CHUNG S H , LEE S W , LEE S K , et al . LIDAR system with electromagnetic two-axis scanning micromirror based on indirect time-of-flight method [J ] . Micro and Nano Systems Letters , 2019 , 7 ( 1 ): 1 - 5 . DOI: 10.1186/s40486-019-0080-y http://doi.org/10.1186/s40486-019-0080-y

FAYYAD J , JARADAT M A , GRUYER D , et al . Deep learning sensor fusion for autonomous vehicle perception and localization: a review [J ] . Sensors , 2020 , 20 ( 15 ): 4220 . DOI: 10.3390/s20154220 http://doi.org/10.3390/s20154220 https://www.mdpi.com/1424-8220/20/15/4220 https://www.mdpi.com/1424-8220/20/15/4220 Autonomous vehicles (AV) are expected to improve, reshape, and revolutionize the future of ground transportation. It is anticipated that ordinary vehicles will one day be replaced with smart vehicles that are able to make decisions and perform driving tasks on their own. In order to achieve this objective, self-driving vehicles are equipped with sensors that are used to sense and perceive both their surroundings and the faraway environment, using further advances in communication technologies, such as 5G. In the meantime, local perception, as with human beings, will continue to be an effective means for controlling the vehicle at short range. In the other hand, extended perception allows for anticipation of distant events and produces smarter behavior to guide the vehicle to its destination while respecting a set of criteria (safety, energy management, traffic optimization, comfort). In spite of the remarkable advancements of sensor technologies in terms of their effectiveness and applicability for AV systems in recent years, sensors can still fail because of noise, ambient conditions, or manufacturing defects, among other factors; hence, it is not advisable to rely on a single sensor for any of the autonomous driving tasks. The practical solution is to incorporate multiple competitive and complementary sensors that work synergistically to overcome their individual shortcomings. This article provides a comprehensive review of the state-of-the-art methods utilized to improve the performance of AV systems in short-range or local vehicle environments. Specifically, it focuses on recent studies that use deep learning sensor fusion algorithms for perception, localization, and mapping. The article concludes by highlighting some of the current trends and possible future research directions.

SHI C H , WANG C Y , LIU X L , et al . Three-dimensional point cloud denoising via a gravitational feature function [J ] . Applied Optics , 2022 , 61 ( 6 ): 1331 - 1343 . DOI: 10.1364/AO.446913 http://doi.org/10.1364/AO.446913 https://opg.optica.org/abstract.cfm?URI=ao-61-6-1331 https://opg.optica.org/abstract.cfm?URI=ao-61-6-1331 Point cloud noise is inevitable in the LiDAR scanning of objects and affects measurement accuracy and integrity. To minimize such noise, we propose a gravitational feature function-based point cloud denoising algorithm and a universal gravitation formula for a point cloud. First, we calculate the point cloud barycenter (i.e., the position of the average mass distribution) and the spherical neighborhood of points in terms of the distribution of the point cloud in three-dimensional space. Next, using the proposed formula, we calculate the gravitational forces between the barycenter and the spherical neighborhood of all points. We then combine all of the gravitational forces into a gravitational feature function and filter the noises in the point cloud using a gravitational feature-function threshold. This novel algorithm, to the best of our knowledge, effectively removes drift noises and takes into account the local and global structure of point clouds. Finally, we demonstrate the effectiveness of the algorithm through extensive experiments in which sparse, dense, and mixed noises are removed.

RUSU R B , MARTON Z C , BLODOW N , et al . Towards 3D point cloud based object maps for household environments [J ] . Robotics and Autonomous Systems , 2008 , 56 ( 11 ): 927 - 941 . DOI: 10.1016/j.robot.2008.08.005 http://doi.org/10.1016/j.robot.2008.08.005 https://linkinghub.elsevier.com/retrieve/pii/S0921889008001140 https://linkinghub.elsevier.com/retrieve/pii/S0921889008001140

李朋超 , 王金涛 , 宋吉来 . 基于PCL的3D点云视觉数据预处理 [J ] . 计算机应用 , 2019 , 39 ( 增刊2 ): 227 - 230 .

