{"title":"Driver's Seat Belt Detection in Crossroad Based on Gradient Orientation","authors":"Dian Yu, Hong Zheng, Cao Liu","doi":"10.1109/ISCC-C.2013.65","DOIUrl":null,"url":null,"abstract":"Seat belt detection is one of the important detecting functions and is widely needed in the field of intelligent transportation system. However, research for which is still limited in terms of the increasing requirements at present. In this paper, one algorithm for detecting vehicle seat belts on road is proposed. And according to the method discussed in this paper, a type of feature based on gradient orientation is employed to describe and detect seat belts. After the image pre-processing, the front window location and the human face detecting, this feature is finally extracted in the selected region and the conclusion is given by counting the seat belt feature in the area which close to the right side of the detected human face area. Another approach is also designed in case that the human face detection fails. Tests on high-definition vehicle images show that the proposed algorithm is capable of extracting belt-feature under difference circumstances and is also effective to tell whether the driver has fastened its seat belt.","PeriodicalId":313511,"journal":{"name":"2013 International Conference on Information Science and Cloud Computing Companion","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 International Conference on Information Science and Cloud Computing Companion","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCC-C.2013.65","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
Seat belt detection is one of the important detecting functions and is widely needed in the field of intelligent transportation system. However, research for which is still limited in terms of the increasing requirements at present. In this paper, one algorithm for detecting vehicle seat belts on road is proposed. And according to the method discussed in this paper, a type of feature based on gradient orientation is employed to describe and detect seat belts. After the image pre-processing, the front window location and the human face detecting, this feature is finally extracted in the selected region and the conclusion is given by counting the seat belt feature in the area which close to the right side of the detected human face area. Another approach is also designed in case that the human face detection fails. Tests on high-definition vehicle images show that the proposed algorithm is capable of extracting belt-feature under difference circumstances and is also effective to tell whether the driver has fastened its seat belt.