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 Second International Conference on Cognitive Computing and Information Processing (CCIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCIP.2016.7802847","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
In this paper, a novel video frame segmentation algorithm based on Newton's law of gravity is presented, which is called as Object feature based Gravitational Video Segmentation Algorithm (OGVSA).The proposed OGVSA uses spatial information, color and texture information of video frame to partition the object in video frame into homogenous and semi-compact segments. We introduce new operator called “escape” such that it is the concept of escape velocity in physics and moreover the proposed algorithm has the ability to search the object for finding the best regions that are suitable for that object. Experiments on standard dataset as well as SIVA reported show that OGVSA outperforms the reported algorithms.