LI P C , WANG J T , SONG J L . PCL-based preprocessing for point cloud data of 3D vision [J ] . Journal of Computer Applications , 2019 , 39 ( S2 ): 227 - 230 . (in Chinese)

JULIE D , CARLO D F . The bilateral filter for point clouds [J ] . Image Processing on Line , 2017 , 7 : 278 - 287 . DOI: 10.5201/ipol http://doi.org/10.5201/ipol https://www.ipol.im/?utm_source=doi https://www.ipol.im/?utm_source=doi

TIZIANA C , ALESSANDRO D , GAETANO S , et al . VIPDA: a visually driven point cloud denoising algorithm based on anisotropic point cloud filtering [J ] . Frontiers in Signal Processing , 2022 , 2 : 842570 . DOI: 10.3389/frsip.2022.842570 http://doi.org/10.3389/frsip.2022.842570 https://www.frontiersin.org/articles/10.3389/frsip.2022.842570/full https://www.frontiersin.org/articles/10.3389/frsip.2022.842570/full Point clouds (PCs) provide fundamental tools for digital representation of 3D surfaces, which have a growing interest in recent applications, such as e-health or autonomous means of transport. However, the estimation of 3D coordinates on the surface as well as the signal defined on the surface points (vertices) is affected by noise. The presence of perturbations can jeopardize the application of PCs in real scenarios. Here, we propose a novel visually driven point cloud denoising algorithm (VIPDA) inspired by visually driven filtering approaches. VIPDA leverages recent results on local harmonic angular filters extending image processing tools to the PC domain. In more detail, the VIPDA method applies a harmonic angular analysis of the PC shape so as to associate each vertex of the PC to suit a set of neighbors and to drive the denoising in accordance with the local PC variability. The performance of VIPDA is assessed by numerical simulations on synthetic and real data corrupted by Gaussian noise. We also compare our results with state-of-the-art methods, and we verify that VIPDA outperforms the others in terms of the signal-to-noise ratio (SNR). We demonstrate that our method has strong potential in denoising the point clouds by leveraging a visually driven approach to the analysis of 3D surfaces.

霍健 , 陈慧敏 , 马云飞 , 等 . 基于MEMS激光雷达的车辆目标识别算法 [J ] . 兵工学报 , 2023 , 44 ( 4 ): 940 - 948 .

HUO J , CHEN H M , MA Y F , et al. Vehicle targets recognition algorithm based on MEMS lidar [J ] . Acta Armamentarii , 2023 , 44 ( 4 ): 940 - 948 . (in Chinese)

LIU X Q , CHEN Y M , CHENG L , et al . Airborne laser scanning point clouds filtering method based on the construction of virtual ground seed points [J ] . Journal of Applied Remote Sensing , 2017 , 11 ( 1 ): 016032 . DOI: 10.1117/1.JRS.11.016032 http://doi.org/10.1117/1.JRS.11.016032 http://remotesensing.spiedigitallibrary.org/article.aspx?doi=10.1117/1.JRS.11.016032 http://remotesensing.spiedigitallibrary.org/article.aspx?doi=10.1117/1.JRS.11.016032

焦亚男 , 马杰 , 钟斌斌 . 一种基于尺度变化的点云并行去噪方法 [J ] . 武汉大学学报(工学版) , 2021 , 54 ( 3 ): 277 - 282 .

JIAO Y N , MA J , ZHONG B B . Point cloud parallel de-noising algorithms based on scale change [J ] . Engineering Journal of Wuhan University , 2021 , 54 ( 3 ): 277 - 282 . (in Chinese)

赵鹏 , 柴会轩 . 基于不同尺度算法的激光雷达点云去噪研究 [J ] . 应用激光 , 2023 , 43 ( 1 ): 66 - 75 .

ZHAO P , CHAI H X . Research on lidar point cloud denoising based on different scale algorithm [J ] . Applied Laser , 2023 , 43 ( 1 ): 66 - 75 . (in Chinese)

韩东升 , 徐茂林 , 金远航 . 多源异构点云配准数据的滤波及精度分析 [J ] . 测绘科学技术学报 , 2020 , 37 ( 5 ): 503 - 509 .

