LCD -- Line Clustering and Description for Place Recognition

TL;DR

This paper presents a novel place recognition method using RGB-D images and line clusters, preserving structural information and achieving good generalization from synthetic to real data.

Contribution

It introduces a learning-based approach that recognizes line clusters as objects for place recognition, maintaining geometric structure and using attention-based neural networks.

Findings

Outperforms bag-of-words and NetVLAD on indoor scenes

Generalizes well from synthetic to real RGB-D data

Provides geometric arrangement information of scene instances

Abstract

Current research on visual place recognition mostly focuses on aggregating local visual features of an image into a single vector representation. Therefore, high-level information such as the geometric arrangement of the features is typically lost. In this paper, we introduce a novel learning-based approach to place recognition, using RGB-D cameras and line clusters as visual and geometric features. We state the place recognition problem as a problem of recognizing clusters of lines instead of individual patches, thus maintaining structural information. In our work, line clusters are defined as lines that make up individual objects, hence our place recognition approach can be understood as object recognition. 3D line segments are detected in RGB-D images using state-of-the-art techniques. We present a neural network architecture based on the attention mechanism for frame-wise line clustering. A similar neural network is used for the description of these clusters with a compact embedding of 128 floating point numbers, trained with triplet loss on training data obtained from the InteriorNet dataset. We show experiments on a large number of indoor scenes and compare our method with the bag-of-words image-retrieval approach using SIFT and SuperPoint features and the global descriptor NetVLAD. Trained only on synthetic data, our approach generalizes well to real-world data captured with Kinect sensors, while also providing information about the geometric arrangement of instances.