LandmarkBoost: Efficient visualContext Classifiers for Robust Localization

The growing popularity of autonomous systems creates a need for reliable and efficient metric pose retrieval algorithms. Currently used approaches tend to rely on nearest neighbor search of binary descriptors to perform the 2D-3D matching and guarantee realtime capabilities on mobile platforms. These methods struggle, however, with the growing size of the map, changes in viewpoint or appearance, and visual aliasing present in the environment. The rigidly defined descriptor patterns only capture a limited neighborhood of the keypoint and completely ignore the overall visual context. We propose LandmarkBoost - an approach that, in contrast to the conventional 2D-3D matching methods, casts the search problem as a landmark classification task. We use a boosted classifier to classify landmark observations and directly obtain correspondences as classifier scores. We also introduce a formulation of visual context that is flexible, efficient to compute, and can capture relationships in the entire image plane. The original binary descriptors are augmented with contextual information and informative features are selected by the boosting framework. Through detailed experiments, we evaluate the retrieval quality and performance of Landmark-Boost, demonstrating that it outperforms common state-of-the-art descriptor matching methods.

Authors

• Marcin Dymczyk
• Igor Gilitschenski
• Juan I. Nieto 0001
• Simon Lynen
• Bernhard Zeisl
• Roland Siegwart

Keywords

• Visualization
• Feature extraction
• Measurement
• Robots
• Three-dimensional displays
• Pose estimation
• Context modeling
• Feature Information
• Image Plane
• Mobile Platform
• Visual Context
• Viewpoint Changes
• Mobile Devices
• Negative Samples
• Long Short-term Memory
• Multi-label
• Classification Of Samples
• Precision And Recall
• Baseline Methods
• Feature Points
• Image Retrieval
• Group Approach
• Matching Performance
• Weak Learners
• Background Class
• Priority Map
• 3D Landmarks
• Contextual Embedding
• Place Recognition