{"title":"EmnDash:基于矢量激光投影的m序列虚线标记鲁棒高速空间跟踪","authors":"Ryota Nishizono, Tomohiro Sueishi, M. Ishikawa","doi":"10.1109/ISMAR-Adjunct51615.2020.00058","DOIUrl":null,"url":null,"abstract":"Camera pose estimation is commonly used for augmented reality, and it is currently expected to be integrated into sports assistant technologies. However, conventional methods face difficulties in simultaneously achieving fast estimation in milliseconds or less for sports, bright lighting environments of the outdoors, and capturing of large activity areas. In this paper, we propose EmnDash, M-sequence dashed markers on vector-based laser projection for an asynchronous high-speed dynamic camera, which provides both a graphical information display for humans and markers for the wearable high-speed camera with a high S/N ratio from a distance. One of the main notions is drawing a vector projection image with a single stroke using two dashed lines as markers. The other involves embedding the binary M-sequence as the length of each dashed line and its recognition method using locality. The recognition of the M-sequence dashed line requires only a one-shot image, which increases the robustness of tracking both in terms of camera orientation and occlusion. We experimentally confirm an increase in recognizable posture, sufficient tracking accuracy, and low-computational cost in the evaluation of a static camera. We also show good tracking ability and demonstrate immediate recovery from occlusion in the evaluation of a dynamic camera.","PeriodicalId":433361,"journal":{"name":"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"EmnDash: M-sequence Dashed Markers on Vector-based Laser Projection for Robust High-speed Spatial Tracking\",\"authors\":\"Ryota Nishizono, Tomohiro Sueishi, M. Ishikawa\",\"doi\":\"10.1109/ISMAR-Adjunct51615.2020.00058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Camera pose estimation is commonly used for augmented reality, and it is currently expected to be integrated into sports assistant technologies. However, conventional methods face difficulties in simultaneously achieving fast estimation in milliseconds or less for sports, bright lighting environments of the outdoors, and capturing of large activity areas. In this paper, we propose EmnDash, M-sequence dashed markers on vector-based laser projection for an asynchronous high-speed dynamic camera, which provides both a graphical information display for humans and markers for the wearable high-speed camera with a high S/N ratio from a distance. One of the main notions is drawing a vector projection image with a single stroke using two dashed lines as markers. The other involves embedding the binary M-sequence as the length of each dashed line and its recognition method using locality. The recognition of the M-sequence dashed line requires only a one-shot image, which increases the robustness of tracking both in terms of camera orientation and occlusion. We experimentally confirm an increase in recognizable posture, sufficient tracking accuracy, and low-computational cost in the evaluation of a static camera. We also show good tracking ability and demonstrate immediate recovery from occlusion in the evaluation of a dynamic camera.\",\"PeriodicalId\":433361,\"journal\":{\"name\":\"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISMAR-Adjunct51615.2020.00058\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISMAR-Adjunct51615.2020.00058","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
EmnDash: M-sequence Dashed Markers on Vector-based Laser Projection for Robust High-speed Spatial Tracking
Camera pose estimation is commonly used for augmented reality, and it is currently expected to be integrated into sports assistant technologies. However, conventional methods face difficulties in simultaneously achieving fast estimation in milliseconds or less for sports, bright lighting environments of the outdoors, and capturing of large activity areas. In this paper, we propose EmnDash, M-sequence dashed markers on vector-based laser projection for an asynchronous high-speed dynamic camera, which provides both a graphical information display for humans and markers for the wearable high-speed camera with a high S/N ratio from a distance. One of the main notions is drawing a vector projection image with a single stroke using two dashed lines as markers. The other involves embedding the binary M-sequence as the length of each dashed line and its recognition method using locality. The recognition of the M-sequence dashed line requires only a one-shot image, which increases the robustness of tracking both in terms of camera orientation and occlusion. We experimentally confirm an increase in recognizable posture, sufficient tracking accuracy, and low-computational cost in the evaluation of a static camera. We also show good tracking ability and demonstrate immediate recovery from occlusion in the evaluation of a dynamic camera.