HAN D S , XU M L , JIN Y H . Filtering and accuracy analysis of multi-source heterogeneous point cloud registration data [J ] . Journal of Geomatics Science and Technology , 2020 , 37 ( 5 ): 503 - 509 . (in Chinese)

ZHENG Z , ZHA B T , ZHOU Y , et al . Single-stage adaptive multi-scale point cloud noise filtering algorithm based on feature information [J ] . Remote Sensing , 2022 , 14 ( 2 ): 367 . DOI: 10.3390/rs14020367 http://doi.org/10.3390/rs14020367 https://www.mdpi.com/2072-4292/14/2/367 https://www.mdpi.com/2072-4292/14/2/367 This paper proposes a single-stage adaptive multi-scale noise filtering algorithm for point clouds, based on feature information, which aims to mitigate the fact that the current laser point cloud noise filtering algorithm has difficulty quickly completing the single-stage adaptive filtering of multi-scale noise. The feature information from each point of the point cloud is obtained based on the efficient k-dimensional (k-d) tree data structure and amended normal vector estimation methods, and the adaptive threshold is used to divide the point cloud into large-scale noise, a feature-rich region, and a flat region to reduce the computational time. The large-scale noise is removed directly, the feature-rich and flat regions are filtered via improved bilateral filtering algorithm and weighted average filtering algorithm based on grey relational analysis, respectively. Simulation results show that the proposed algorithm performs better than the state-of-art comparison algorithms. It was, thus, verified that the algorithm proposed in this paper can quickly and adaptively (i) filter out large-scale noise, (ii) smooth small-scale noise, and (iii) effectively maintain the geometric features of the point cloud. The developed algorithm provides research thought for filtering pre-processing methods applicable in 3D measurements, remote sensing, and target recognition based on point clouds.

刘大峰 , 廖文和 , 戴宁 , 等 . 散乱点云去噪算法的研究与实现 [J ] . 东南大学学报(自然科学版) , 2007 , 37 ( 6 ): 1108 - 1112 .

LIU D F , LIAO W H , DAI N , et al . Research and implementation for denoising noisy scattered point data [J ] . Journal of Southeast University(Natural Science Edition ), 2007 , 37 ( 6 ): 1108 - 1113 . (in Chinese)

周圣涛 . 基于多核的DSP的点云数据快速降噪技术研究 [D ] . 长春 : 长春理工大学 , 2020 .

ZHOU S T . Research on fast noise reduction technology of point cloud data based on multi-core DSP [D ] . Changchun : Changchun University of Science and Technology , 2020 . (in Chinese)

张彬 , 熊传兵 . 基于体素下采样和关键点提取的点云自动配准 [J ] . 激光与光电子学进展 , 2020 , 57 ( 4 ): 101 - 109 .

ZHANG B , XIONG C B . Automatic point cloud registration based on voxel downsampling and key point extraction [J ] . Laser & Optoelectronics Progress , 2020 , 57 ( 4 ): 101 - 109 . (in Chinese)

李仁忠 , 杨曼 , 冉媛 , 等 . 基于方法库的点云去噪与精简算法 [J ] . 激光与光电子学进展 , 2018 , 55 ( 1 ): 243 - 249 .

LI R Z , YANG M , RAN Y , et al . Point cloud denoising and simplification algorithm based on method library [J ] . Laser & Optoelectronics Progress , 2018 , 55 ( 1 ): 243 - 249 . (in Chinese)

朱志华 , 刘晋 , 胡晰远 . 线形痕迹三维点云去噪技术研究 [J ] . 刑事技术 , 2020 , 45 ( 6 ): 556 - 561 . DOI: 10.16467/j.1008-3650.2020.06.002 http://doi.org/10.16467/j.1008-3650.2020.06.002 目的 通过对采集到的线形痕迹的三维点云数据进行去噪处理研究,为后续点云数据的特征提取和匹配提供良好的依据。方法 针对共聚焦显微镜采集的10种常见工具痕迹的点云数据,实验了均值滤波、中值滤波、曲率滤波三种点云数据去噪的滤波算法,通过对这三种算法处理结果的分析,提出了融合这三种滤波的线形痕迹三维点云数据去噪算法。结果 测试样本在去噪后,点云特征更加显著,经过计算滤波后点云、带噪声点云与标准点云的误差值,可以发现最大误差平均减少了79.6%。结论 融合后的去噪算法利用了三种滤波器各自的优势,在针对工具的线形痕迹点云的去噪实验中取得了比单独采用三种滤波方法更好的效果。

