Abstract
The precise measuring of vehicle location has been a critical task in enhancing the autonomous driving in terms of intelligent decision making and safe transportation. Internet of Vehicles (IoV) is an important infrastructure in support of autonomous driving, allowing real-time road information exchanging and sharing for localizing vehicles. Global positioning System (GPS) is widely used in the traditional IoV system. GPS is unable to meet the key application requirements of autonomous driving due to meter level error and signal deterioration. In this article, we propose a novel solution, named Semi-Direct Monocular Visual-Inertial Odometry using Point and Line Features (SDMPL-VIO) for precise vehicle localization. Our SDMPL-VIO model takes advantage of a low-cost Inertial Measurement Unit (IMU) and monocular camera, using them as the sensor to acquire the surrounding environmental information. Visual-Inertial Odometry (VIO), taking into account both point and line features, is proposed, which is able to deal with both weak texture and dynamic environment. We use a semi-direct method to deal with keyframes and non-keyframes, respectively. Dual sliding window mechanisms can effectively fuse point-line and IMU information. To evaluate our SDMPL-VIO system model, we conduct extensive experiments on both an indoor dataset (i.e., EuRoC) and an outdoor dataset (i.e., KITTI) from the real-world applications, respectively. The experimental results show that the accuracy of SDMPL-VIO proposed by us is better than the mainstream VIO system at present. Especially in the weak texture of the datasets, fast-moving datasets, and other challenging datasets, SDMPL-VIO has a relatively high robustness.
- Mehiddin Albaali and Roger Fletcher. 1985. Variational methods for non-linear least-squares. Journal of the Operational Research Society 36, 5 (1985), 405–421.Google Scholar
Cross Ref
- Guillaume Bresson, Thomas Feraud, Romuald Aufrere, Paul Checchin, and Roland Chapuis. 2015. Real-time monocular slam with low memory requirements. IEEE Transactions on Intelligent Transportation Systems 16, 4 (2015), 1827–1839.Google Scholar
Digital Library
- Michael Burri, Janosch Nikolic, Pascal Gohl, Thomas Schneider, Joern Rehder, Sammy Omari, Markus Achtelik, and Roland Siegwart. 2016. The EuRoC micro aerial vehicle datasets. The International Journal of Robotics Research 35, 10 (2016), 1157–1163. Google Scholar
Digital Library
- Alejo Concha, Giuseppe Loianno, Vijay Kumar, and Javier Civera. 2016. Visual-inertial direct SLAM. In 2016 IEEE International Conference on Robotics and Automation. 1331–1338.Google Scholar
Digital Library
- Christian Forster, Luca Carlone, Frank Dellaert, and Davide Scaramuzza. 2015. On-manifold preintegration for real-time visual-inertial odometry. IEEE Transactions on Robotics 33, 1 (2015), 1–21. Google Scholar
Digital Library
- Christian Forster, Zichao Zhang, Michael Gassner, Manuel Werlberger, and Davide Scaramuzza. 2017. SVO: Semidirect visual odometry for monocular and multicamera systems. IEEE Transactions on Robotics 33, 2 (2017), 249–265. Google Scholar
Digital Library
- Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. 2013. Vision meets robotics: The KITTI dataset. The International Journal of Robotics Research 32, 11 (2013), 1231–1237. Google Scholar
Digital Library
- Ruben Gomezojeda and Javier Gonzalezjimenez. 2016. Robust stereo visual odometry through a probabilistic combination of points and line segments. In 2016 IEEE International Conference on Robotics and Automation. 2521–2526.Google Scholar
- Gottfried Graber, Thomas Pock, and Horst Bischof. 2011. Online 3D reconstruction using convex optimization. In 2011 IEEE International Conference on Computer Vision Workshops. 708–711.Google Scholar
Cross Ref
