Abstract
Real-time vehicle localization (i.e., position and orientation estimation in the world coordinate system) with high accuracy is the fundamental function of an intelligent vehicle (IV) system. In the process of commercialization of IVs, many car manufacturers attempt to avoid high-cost sensor systems (e.g., RTK GNSS and LiDAR) in favor of low-cost optical sensors such as cameras. The same cost-saving strategy also gives rise to an increasing number of vehicles equipped with High Definition (HD) maps. Rooted upon these existing technologies, this article presents the concept of Monocular Localization with Vector HD Map (MLVHM), a novel camera-based map-matching method that efficiently aligns semantic-level geometric features in-camera acquired frames against the vector HD map in order to achieve high-precision vehicle absolute localization with minimal cost. The semantic features are delicately chosen for the ease of map vector alignment as well as for the resiliency against occlusion and fluctuation in illumination. The effective data association method in MLVHM serves as the basis for the camera position estimation by minimizing feature re-projection errors, and the frame-to-frame motion fusion is further introduced for reliable localization results. Experiments have shown that MLVHM can achieve high-precision vehicle localization with an RMSE of 24 cm with no cumulative error. In addition, we use low-cost on-board sensors and light-weight HD maps to achieve or even exceed the accuracy of existing map-matching algorithms.
Highlights
Precise knowledge of the localization and orientation of a vehicle is critical in realizing many map-based intelligent vehicle (IV) applications [1,2], such as decision-making, cooperative driving, map updating, etc.The state-of-the-art integrated inertial navigation system based on the global navigation satellite system (GNSS) real-time kinematic (RTK) module, high-quality IMU, and LiDAR-based positioning technology is well-known to deliver high-precision localization [3]; due to its high cost, it remains mostly in the research stage and is seldom seen in mass-produced vehicles.As an effective augmentation tool among on-board sensors, the High Definition (HD) compact map has gained tremendous popularity as a consumer vehicle add-on feature
In order to address these shortcomings, we propose in this paper the concept of Monocular Localization with Vector HD Map (MLVHM), a novel map-based localization algorithm, as well as its data association method implemented on low-cost visual sensors and compact HD vector maps to deliver high-precision, drift-free vehicle localization
This paper focuses on using the higher-level semantic features instead, which are relatively stable under environment changes in ambient illumination, angle of view, season, and weather
Summary
Precise knowledge of the localization and orientation of a vehicle is critical in realizing many map-based IV applications [1,2], such as decision-making, cooperative driving, map updating, etc.The state-of-the-art integrated inertial navigation system based on the global navigation satellite system (GNSS) real-time kinematic (RTK) module, high-quality IMU, and LiDAR-based positioning technology is well-known to deliver high-precision localization [3]; due to its high cost, it remains mostly in the research stage and is seldom seen in mass-produced vehicles.As an effective augmentation tool among on-board sensors, the HD compact map has gained tremendous popularity as a consumer vehicle add-on feature. High-precision HD maps are considered the cornerstone of IV technology, especially for more advanced automated vehicles [2]. HD maps are often deployed in costly equipment such as LiDAR and the corresponding high-performance integrated inertial navigation system, the HD map itself is not considered as a costly technology, and are widely available as an optional feature for most of the vehicles in the market. This kind of map retains raw geometric information and may be segmented with semantic labels; it is not Sensors 2020, 20, 1870; doi:10.3390/s20071870 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
