Efficient descriptor learning for large scale localization

Many robotics and Augmented Reality (AR) systems that use sparse keypoint-based visual maps operate in large and highly repetitive environments, where pose tracking and localization are challenging tasks. Additionally, these systems usually face further challenges, such as limited computational power, or insufficient memory for storing large maps of the entire environment. Thus, developing compact map representations and improving retrieval is of considerable interest for enabling large-scale visual place recognition and loop-closure. In this paper, we propose a novel approach to compress descriptors while increasing their discriminability and match-ability, based on recent advances in neural networks. At the same time, we target resource-constrained robotics applications in our design choices. The main contributions of this work are twofold. First, we propose a linear projection from descriptor space to a lower-dimensional Euclidean space, based on a novel supervised learning strategy employing a triplet loss. Second, we show the importance of including contextual appearance information to the visual feature in order to improve matching under strong viewpoint, illumination and scene changes. Through detailed experiments on three challenging datasets, we demonstrate significant gains in performance over state-of-the-art methods.

Authors

• Antonio Loquercio
• Marcin Dymczyk
• Bernhard Zeisl
• Simon Lynen
• Igor Gilitschenski
• Roland Siegwart

Keywords

• Training
• Three-dimensional displays
• Optimization
• Visualization
• Supervised learning
• Solid modeling
• Robots
• Descriptor Learning
• Visual Features
• Euclidean Space
• Low-dimensional Space
• Visual Map
• Linear Projection
• Triplet Loss
• Advances In Neural Networks
• Scene Changes
• Strong Illumination
• Descriptor Space
• Pose Tracking
• Training Data
• Convolutional Neural Network
• Image Features
• Descriptive Characteristics
• Performance Gain
• Low-level Features
• Convolutional Neural Network Architecture
• Nearest Neighbor Search
• Simultaneous Localization And Mapping
• 3D Point
• Strong Changes
• 3D Landmarks
• Image Patches
• Image Descriptors
• Viewpoint Changes
• Policy Learning
• Query Image