Journal
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
Volume 70, Issue 8, Pages 8225-8234Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2022.3229385
Keywords
Laser radar; Transformers; Feature extraction; Image recognition; Fuses; Location awareness; Point cloud compression; Deep learning methods; LiDAR place recognition; sequence matching
Ask authors/readers for more resources
In this article, we propose a transformer-based network named SeqOT for place recognition based on sequential 3-D LiDAR scans. Our method exploits temporal and spatial information provided by sequential range images and generates global descriptors using multiscale transformers. The results show that our method outperforms state-of-the-art LiDAR-based place recognition methods and operates faster than the sensor's frame rate.
Place recognition is an important component for autonomous vehicles to achieve loop closing or global localization. In this article, we tackle the problem of place recognition based on sequential 3-D LiDAR scans obtained by an onboard LiDAR sensor. We propose a transformer-based network named SeqOT to exploit the temporal and spatial information provided by sequential range images generated from the LiDAR data. It uses multiscale transformers to generate a global descriptor for each sequence of LiDAR range images in an end-to-end fashion. During online operation, our SeqOT finds similar places by matching such descriptors between the current query sequence and those stored in the map. We evaluate our approach on four datasets collected with different types of LiDAR sensors in different environments. The experimental results show that our method outperforms the state-of-the-art LiDAR-based place recognition methods and generalizes well across different environments. Furthermore, our method operates online faster than the frame rate of the sensor.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available