MixedSCNet: LiDAR-Based Place Recognition Using Multi-Channel Scan Context Neural Network
Open Access
- 18 January 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (2) , 406
Abstract
In the realm of LiDAR-based place recognition tasks, three predominant methodologies have emerged: manually crafted feature descriptor-based methods, deep learning-based methods, and hybrid methods that combine the former two. Manually crafted feature descriptors often falter in reverse visits and confined indoor environments, while deep learning-based methods exhibit limitations in terms of generalization to distinct data domains. Hybrid methods tend to fix these problems, albeit at the cost of an expensive computational burden. In response to this, this paper introduces MixedSCNet, a novel hybrid approach designed to harness the strengths of manually crafted feature descriptors and deep learning models while keeping a relatively low computing overhead. MixedSCNet starts with constructing a BEV descriptor called MixedSC, which takes height, intensity, and smoothness into consideration simultaneously, thus offering a more comprehensive representation of the point cloud. Subsequently, MixedSC is fed into a compact Convolutional Neural Network (CNN), which further extracts high-level features, ultimately yielding a discriminative global point cloud descriptor. This descriptor is then employed for place retrieval, effectively bridging the gap between manually crafted feature descriptors and deep learning models. To substantiate the efficacy of this amalgamation, we undertake an extensive array of experiments on the KITTI and NCLT datasets. Results show that MixedSCNet stands out as the sole method showcasing state-of-the-art performance across both datasets, outperforming the other five methods while maintaining a relatively short runtime.Keywords
Funding Information
- Key Research and Development Plan Project of Hubei Province (2021BAA196)
This publication has 36 references indexed in Scilit:
- Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection2020
- 3D LiDAR-Based Global Localization Using Siamese Neural NetworkIEEE Transactions on Intelligent Transportation Systems, 2019
- PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval2019
- 1-Day Learning, 1-Year Localization: Long-Term LiDAR Localization Using Scan Context ImageIEEE Robotics and Automation Letters, 2019
- Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map2018
- PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition2018
- Deep Residual Learning for Image Recognition2016
- University of Michigan North Campus long-term vision and lidar datasetThe International Journal of Robotics Research, 2015
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Bags of Binary Words for Fast Place Recognition in Image SequencesIEEE Transactions on Robotics, 2012