Object‐Enhanced Loop Closing With Semantic Topological Graphs

ABSTRACT Loop closing is crucial for correcting drift in ego‐localization and mapping. Current approaches face a critical precision–recall trade‐off. To ensure precision and accurate loop pose estimation, traditional methods that impose strict geometric verification inevitably suffer from low recall. Moreover, existing semantic methods, while addressing perceptual aliasing, have yet to effectively utilize semantic information to enhance the recall of geometrically valid loop candidates. In response, we propose a novel loop‐closing method that integrates geometric and semantic verification to enhance loop recall while strictly maintaining precision under the same geometric verification. To effectively utilize semantic information, we utilize a semantic topological graph to organize semantic details. To measure the similarity between semantic topological graphs, we propose semantic object associations after long intervals. This association leverages geometric constraints, appearance similarity, and coarse‐grained object similarity, effectively formulating object associations as a linear matching problem. Finally, we implement an object‐level Bundle Adjustment method that accurately computes geometric transformations between matching keyframes, to improve loop recall and trajectory estimation accuracy. Experimental results demonstrate that the proposed object associations, even after long intervals, can handle dense, occluded, and small objects. Moreover, our loop closing significantly improves loop recall rates and trajectory estimation accuracy, while maintaining strict geometric consistency, as validated on the KITTI and KITTI‐360 data sets.