Michel Heinemann, Jonas Herzfeld, M. J. Sliwinski, Johannes Hinckeldeyn, J. Kreutzfeldt
{"title":"六种用于机器人的消费级立体深度相机的计量和应用相关比较","authors":"Michel Heinemann, Jonas Herzfeld, M. J. Sliwinski, Johannes Hinckeldeyn, J. Kreutzfeldt","doi":"10.1109/ROSE56499.2022.9977421","DOIUrl":null,"url":null,"abstract":"Consumer grade depth cameras are important devices to enable robots and unmanned vehicles to perceive their environments. Three major technologies are relevant for those devices: Time-of-Flight, structured light and stereo vision. Stereo cameras in particular have conquered the market in recent years, with Intel's D-series systems leading the way. Besides stereo cameras from Intel, there are many models from other manufacturers, but it has not yet been investigated how these cameras perform in comparison. This paper proposes and applies methods to measure the performance of depth cameras in a metrological way as well as with a focus on the use in robotics. Six stereo depth cameras are tested and compared. In addition, a real world benchmark test and a qualitative evaluation of the accompanying software and documentation is done. A clear recommendation is given in the end.","PeriodicalId":265529,"journal":{"name":"2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A metrological and application-related comparison of six consumer grade stereo depth cameras for the use in robotics\",\"authors\":\"Michel Heinemann, Jonas Herzfeld, M. J. Sliwinski, Johannes Hinckeldeyn, J. Kreutzfeldt\",\"doi\":\"10.1109/ROSE56499.2022.9977421\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Consumer grade depth cameras are important devices to enable robots and unmanned vehicles to perceive their environments. Three major technologies are relevant for those devices: Time-of-Flight, structured light and stereo vision. Stereo cameras in particular have conquered the market in recent years, with Intel's D-series systems leading the way. Besides stereo cameras from Intel, there are many models from other manufacturers, but it has not yet been investigated how these cameras perform in comparison. This paper proposes and applies methods to measure the performance of depth cameras in a metrological way as well as with a focus on the use in robotics. Six stereo depth cameras are tested and compared. In addition, a real world benchmark test and a qualitative evaluation of the accompanying software and documentation is done. A clear recommendation is given in the end.\",\"PeriodicalId\":265529,\"journal\":{\"name\":\"2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE)\",\"volume\":\"71 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ROSE56499.2022.9977421\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROSE56499.2022.9977421","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A metrological and application-related comparison of six consumer grade stereo depth cameras for the use in robotics
Consumer grade depth cameras are important devices to enable robots and unmanned vehicles to perceive their environments. Three major technologies are relevant for those devices: Time-of-Flight, structured light and stereo vision. Stereo cameras in particular have conquered the market in recent years, with Intel's D-series systems leading the way. Besides stereo cameras from Intel, there are many models from other manufacturers, but it has not yet been investigated how these cameras perform in comparison. This paper proposes and applies methods to measure the performance of depth cameras in a metrological way as well as with a focus on the use in robotics. Six stereo depth cameras are tested and compared. In addition, a real world benchmark test and a qualitative evaluation of the accompanying software and documentation is done. A clear recommendation is given in the end.