Intensity-based Feature Filtering for LiDAR-based SLAM

doi:10.16182/j.issn1004731x.joss.23-1166

Abstract

Abstract:

In order to solve the problem that an excessive influx of feature points into the point cloud registration phase can potentially lead to diminished algorithmic accuracy and suboptimal mapping outcomes, a novel laser SLAM algorithm predicated on the filtering of feature points through the utilization of intensity information is proposed. The intensity distribution near the feature points in the local map is calculated based on the point cloud intensity information, and each feature point within the local map is attributed an intensity distribution index. Through the application of an intensity threshold, feature points that exhibit substantial variations in intensity across successive frames are systematically removed. This process identifies and retains only valid feature points amenable for the registration of scanned frames with the local maps. A novel intensity-weighted cost function is proposed. This function aims to enhance the accuracy of the robot frame's pose estimation within the global map. The simulation results show that it achieves an average reduction of 13.8% in feature point count per scan frame, along with an average decrease of 18.8% in the number of feature points within the local map, enhances registration accuracy by 5.7%.

Key words: simultaneous localization and mapping, LiDAR, intensity information, feature filtering, point cloud registration

CLC Number:

TP242

Li Weigang, Zou Shaofeng, Wang Yongqiang, Yu Chuxiang. Intensity-based Feature Filtering for LiDAR-based SLAM[J]. Journal of System Simulation, 2025, 37(2): 392-403.

Figures/Tables 15

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Table 1

Fig. 8

Table 2

Fig. 9

Table 3

Fig. 10

Table 4

Table 5

Mapping results of LO systems on KITTI dataset

$θ i$	NFP-SF	Δ/%	NFP-LFM	Δ/%	RMSE
0.5	1 940	29.7	39 579	56.2	4.1
1.0	1 922	30.3	38 665	57.3	3.9
1.25	1 884	31.7	38 636	57.3	3.6
1.5	1 857	32.7	39 245	56.6	4.3
2.0	1 780	35.5	41 474	54.2	4.6

