Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions

• Published in: 2018 IEEE CVF Conference on Computer Vision and Pattern Recognition pp. 8601 - 8610
• Main Authors: Sattler, Torsten, Maddern, Will, Toft, Carl, Torii, Akihiko, Hammarstrand, Lars, Stenborg, Erik, Safari, Daniel, Okutomi, Masatoshi, Pollefeys, Marc, Sivic, Josef, Kahl, Fredrik, Pajdla, Tomas
• Format: Conference Proceeding Book Chapter
• Language: English
• Published: IEEE 01.06.2018
• Subjects: benchmark; Benchmark testing; camera pose estimation; Cameras; Computer and Information Science; Computer and Information Sciences; Computer graphics and computer vision; Computer Vision and Robotics (Autonomous Systems); Data- och informationsvetenskap (Datateknik); Datorgrafik och datorseende; Datorseende och robotik (autonoma system); long term localization; Natural Sciences; Naturvetenskap; Robots; Solid modeling; Three-dimensional displays; Trajectory; Visual localization; Visualization
• ISBN: 9781538664209; 1538664208
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2018.00897

Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing condition, including day-night changes, as well as weather and seasonal variations, while providing highly accurate 6 degree-of-freedom (6DOF) camera pose estimates. In this paper, we introduce the first benchmark datasets specifically designed for analyzing the impact of such factors on visual localization. Using carefully created ground truth poses for query images taken under a wide variety of conditions, we evaluate the impact of various factors on 6DOF camera pose estimation accuracy through extensive experiments with state-of-the-art localization approaches. Based on our results, we draw conclusions about the difficulty of different conditions, showing that long-term localization is far from solved, and propose promising avenues for future work, including sequence-based localization approaches and the need for better local features. Our benchmark is available at visuallocalization.net.