Scene Overlap Prediction for LiDAR-Based Place Recognition

Yingjian Zhang, Chenguang Dai, Ruqin Zhou, Zhenchao Zhang, Hongliang Ji, Huixin Fan, Yongsheng Zhang, Hanyun Wang

Abstract: Recently, light detection and ranging (LiDAR)-based place recognition has been widely concerned because of its robustness to light conditions, seasonal changes, and viewpoint variations. Unlike most of the existing methods that represent the whole point cloud scenes with global descriptors, we treat the LiDAR-based place recognition problem as a scene overlap prediction task and propose an end-to-end overlap prediction network, which consists of a feature learning backbone, a feature enhancement module, and an overlap prediction module. Based on the prediction result for each point, the overlapping ratios between two point clouds are computed and used to predict whether these two point clouds are at the same place. In addition, to promote the computational efficiency and reduce the model complexity, a lightweight feature learning backbone is adopted. The experiments conducted on the KITTI Odometry dataset demonstrate that the proposed method achieves superior performance compared with the state-of-the-art methods. The lightweight method also obtains $2\times $ inference speed with little performance degradation compared with the vanilla method.