Table 5

References 31

1	Cadena Cesar, Carlone L, Carrillo Henry, et al. Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-perception Age[J]. IEEE Transactions on Robotics, 2016, 32(6): 1309-1332.
2	薛光辉, 李瑞雪, 张钲昊, 等. 基于3D激光雷达的SLAM算法研究现状与发展趋势[J]. 信息与控制, 2023, 52(1): 18-36.
	Xue Guanghui, Li Ruixue, Zhang Zhenghao, et al. State-of-the-art and Tendency of SLAM Algorithms Based on 3D LiDAR[J]. Information and Control, 2023, 52(1): 18-36.
3	Zhang J, Singh S. LOAM: Lidar Odometry and Mapping in Real-time[C]//Robotics: Science and Systems, 2014, 2(9): 1-9.
4	周治国, 曹江微, 邸顺帆. 3D激光雷达SLAM算法综述[J]. 仪器仪表学报, 2021, 41(9): 13-27.
	Zhou Zhiguo, Cao Jiangwei, Di Shunfan. Overview of 3D Lidar SLAM Algorithms[J]. Chinese Journal of Scientific Instrument, 2021, 41(9): 13-27.
5	Deschaud Jean-Emmanuel. IMLS-SLAM: Scan-to-model Matching Based on 3D Data[C]//2018 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2018: 2480-2485.
6	Lin Jiarong, Zhang Fu. Loam Livox: A Fast, Robust, High-precision LiDAR Odometry and Mapping Package for LiDARs of Small FoV[C]//2020 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2020: 3126-3131.
7	Chen Xieyuanli, Milioto Andres, Palazzolo Emanuele, et al. SuMa++: Efficient LiDAR-based Semantic SLAM[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2019: 4530-4537.
8	Dellenbach Pierre, Deschaud Jean-Emmanuel, Jacquet Bastien, et al. CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure[C]//2022 International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2022: 5580-5586.
9	Besl P J, Mckay N D. Method for Registration of 3-D Shapes[C]//Sensor Fusion IV: Control Paradigms and Data Structures. Bellingham: SPIE, 1992: 586-606.
10	Cattaneo Daniele, Vaghi Matteo, Valada Abhinav. LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM[J]. IEEE Transactions on Robotics, 2022, 38(4): 2074-2093.
11	Segal A, Haehnel D, Thrun S. Generalized-icp[C]//Robotics: Science and Systems, 2009, 2(4): 435.
12	Koide Kenji, Yokozuka Masashi, Oishi Shuji, et al. Voxelized GICP for Fast and Accurate 3D Point Cloud Registration[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2021: 11054-11059.
13	Wang Jikai, Xu Meng, Foroughi Farzin, et al. FasterGICP: Acceptance-rejection Sampling Based 3D Lidar Odometry[J]. IEEE Robotics and Automation Letters, 2022, 7(1): 255-262.
14	Wang Han, Wang Chen, Chen Chunlin, et al. F-LOAM: Fast LiDAR Odometry and Mapping[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2021: 4390-4396.
15	Park Y, Bae S. Keeping Less is More: Point Sparsification for Visual Slam[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2022: 7936-7943.
16	Shan Tixiao, Englot B. LeGO-LOAM: Lightweight and Ground-optimized Lidar Odometry and Mapping on Variable Terrain[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2018: 4758-4765.
17	Duan Yifan, Peng Jie, Zhang Yu, et al. PFilter: Building Persistent Maps through Feature Filtering for Fast and Accurate LiDAR-based SLAM[C]//2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2022: 11087-11093.
18	Geiger Andreas, Lenz Philip, Urtasun R. Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2012: 3354-3361.
19	Wang Han, Wang Chen, Xie Lihua. Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 1715-1721.
20	Hess W, Kohler D, Rapp H, et al. Real-time Loop Closure in 2D LIDAR SLAM[C]//2016 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2016: 1271-1278.
21	Wang Han, Wang Chen, Xie Lihua. Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection[C]//2020 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2020: 2095-2101.
22	Li Haisong, Tian Bailing, Shen Hongming, et al. An Intensity-augmented LiDAR-inertial SLAM for Solid-state LiDARs in Degenerated Environments[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-10.
23	Hewitt R A, Marshall J A. Towards Intensity-augmented SLAM with LiDAR and ToF Sensors[C]//2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2015: 1956-1961.
24	Kashani A G, Olsen M J, Parrish C E, et al. A Review of LIDAR Radiometric Processing: From Ad Hoc Intensity Correction to Rigorous Radiometric Calibration[J]. Sensors, 2015, 15(11): 28099-28128.
25	张清宇, 崔丽珍, 杜秀铎, 等. 矿山环境三维激光雷达SLAM算法建图与定位[J]. 测绘通报, 2023(5): 72-77.
	Zhang Qingyu, Cui Lizhen, Du Xiuduo, et al. Mapping and Positioning of 3D LiDAR SLAM Algorithm in Mine Environment[J]. Bulletin of Surveying and Mapping, 2023(5): 72-77.
26	Yuan Chongjian, Xu Wei, Liu Xiyuan, et al. Efficient and Probabilistic Adaptive Voxel Mapping for Accurate Online LiDAR Odometry[J]. IEEE Robotics and Automation Letters, 2022, 7(3): 8518-8525.
27	Zhang Le, Ponnuthurai Nagaratnam Suganthan. Robust Visual Tracking via Co-trained Kernelized Correlation Filters[J]. Pattern Recognition, 2017, 69: 82-93.
28	Yin Jie, Li Ang, Li Tao, et al. M2DGR: A Multi-sensor and Multi-scenario SLAM Dataset for Ground Robots[J]. IEEE Robotics and Automation Letters, 2022, 7(2): 2266-2273.
29	Geiger A, Lenz P, Stiller C, et al. Vision Meets Robotics: The KITTI Dataset[J]. The International Journal of Robotics Research, 2013, 32(11): 1231-1237.
30	Zhang Zichao, Scaramuzza Davide. A Tutorial on Quantitative Trajectory Evaluation for Visual(-Inertial) Odometry[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2018: 7244-7251.
31	Yokozuka Masashi, Koide Kenji, Oishi Shuji, et al. LiTAMIN2: Ultra Light LiDAR-based SLAM Using Geometric Approximation Applied with KL-divergence[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2021: 11619-11625.

序号	F-LOAM	PFilter	Δ/%	IF-LOAM	Δ/%
平均值	3 391.9	2 707.2	19.3	2 338.8	30.5
KITTI-00	2 758	2 340	15.2	1 884	31.7
KITTI-01	4 127	2 538	38.5	2 231	45.9
KITTI-02	2 946	2 481	15.8	2 102	28.7
KITTI-03	3 927	3 083	21.5	2 678	31.8
KITTI-04	3 749	2 957	21.1	2 541	32.2
KITTI-05	3 056	2 557	16.3	2 173	28.9
KITTI-06	4 596	3 657	20.4	3 248	29.3
KITTI-07	2 770	2 378	14.2	2 059	25.7
KITTI-08	3 325	2 635	20.8	2 296	31.0
KITTI-09	3 384	2 757	18.5	2 417	28.6
KITTI-10	2 673	2 396	10.4	2 097	21.6

序号	F-LOAM	PFilter	Δ/%	IF-LOAM	Δ/%
平均值	87 329.4	45053.6	48.4	36605.5	57.9
KITTI-00	90 465	50 345	44.3	38 636	57.3
KITTI-01	84 775	30 273	64.3	33 781	60.2
KITTI-02	72 660	42 494	41.5	32 325	55.5
KITTI-03	91 788	47109	48.7	38158	58.4
KITTI-04	78 773	33086	58.0	31087	60.5
KITTI-05	90 940	52487	42.3	39704	56.3
KITTI-06	90 241	44861	50.3	37377	58.6
KITTI-07	90 062	47752	47.0	38205	57.6
KITTI-08	109 777	56327	48.7	42320	61.4
KITTI-09	86 714	47100	45.7	36254	58.2
KITTI-10	74 428	43756	41.2	34813	53.2