- Chunzhao Guo, Kiyosumi Kidono, Junichi Meguro, Yoshiko Kojima, Masaru Ogawa, and Takashi Naito. 2016. A low-cost solution for automatic lane-level map generation using conventional in-car sensors. IEEE Transactions on Intelligent Transportation Systems 17, 8 (2016), 2355–2366.Google Scholar
Digital Library
- Yijia He, Ji Zhao, Yue Guo, Wenhao He, and Kui Yuan. 2018. PL-VIO: Tightly-coupled monocular visual-inertial odometry using point and line features. Sensors 18, 4 (2018), 1159.Google Scholar
Cross Ref
- Manuel Hofer, Michael Maurer, and Horst Bischof. 2015. Line3D: Efficient 3D scene abstraction for the built environment. In German Conference on Pattern Recognition. 237–248.Google Scholar
Cross Ref
- Georg Klein and D. W. Murray. 2007. Parallel tracking and mapping for small AR workspaces. In 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. 225–234. Google Scholar
Digital Library
- Xianglong Kong, Wenqi Wu, Lilian Zhang, and Yujie Wang. 2015. Tightly-coupled stereo visual-inertial navigation using point and line features. Sensors 15, 6 (2015), 12816–12833.Google Scholar
Cross Ref
- Stefan Leutenegger, Simon Lynen, Michael Bosse, Roland Siegwart, and Paul Furgale. 2014. Keyframe-based visual-inertial odometry using nonlinear optimization. International Journal of Robotics Research 34, 3 (2014), 314–334. Google Scholar
Digital Library
- Xiaohu Lin, Fuhong Wang, Lei Guo, and Wanwei Zhang. 2019. An automatic key-frame selection method for monocular visual odometry of ground vehicle. IEEE Access 7 (2019), 70742–70754.Google Scholar
Cross Ref
- Yanqing Liu, Dongdong Yang, Jiamao Li, Yuzhang Gu, Jiatian Pi, and Xiaolin Zhang. 2018. Stereo visual-inertial SLAM with points and lines. IEEE Access 6 (2018), 69381–69392.Google Scholar
Cross Ref
- Lupton and Sukkarieh. 2012. Visual-inertial-aided navigation for high-dynamic motion in built environments without initial conditions. IEEE Transactions on Robotics 28, 1 (2012), 61–76. Google Scholar
Digital Library
- Agostino Martinelli. 2012. Vision and IMU Data Fusion: Closed-form solutions for attitude, speed, absolute scale and bias determination. IEEE Transactions on Robotics 28, 1 (2012), 44–60. Google Scholar
Digital Library
- Chen Min, Yuanwen Tian, Giancarlo Fortino, Zhang Jing, and Iztok Humar. 2018. Cognitive internet of vehicles. Computer Communications (2018), 58–76. Google Scholar
Digital Library
- Anastasios I. Mourikis and Stergios I. Roumeliotis. 2007. A multi-state constraint Kalman filter for vision-aided inertial navigation. In 2007 IEEE International Conference on Robotics and Automation. 3565–3572.Google Scholar
- Raul Mur-Artal and Juan Domingo Tardos. 2016. ORB-SLAM2: An open-source SLAM system for monocular, stereo and RGB-D cameras. IEEE Transactions on Robotics PP, 99 (2016), 1255–1262.Google Scholar
- Raul Mur-Artal and Juan Domingo Tardos. 2016. Visual-inertial monocular SLAM with map reuse. IEEE Robotics & Automation Letters 2, 2 (2016), 796–803.Google Scholar
Cross Ref
- Raul Murartal, J. M. M. Montiel, and Juan D. Tardos. 2017. ORB-SLAM: A versatile and accurate monocular SLAM system. IEEE Transactions on Robotics 31, 5 (2017), 1147–1163.Google Scholar
Digital Library
- Daiduong Nguyen, Abdelhafid Elouardi, Sergio Alberto Rodriguez Florez, and Samir Bouaziz. 2018. HOOFR SLAM System: An embedded vision SLAM algorithm and its hardware-software mapping-based intelligent vehicles applications. IEEE Transactions on Intelligent Transportation Systems (2018), 1–16.Google Scholar
- Taih Pire, Thomas Fischer, Gastn Castro, Pablo Decristforis, Javier Civera, and Julio Jacoboberlles. 2017. S-PTAM: Stereo parallel tracking and mapping. Robotics & Autonomous Systems 93 (2017), 27–42. Google Scholar
Digital Library
- Matia Pizzoli, Christian Forster, and Davide Scaramuzza. 2014. REMODE: Probabilistic, monocular dense reconstruction in real time. In 2014 IEEE International Conference on Robotics & Automation. 2609–2616.Google Scholar
