Abstract：Place recognition retrieves scenes from a prior map and identifies previously visited locations. It is essential to autonomous-driving and robotics in terms of long-term navigation and global localization. Although the semantic graph has made great progress in 3D place recognition, its construction is greatly affected by the complex dynamic environment. In response, this paper designs a scene graph transformation network to solve place recognition in a dynamic environment. To remove the interference of moving objects, we introduce a moving object segmentation (MOS) module. Besides, we design a scene graph transformer-attention module to generate a more discriminative and representative global scene graph descriptor, which significantly improves the performance of place recognition. In addition, we integrate our place recognition method for loop closure with an existing LiDAR-based odometry , boosting its localization accuracy. We evaluate our method on the KITTI and Oxford RobotCar datasets. Many experimental results show that our method can effectively accomplish place recognition, and its accuracy and robustness improve by at least 3% when compared with existing state-of-the-art methods, such as DiSCO. To illustrate the generalization capabilities of our method, we evaluate it on the KITTI-360 and NCLT datasets while using only KITTI for training. The experiments show that our scene graph descriptor can achieve accurate loop-closure and global localization in never-seen environments.
KeyWord：Place recognition; 3D scene graph representation; Moving object segmentation; Transformer; Global localization; 3D point cloud;

相关文献：
1.Knowledge evolution learning: A cost-free weakly supervised semantic segmentation framework for high-resolution land cover classification
2.Multi-echo hyperspectral reflectance extraction method based on full waveform hyperspectral LiDAR
3.geeSEBAL-MODIS: Continental-scale evapotranspiration based on the surface energy balance for South America
4.Suaeda salsa spectral index for Suaeda salsa mapping and fractional cover estimation in intertidal wetlands
5.Better localized predictions with Out-of-Scope information and Explainable AI: One-Shot SAR backscatter nowcast framework with data from neighboring region
6.Blurry dense object extraction based on buffer parsing network for high-resolution satellite remote sensing imagery
7.Rapid survey method for large-scale outdoor surveillance cameras using binary space partitioning
8.Edge aware depth inference for large-scale aerial building multi-view stereo
9.Unsupervised domain adaptation for SAR target classification based on domain- and class-level alignment: From simulated to real data