Global Place Recognition using An Improved Scan Context for LIDAR-based Localization System

Shi, Xiaoyu; Chai, Ziqi; Zhou, Yan; Wu, Jianhua; Xiong, Zhenhua

doi:10.1109/aim46487.2021.9517663

Cited by 5 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adopt the strategy proposed by Shi et al (Shi et al 2021), employing the scan context for coarse localization in the first stage. Subsequently, comparative experiments are conducted using the methods introduced in this paper, alongside ICP, NDT, GICP, and KISS-ICP, in the second stage.…”

Section: Methodsmentioning

confidence: 99%

“…Ratz et al (2020) enhanced SegMap (Dubé et al 2020) by training neural network and evaluated the localization accuracy using Iterative Closest Point (ICP) (Besl and McKay 1992). Shi et al (Shi et al 2021) proposed a variant of Scan Context for keyframe retrieval, then applied Normal Distributions Transform (NDT) (Biber and Straßer 2003) to get a precise initial pose. Luo et al (Luo et al 2022) proposed a descriptor called HOPN and refined the coarse pose using ICP.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, research on two-stage localization methods is relatively limited. Shi et al (2021) enhanced descriptor rotational invariance using principal component analysis (PCA) (Wold, Esbensen, and Geladi 1987) sues in current methods. Firstly, the sparsity of keyframes leads to uncertainty in the translation and overlap between the retrieved data and the map data, subsequently affecting the accuracy and stability of registration algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Constellation-Inspired Single-Shot Global LiDAR Localization

Zhang,

Wang,

Chen

et al. 2024

AAAI

View full text Add to dashboard Cite

Global localization is a challenging task for intelligent robots, as its accuracy directly contributes to the performance of downstream navigation and planning tasks. However, existing literature focus more on the place retrieval and the success rate of localization, with limited attention given to the metrics of position estimation. In this paper, a single-shot global LiDAR localization method is proposed with the ultimate goal of achieving high position accuracy, inspired by the positioning approach of multi-constellation localization systems. Initially, we perform coarse localization using global descriptors and select observation points along with their corresponding coordinates based on the obtained coarse localization results. Coordinates can be acquired from a pre-built map, GNSS, or other devices. Then, a lightweight LiDAR odometry method is designed to estimate the distance between the retrieved data and the observation points. Ultimately, the localization problem is transformed into an optimization problem of solving a system of multiple sphere equations. The experimental results on the KITTI dataset and the self-collected dataset demonstrate that our method achieves an average localization error (including errors in the z-axis) of 0.89 meters. In addition, it achieves retrieval efficiency of 0.357 s per frame on the former dataset and 0.214 s per frame on the latter one. Code and data are available at https://github.com/jlurobot/multi-constellation-localization.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Constellation-Inspired Single-Shot Global LiDAR Localization

Zhang,

Wang,

Chen

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Ref. [9] establishes a local reference frame by rotating the original LiDAR coordinate axis around the z-axis. In this frame, the x-axis corresponds to the direction of maximum point cloud variance, increasing the robustness of Scan Context to changes in viewpoint.…”

Section: Manually Crafted Feature Descriptor-based Methodsmentioning

confidence: 99%

“…The first category couples place recognition and pose estimation, directly estimating the accurate pose of the robot [4][5][6][7][8]. The second one involves a two-stage approach, where place recognition provides a coarse location estimate and pose estimation refines this estimate to determine the precise pose [9][10][11]. For outdoor scenarios, Global Navigation Satellite Systems (GNSSs) are often used to provide an initial estimate of global location.…”

Section: Introductionmentioning

confidence: 99%

MixedSCNet: LiDAR-Based Place Recognition Using Multi-Channel Scan Context Neural Network

Si,

Han,

et al. 2024

Electronics

View full text Add to dashboard Cite

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.

show abstract

3D point cloud-based place recognition: a survey

Luo,

Yu,

Chen

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Place recognition is a fundamental topic in computer vision and robotics. It plays a crucial role in simultaneous localization and mapping (SLAM) systems to retrieve scenes from maps and identify previously visited places to correct cumulative errors. Place recognition has long been performed with images, and multiple survey papers exist that analyze image-based methods. Recently, 3D point cloud-based place recognition (3D-PCPR) has become popular due to the widespread use of LiDAR scanners in autonomous driving research. However, there is a lack of survey paper that discusses 3D-PCPR methods. To bridge the gap, we present a comprehensive survey of recent progress in 3D-PCPR. Our survey covers over 180 related works, discussing their strengths and weaknesses, and identifying open problems within this domain. We categorize mainstream approaches into feature-based, projection-based, segment-based, and multimodal-based methods and present an overview of typical datasets, evaluation metrics, performance comparisons, and applications in this field. Finally, we highlight some promising research directions for future exploration in this domain.

show abstract

Global Place Recognition using An Improved Scan Context for LIDAR-based Localization System

Cited by 5 publications

References 19 publications

Multi-Constellation-Inspired Single-Shot Global LiDAR Localization

Multi-Constellation-Inspired Single-Shot Global LiDAR Localization

MixedSCNet: LiDAR-Based Place Recognition Using Multi-Channel Scan Context Neural Network

3D point cloud-based place recognition: a survey

Contact Info

Product

Resources

About