序号	LOAM	LeGO-LOAM	F-LOAM	PFilter	IF-LOAM
平均值	15.9	14.0	4.7	4.0	3.8
KITTI-00	19.4	6.3	6.5	4.2	3.6
KITTI-01	21.0	119.4	17.4	17.7	16.7
KITTI-02	111.6	14.7	14.1	8.4	8.7
KITTI-03	1.0	0.9	1.0	0.9	0.9
KITTI-04	0.5	0.8	0.4	0.4	0.4
KITTI-05	4.6	2.8	3.7	3.7	3.6
KITTI-06	1.1	0.8	0.8	0.7	0.6
KITTI-07	1.3	0.7	0.7	0.6	0.5
KITTI-08	6.7	3.5	4.6	4.6	3.8
KITTI-09	5.3	2.1	1.5	1.5	1.4
KITTI-10	1.9	1.8	1.3	1.2	1.1

算法	Street_03	Street_05	平均值
F-LOAM	32.5	0.5	16.5
PFilter	22.8	0.7	11.7
IF-LOAM	20.8	0.5	10.6

[1]	Li Weigang, Gan Lei, Wang Yongqiang. Dynamic Scene Point Cloud Mapping Method Based on LiDAR-IMU [J]. Journal of System Simulation, 2025, 37(1): 95-106.
[2]	Wang Haichao, Yin Yong, Jing Qianfeng, Cong Lin. Estimation of the Berthing Parameter of Unmanned Surface Vessels Based on 3D LiDAR [J]. Journal of System Simulation, 2024, 36(8): 1737-1748.
[3]	Li Weigang, Yu Chuxiang, Wang Yongqiang, Zou Shaofeng. Real-time Lidar SLAM Algorithm Based on Distribution Optimal Registration [J]. Journal of System Simulation, 2024, 36(11): 2566-2577.
[4]	Fu Qiang, Teng Xianyun, Ji Yuanfa, Ren Fenghua. SLAM Dynamic Algorithm Based on Improved Feature Description [J]. Journal of System Simulation, 2024, 36(11): 2712-2721.
[5]	Zhiqiang Chen, Menglong Cao, Wenbin Zhao. Research on Application of Monarch Butterfly Optimization Particle Filter in SLAM [J]. Journal of System Simulation, 2023, 35(6): 1351-1361.
[6]	Yuan Zhang, Haoyu Han, Xie Han, Jiaxu Fu. Point Cloud Registration Method Based on Improved Covariance Matrix Descriptor [J]. Journal of System Simulation, 2023, 35(5): 979-986.
[7]	Tong Wang, Guangtao Shang, Shan Gao. Research on Multi-Robot SLAM Map FusionMethod Based on Heuristics [J]. Journal of System Simulation, 2022, 34(7): 1449-1458.
[8]	Xuesong Mao, Runlong Lei, Shaowei Huang, Xuetao Mao. Simulation on Mutual Interference of Laser Radar in Road Environments [J]. Journal of System Simulation, 2022, 34(4): 891-900.
[9]	Liu Ruijun, Wang Xiangshang, Zhang Chen, Zhang Bohua. A Survey on Visual SLAM based on Deep Learning [J]. Journal of System Simulation, 2020, 32(7): 1244-1256.
[10]	Sun Shuifa, Li Zhun, Xia Kun, Shi Yunfei, Yang Jiquan, Dong Fangmin. Variable Scale Point Cloud Registration Algorithm [J]. Journal of System Simulation, 2018, 30(7): 2465-2474.
[11]	Zhang Yanguo, Li Qing. Multi-frame Fusion Method for Point Cloud of LiDAR Based on IMU [J]. Journal of System Simulation, 2018, 30(11): 4334-4339.
[12]	Zhang Hang, Chen Bin, Xue Hanzhang, Zhu Zhengqiu, Wang Rongxiao. Research on 3D Scene Modeling Based on UAV and LIDAR [J]. Journal of System Simulation, 2017, 29(9): 1914-1920.
[13]	Song Liang, Li Zhi, Ma Xingrui. LIDAR-Based Relative Position and Attitude Filtering for Unknown Targets [J]. Journal of System Simulation, 2017, 29(5): 1103-1111.
[14]	Jiang Bingchuan, Wan Gang, Li Feng, Zhang wei, Yang Zhenfa. Robotic Navigation Map Construction with Ultra-High Resolution Volumetric Grid [J]. Journal of System Simulation, 2017, 29(11): 2709-2717.
[15]	Xia Wenze, Han Shaokun, Cao Jingya. Simulation Technology Research on Streak Tube Imaging Lidar [J]. Journal of System Simulation, 2016, 28(12): 3027-3033.