This paper presents a new feature based approach for place recognition using 2D LiDAR (Light Detection And Ranging) data. The main contribution lies in the mapping process. It includes a keypoint selection strategy to model places with persistent keypoints from concatenated LiDAR scans. Our objective is to achieve map data reduction while maintaining good place recognition performace. LiDAR scans are concatenated with a registration algorithm and keypoints are extracted from each scan. Based on a regular grid, our approach measures the occurrence of similar keypoints in each region of interest defined by a grid cell. Only keypoints with occurrences beyond a threshold, qualified as stable keypoints, are kept in the place model called submap. The environment is therefore modeled as a collection of submaps, which constitutes the global map. Place recognition consists in submap matching followed by a two steps geometric verification. In the first stage, optimal parameters are set using corrected data. Mapping parameters satisfy six criteria among which is the spatial distribution distance, which represents another contribution of our work. It gives a measure on how well keypoints are distributed in space. Place recognition optimal parameters are set through global localization. In the second stage, the approach is evaluated using raw data in the contexts of global localization, and loop closure detection in a SLAM framework. The results obtained using popular real data sets show that our approach achieves significant map data reduction (up to $92\%$ ) while maintaining good place recognition performance, comparable to state-of-the-art methods.

We propose an appearance-based approach for topological visual mapping and localization using local invariant features. To optimize running times, matchings between the current image and previously visited places are determined using an index based on a set of randomized kd-trees. We use a discrete Bayes filter for predicting loop candidates, whose observation model is a novel approach based on an efficient matching scheme between features. In order to avoid redundant information in the resulting maps, we also present a map refinement framework, which takes into account the visual information stored in the map for refining the final topology of the environment. These refined maps save storage space and improve the execution times of localizations tasks. The approach is validated using image sequences from several environments and compared with the state-of-the-art FAB-MAP 2.0 algorithm.