Cross Ref
- Pedro F. Proena and Yang Gao. 2018. Probabilistic RGB-D odometry based on points, lines and planes under depth uncertainty. Robotics & Autonomous Systems 104 (2018), 25–39.Google Scholar
Cross Ref
- Albert Pumarola, Alexander Vakhitov, Antonio Agudo, Alberto Sanfeliu, and Francese Morenonoguer. 2017. PL-SLAM: Real-time monocular visual SLAM with points and lines. In 2017 IEEE International Conference on Robotics and Automation. 4503–4508.Google Scholar
Cross Ref
- Tong Qin, Peiliang Li, and Shaojie Shen. 2017. VINS-Mono: A robust and versatile monocular visual-inertial state estimator. IEEE Transactions on Robotics PP, 99 (2017), 1–17. Google Scholar
Digital Library
- Grompone Von Gioi Rafael, Jakubowicz Jĺȩrĺȩmie, Morel Jean-Michel, and Randall Gregory. 2010. LSD: A fast line segment detector with a false detection control. IEEE Transactions on Pattern Analysis & Machine Intelligence 32, 4 (2010), 722–732. Google Scholar
Digital Library
- Milad Ramezani and Kourosh Khoshelham. 2018. Vehicle positioning in GNSS-deprived urban areas by stereo visual-inertial odometry. IEEE Transactions on Intelligent Vehicles 3, 2 (2018), 208–217.Google Scholar
Cross Ref
- Jan Sthmer, Stefan Gumhold, and Daniel Cremers. 2010. Real-time dense geometry from a handheld camera. In Dagm Conference on Pattern Recognition. 11–20. Google Scholar
Digital Library
- Jürgen Sturm, Nikolas Engelhard, Felix Endres, Wolfram Burgard, and Daniel Cremers. 2012. A benchmark for the evaluation of RGB-D SLAM systems. In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. 573–580.Google Scholar
Cross Ref
- Fangchun Yang, Shangguang Wang, Jinglin Li, Zhihan Liu, and Qibo Sun. 2014. An overview of internet of vehicles. China Communications 11, 10 (2014), 1–15.Google Scholar
Cross Ref
- Shichao Yang and Sebastian Scherer. 2017. Direct monocular odometry using points and lines. In 2017 IEEE International Conference on Robotics and Automation. 3871–3877.Google Scholar
Cross Ref
- Hongsheng Yu and Anastasios I. Mourikis. 2017. Edge-based visual-inertial odometry. In 2017 IEEE/ RSJ International Conference on Intelligent Robots and Systems. 6670–6677.Google Scholar
Cross Ref
- Guoxuan Zhang, Han Lee Jin, Jongwoo Lim, and Il Hong Suh. 2015. Building a 3-D line-based map using stereo SLAM. IEEE Transactions on Robotics 31, 6 (2015), 1364–1377.Google Scholar
Digital Library
- Xingxing Zuo, Xiaojia Xie, Yong Liu, and Guoquan Huang. 2017. Robust visual SLAM with point and line features. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems. 1775–1782.Google Scholar
Cross Ref
Index Terms
Semi-Direct Monocular Visual-Inertial Odometry Using Point and Line Features for IoV
Recommendations
Direct visual-inertial odometry with semi-dense mapping
AbstractThe paper presents a direct visual-inertial odometry system. In particular, a tightly coupled nonlinear optimization based method is proposed by integrating the recent development in direct dense visual tracking of camera and the ...
ImPL-VIO: An Improved Monocular Visual-Inertial Odometry Using Point and Line Features
Intelligent Robotics and ApplicationsAbstractMost of the visual-inertial navigation systems (VINS) that use only point features usually work well in regular environment, but decay in low-texture scenes. Meanwhile, those systems rarely construct environmental map with structural information. ...
Semi-dense Visual Odometry for a Monocular Camera
ICCV '13: Proceedings of the 2013 IEEE International Conference on Computer VisionWe propose a fundamentally novel approach to real-time visual odometry for a monocular camera. It allows to benefit from the simplicity and accuracy of dense tracking - which does not depend on visual features - while running in real-time on a CPU. The ...






Comments