Kyle Lindgren, Sarah Leung, W. Nothwang, E. J. Shamwell
{"title":"BooM-Vio:通过无监督深度学习的绝对轨迹估计的自引导单目视觉惯性里程计","authors":"Kyle Lindgren, Sarah Leung, W. Nothwang, E. J. Shamwell","doi":"10.1109/ICAR46387.2019.8981570","DOIUrl":null,"url":null,"abstract":"Machine learning has emerged as an extraordinary tool for solving many computer vision tasks by extracting and correlating meaningful features from high dimensional inputs in ways that often exceed the best human-derived modeling efforts. However, the area of vision-aided localization remains diverse with many traditional, model-based approaches (i.e. filtering- or nonlinear least- squares- based) often outperforming deep, model-free approaches. In this work, we present Bootstrapped Monocular VIO (BooM), a scaled monocular visual-inertial odometry (VIO) solution that leverages the complex data association ability of model-free approaches with the ability to exploit known geometric dynamics with model-based approaches. Our end-to-end, unsupervised deep neural network simultaneously learns to perform visual-inertial odometry and estimate scene depth while scale is enforced through a loss signal computed from position change magnitude estimates from traditional methods. We evaluate our network against a state-of-the-art (SoA) approach on the KITTI driving dataset as well as a micro aerial vehicle (MAV) dataset that we collected in the AirSim simulation environment. We further demonstrate the benefits of our combined approach through robustness tests on degraded trajectories.","PeriodicalId":6606,"journal":{"name":"2019 19th International Conference on Advanced Robotics (ICAR)","volume":"71 1","pages":"516-522"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"BooM-Vio: Bootstrapped Monocular Visual-Inertial Odometry with Absolute Trajectory Estimation through Unsupervised Deep Learning\",\"authors\":\"Kyle Lindgren, Sarah Leung, W. Nothwang, E. J. Shamwell\",\"doi\":\"10.1109/ICAR46387.2019.8981570\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Machine learning has emerged as an extraordinary tool for solving many computer vision tasks by extracting and correlating meaningful features from high dimensional inputs in ways that often exceed the best human-derived modeling efforts. However, the area of vision-aided localization remains diverse with many traditional, model-based approaches (i.e. filtering- or nonlinear least- squares- based) often outperforming deep, model-free approaches. In this work, we present Bootstrapped Monocular VIO (BooM), a scaled monocular visual-inertial odometry (VIO) solution that leverages the complex data association ability of model-free approaches with the ability to exploit known geometric dynamics with model-based approaches. Our end-to-end, unsupervised deep neural network simultaneously learns to perform visual-inertial odometry and estimate scene depth while scale is enforced through a loss signal computed from position change magnitude estimates from traditional methods. We evaluate our network against a state-of-the-art (SoA) approach on the KITTI driving dataset as well as a micro aerial vehicle (MAV) dataset that we collected in the AirSim simulation environment. We further demonstrate the benefits of our combined approach through robustness tests on degraded trajectories.\",\"PeriodicalId\":6606,\"journal\":{\"name\":\"2019 19th International Conference on Advanced Robotics (ICAR)\",\"volume\":\"71 1\",\"pages\":\"516-522\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 19th International Conference on Advanced Robotics (ICAR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAR46387.2019.8981570\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 19th International Conference on Advanced Robotics (ICAR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAR46387.2019.8981570","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
BooM-Vio: Bootstrapped Monocular Visual-Inertial Odometry with Absolute Trajectory Estimation through Unsupervised Deep Learning
Machine learning has emerged as an extraordinary tool for solving many computer vision tasks by extracting and correlating meaningful features from high dimensional inputs in ways that often exceed the best human-derived modeling efforts. However, the area of vision-aided localization remains diverse with many traditional, model-based approaches (i.e. filtering- or nonlinear least- squares- based) often outperforming deep, model-free approaches. In this work, we present Bootstrapped Monocular VIO (BooM), a scaled monocular visual-inertial odometry (VIO) solution that leverages the complex data association ability of model-free approaches with the ability to exploit known geometric dynamics with model-based approaches. Our end-to-end, unsupervised deep neural network simultaneously learns to perform visual-inertial odometry and estimate scene depth while scale is enforced through a loss signal computed from position change magnitude estimates from traditional methods. We evaluate our network against a state-of-the-art (SoA) approach on the KITTI driving dataset as well as a micro aerial vehicle (MAV) dataset that we collected in the AirSim simulation environment. We further demonstrate the benefits of our combined approach through robustness tests on degraded trajectories.