2019/06/25 by Yongfei Li, Dongfang Yang, Shicheng Wang +3 · 13 citations
Computer Science · Engineering · Environmental Science · Mathematics · #Artificial intelligence #Automated Road and Building Extraction #Computer science #Computer vision #Consistency (knowledge bases) #Feature extraction #Homography #Image (mathematics) #Image registration #Matching (statistics) #Mathematics #Pattern recognition (psychology) #Point (geometry) #Point cloud #Point set registration #Remote Sensing and LiDAR Applications #Rigid transformation #Robotics and Sensor-Based Localization #Scale-invariant feature transform #Transformation (genetics) #cs.AI #cs.CV #eess.IV
paper · pdf · doi:10.1109/tgrs.2020.3011034
published in IEEE Transactions on Geoscience and Remote Sensing 59(7), 6065-6076 (Institute of Electrical and Electronics Engineers) · 19pages, 10 figures, 3 tables. in IEEE Transactions on Geoscience and Remote Sensing
arxiv created 2019/06/25 · openalex created_date 2019/07/12 · openalex publication_date 2020/08/18 · arxiv updated 2020/10/12 · openalex updated_date 2026/08/05
In this article, a road-network-based geolocalization method is proposed. We match roads in the onboard images to the reference road vector map, and realize successful localization over areas as large as a whole city. The road network matching problem is treated as a point cloud registration problem under the homography transformation and solved under the hypothesize-and-test framework. To tackle the point cloud registration problem, a global projective-invariant feature is proposed, which consists of two road intersections augmented with their tangents. In addition, we propose the necessary conditions for the features to match. This can reduce the candidate matching features, thus accelerating the search to a great extent. These matching candidates are first “filtered” with the model consistency check in parameter space and then tested with similarity metrics to identify the correct transformation. The experiments show that our method can localize an aerial image over an area larger than 1000 km2within several seconds on a single CPU. Our code can be found at: https://github.com/FlyAlCode/RCLGeolocalization-2.0.