{"title":"基于智能视频传感器架构的卡尔曼滤波车辆跟踪","authors":"I. Imelda, A. Harjoko, P. Nurwantoro","doi":"10.1109/ICITISEE.2018.8720947","DOIUrl":null,"url":null,"abstract":"Traffic information is needed to determine the cause of the accident. Problems arise when many traffic accidents or violations co-occur. Technical failures in delivering important frames also hinder the process of analyzing the video, which occurs due to disconnected network, limited bandwidth and CPU processing power. Besides, the size of the video to be processed at the same time slow the CPU down preventing the video from being treated. In this research, we propose Smart Video Sensor (SVS) resolve the missing frame issues. SVS is a video sensor recording images streaming frames for the frame. SVS extract only features of traffic objects and compress the video so that the data will be received faster and lighter. SVS also processes the primary data, so the other system is ready to use the features needed for further data processing. To demonstrate how well SVS works, we experimented it by tracking vehicles by type. This study uses 3 locations and 1000 frames in each area. The contribution of this paper is to produce a vehicle tracking model by type using Kalman Filter based SVS Architecture. The highest accuracy found for motorcycles is in Galeria (90.71%).","PeriodicalId":180051,"journal":{"name":"2018 3rd International Conference on Information Technology, Information System and Electrical Engineering (ICITISEE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Vehicle Tracking using Kalman Filter based on Smart Video Sensor Architecture\",\"authors\":\"I. Imelda, A. Harjoko, P. Nurwantoro\",\"doi\":\"10.1109/ICITISEE.2018.8720947\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Traffic information is needed to determine the cause of the accident. Problems arise when many traffic accidents or violations co-occur. Technical failures in delivering important frames also hinder the process of analyzing the video, which occurs due to disconnected network, limited bandwidth and CPU processing power. Besides, the size of the video to be processed at the same time slow the CPU down preventing the video from being treated. In this research, we propose Smart Video Sensor (SVS) resolve the missing frame issues. SVS is a video sensor recording images streaming frames for the frame. SVS extract only features of traffic objects and compress the video so that the data will be received faster and lighter. SVS also processes the primary data, so the other system is ready to use the features needed for further data processing. To demonstrate how well SVS works, we experimented it by tracking vehicles by type. This study uses 3 locations and 1000 frames in each area. The contribution of this paper is to produce a vehicle tracking model by type using Kalman Filter based SVS Architecture. The highest accuracy found for motorcycles is in Galeria (90.71%).\",\"PeriodicalId\":180051,\"journal\":{\"name\":\"2018 3rd International Conference on Information Technology, Information System and Electrical Engineering (ICITISEE)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 3rd International Conference on Information Technology, Information System and Electrical Engineering (ICITISEE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICITISEE.2018.8720947\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 3rd International Conference on Information Technology, Information System and Electrical Engineering (ICITISEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICITISEE.2018.8720947","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Vehicle Tracking using Kalman Filter based on Smart Video Sensor Architecture
Traffic information is needed to determine the cause of the accident. Problems arise when many traffic accidents or violations co-occur. Technical failures in delivering important frames also hinder the process of analyzing the video, which occurs due to disconnected network, limited bandwidth and CPU processing power. Besides, the size of the video to be processed at the same time slow the CPU down preventing the video from being treated. In this research, we propose Smart Video Sensor (SVS) resolve the missing frame issues. SVS is a video sensor recording images streaming frames for the frame. SVS extract only features of traffic objects and compress the video so that the data will be received faster and lighter. SVS also processes the primary data, so the other system is ready to use the features needed for further data processing. To demonstrate how well SVS works, we experimented it by tracking vehicles by type. This study uses 3 locations and 1000 frames in each area. The contribution of this paper is to produce a vehicle tracking model by type using Kalman Filter based SVS Architecture. The highest accuracy found for motorcycles is in Galeria (90.71%).