Scale-Robust Localization Using General Object Landmarks

Visual localization under large changes in scale is an important capability in many robotic mapping applications, such as localizing at low altitudes in maps built at high altitudes, or performing loop closure over long distances. Existing approaches, however, are robust only up to about a 3× difference in scale between map and query images. We propose a novel combination of deep-learning-based object features and state-of-the-art SIFT point-features that yields improved robustness to scale change. This technique is training-free and class-agnostic, and in principle can be deployed in any environment out-of-the-box. We evaluate the proposed technique on the KITTI Odometry benchmark and on a novel dataset of outdoor images exhibiting changes in visual scale of 7× and greater, which we have released to the public. Our technique consistently outperforms localization using either SIFT features or the proposed object features alone, achieving both greater accuracy and much lower failure rates under large changes in scale.

Authors

• Andrew Holliday
• Gregory Dudek

Keywords

• Visualization
• Measurement
• Simultaneous localization and mapping
• Robustness
• Databases
• Search problems
• Object Landmarks
• Large Changes
• Visual Scale
• High Altitude
• Low Altitude
• Scale Changes
• Large-scale Changes
• Scale-invariant Feature Transform
• Visual Localization
• Query Image
• Loop Closure
• Convolutional Neural Network
• Support Vector Machine
• Network Layer
• Bounding Box
• Image Pairs
• Feature Points
• Total Error
• Sequence Of Frames
• Pose Estimation
• Autonomous Underwater Vehicles
• Global Localization
• Place Recognition
• Change Of Perspective
• Homography
• Visual Odometry
• Input Resolution
• Object Matching
• Object Proposals