Exploiting Structural Knowledge for Place Recognition

Place recognition is the problem of finding associations between a query set of place descriptions and a database. It is an important means for loop closure detection in SLAM. The primary source of information to decide about associations is the pairwise similarity of descriptors between the query and the database items (e.g., image descriptor similarities). Beyond better descriptors, significant improvements were achieved by exploiting additional structural information, in particular by comparing sequences instead of individual items. We work towards exploitation of additional systematic sources of information. For example, intra-set similarities between items within the query or the database sets. They can be used to detect inconsistencies of groups of associations between database and query items, e.g. to inhibit matchings of multiple query descriptors to the same database descriptor if the query descriptors are mutually different. This is only one example of additional structural knowledge. Please refer to the publications below for more details.

The basic place recognition pipeline (above the horizontal dashed line) can be extended with additional information (below this line). Established approaches are standardization of descriptors and sequence processing. We work on algorithms that exploit additional knowledge, for example the intra-set similarities of database or query images.

Related Publications

Neubert, P. & Schubert, S. (2022) SEER: Unsupervised and sample-efficient environment specialization of image descriptors. In Proc. of Robotics: Science and Systems (RSS). DOI: 10.15607/RSS.2022.XVIII.006. Code Testdata

Schubert, S., Neubert, P. & Protzel, P. (2021) Fast and Memory Efficient Graph Optimization via ICM for Visual Place Recognition. In Proc. of Robotics: Science and Systems (RSS). DOI: 10.15607/RSS.2021.XVII.091. Video Code

Schubert, S., Neubert, P. & Protzel, P. (2021) Beyond ANN: Exploiting Structural Knowledge for Efficient Place Recognition. In Proc. of Intl. Conf. on Robotics and Automation (ICRA). DOI: 10.1109/ICRA48506.2021.9561006 Code

Neubert, P., Schubert, S. & Protzel, P. (2021) Resolving Place Recognition Inconsistencies Using Intra-Set Similarities. IEEE Robotics and Automation Letters (RA-L) and ICRA. DOI: 10.1109/LRA.2021.3060729 Code

Schubert, S., Neubert, P. & Protzel, P. (2021) Graph-based Non-Linear Least Squares Optimization for Visual Place Recognition in Changing Environments. In IEEE Robotics and Automation Letters (RA-L). DOI: 10.1109/LRA.2021.3052446

Schubert, S., Neubert, P. & Protzel, P. (2020) Unsupervised Learning Methods for Visual Place Recognition in Discretely and Continuously Changing Environments. In Proc. of Intl. Conf. on Robotics and Automation (ICRA). DOI: 10.1109/ICRA40945.2020.9197044 Code

Neubert, P., Schubert, S. & Protzel, P. (2019) A neurologically inspired sequence processing model for mobile robot place recognition. In IEEE Robotics and Automation Letters (RA-L) and presentation at Intl. Conf. on Intelligent Robots and Systems (IROS). DOI: 10.1109/LRA.2019.2927096 MCN_v0_1 Code

Schubert, S., Neubert, P. & Protzel, P. (2019) Towards combining a neocortex model with entorhinal grid cells for mobile robot localization. In Proc. of European Conference on Mobile Robotics (ECMR). DOI: 10.1109/ECMR.2019.8870939

Neubert, P., Schubert, S. & Protzel, P. (2015) Exploiting intra Database Similarities for Selection of Place Recognition Candidates in Changing Environments. In Proc. of. Computer Vision and Pattern Recognition (CVPR) Workshop on Visual Place Recognition in Changing Environments