Augmenting Visual Place Recognition with Structural Cues
This work addresses place recognition for robotics or autonomous systems, offering a significant but incremental improvement by combining existing modalities.
The paper tackles visual place recognition by augmenting image-based methods with structural cues from structure-from-motion, achieving up to 90% better performance than state-of-the-art descriptors at low dimensionalities on the Oxford RobotCar dataset.
In this paper, we propose to augment image-based place recognition with structural cues. Specifically, these structural cues are obtained using structure-from-motion, such that no additional sensors are needed for place recognition. This is achieved by augmenting the 2D convolutional neural network (CNN) typically used for image-based place recognition with a 3D CNN that takes as input a voxel grid derived from the structure-from-motion point cloud. We evaluate different methods for fusing the 2D and 3D features and obtain best performance with global average pooling and simple concatenation. On the Oxford RobotCar dataset, the resulting descriptor exhibits superior recognition performance compared to descriptors extracted from only one of the input modalities, including state-of-the-art image-based descriptors. Especially at low descriptor dimensionalities, we outperform state-of-the-art descriptors by up to 90%.