ZHU Z H , LIU J , HU X Y . Attempt to denoise into 3D-point cloud of linear trace [J ] . Forensic Science and Technology , 2020 , 45 ( 6 ): 556 - 561 . (in Chinese) DOI: 10.16467/j.1008-3650.2020.06.002 http://doi.org/10.16467/j.1008-3650.2020.06.002 <strong>Objective</strong> To tentatively denoise into the 3D-point cloud data collected from linear traces so as to provide basis or reference for the successive feature extraction and matching against the point cloud data. <strong>Methods</strong> Through denoising into the point cloud data of 10 kinds of common-tool traces collected via confocal microscope, three filtering algorithms, i.e., the mean, median and curvature, were tested of their effect with evaluation. Based on the processing results of the three algorithms, a denoising algorithm of three-dimensional point-cloud data was proposed for the involving linear traces, having successfully resulted in such an integrative arithmetic that was built with the three algorithms from being weighted. <strong>Results</strong> The tested results showed that the post-denoising sample, processed from the integrated algorithm, did demonstrate more distinct features exhibiting the pattern of point cloud, having rendered the maximal average error decreasing by 79.6% against the noise-harboring and/or standard point cloud data. <strong>Conclusions</strong> The integration of three filtering algorithms optimizes the preponderance of each individual, achieving better performance than each single one of the three choices for the point-cloud data of trace to deniose.

LIU D , LI D J , WANG M Z , et al . 3D change detection using adaptive thresholds based on local point cloud density [J ] . ISPRS International Journal of Geo-Information , 2021 , 10 ( 3 ): 127 . DOI: 10.3390/ijgi10030127 http://doi.org/10.3390/ijgi10030127 https://www.mdpi.com/2220-9964/10/3/127 https://www.mdpi.com/2220-9964/10/3/127 In recent years, because of highly developed LiDAR (Light Detection and Ranging) technologies, there has been increasing demand for 3D change detection in urban monitoring, urban model updating, and disaster assessment. In order to improve the effectiveness of 3D change detection based on point clouds, an approach for 3D change detection using point-based comparison is presented in this paper. To avoid density variation in point clouds, adaptive thresholds are calculated through the k-neighboring average distance and the local point cloud density. A series of experiments for quantitative evaluation is performed. In the experiments, the influencing factors including threshold, registration error, and neighboring number of 3D change detection are discussed and analyzed. The results of the experiments demonstrate that the approach using adaptive thresholds based on local point cloud density are effective and suitable.

MUNARO M , RUDU R B , EMANUELE M . 3D robot perception with Point cloud library [J ] . Robotics and Autonomous Systems , 2016 , 78 : 97 - 99 . DOI: 10.1016/j.robot.2015.12.008 http://doi.org/10.1016/j.robot.2015.12.008 https://linkinghub.elsevier.com/retrieve/pii/S0921889015003176 https://linkinghub.elsevier.com/retrieve/pii/S0921889015003176

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 . DOI: 10.1177/0278364913491297 http://doi.org/10.1177/0278364913491297 http://journals.sagepub.com/doi/10.1177/0278364913491297 http://journals.sagepub.com/doi/10.1177/0278364913491297 We present a novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research. In total, we recorded 6 hours of traffic scenarios at 10–100 Hz using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras, a Velodyne 3D laser scanner and a high-precision GPS/IMU inertial navigation system. The scenarios are diverse, capturing real-world traffic situations, and range from freeways over rural areas to inner-city scenes with many static and dynamic objects. Our data is calibrated, synchronized and timestamped, and we provide the rectified and raw image sequences. Our dataset also contains object labels in the form of 3D tracklets, and we provide online benchmarks for stereo, optical flow, object detection and other tasks. This paper describes our recording platform, the data format and the utilities that we provide.