Low-cost Light Detection And Ranging Research Articles

OR-LIM: Observability-aware robust LiDAR-inertial-mapping under high dynamic sensor motion

Light Detection And Ranging (LiDAR) technology has provided an impactful way to capture 3D data. However, consistent mapping in sensing-degenerated and perceptually-limited scenes (e.g. multi-story buildings) or under high dynamic sensor motion (e.g. rotating platform) remains a significant challenge. In this paper, we present OR-LIM, a novel observability-aware LiDAR-inertial-mapping system. Essentially, it combines a robust real-time LiDAR-inertial-odometry (LIO) module with an efficient surfel-map-smoothing (SMS) module that seamlessly optimizes the sensor poses and scene geometry at the same time. To improve robustness, the planar surfels are hierarchically generated and grown from point cloud maps to provide reliable correspondences for fixed-lag optimization. Moreover, the normals of surfels are analyzed for the observability evaluation of each frame. To maintain global consistency, a factor graph is utilized integrating the information from IMU propagation, LIO as well as the SMS. The system is extensively tested on the datasets collected by a low-cost multi-beam LiDAR (MBL) mounted on a rotating platform. The experiments with various settings of sensor motion, conducted on complex multi-story buildings and large-scale outdoor scenes, demonstrate the superior performance of our system over multiple state-of-the-art methods. The improvement of point accuracy reaches 3.39–13.6 % with an average 8.71 % outdoor and correspondingly 1.89–15.88 % with 9.09 % indoor, with reference to the collected Terrestrial Laser Scanning (TLS) map.

MFSCNN: APPENDING A MASKED BRANCH TO FAST-SCNN TO IMPROVE ROAD MARKING EXTRACTION ON SPARSE MLS POINT CLOUD-DERIVED IMAGES

Abstract. With the rise of self-driving cars, an increasing number of vehicles are equipped with low-cost light detection and ranging (LiDAR) sensors that could potentially serve as a massive mobile mapping resource, particularly for jobs that require multiple and frequent scanning, such as maintaining dynamic high-definition maps or digital twins. However, low-cost LiDAR sensors produce sparser point clouds during scanning which can make deep learning techniques for the automatic retrieval of features difficult like extracting road markings. In this work, we aim to improve the performance of a convolutional neural network (CNN) model for road marking extraction from sparse mobile LiDAR scanning (MLS) point cloud-derived images. We propose the modification of the Fast-SCNN model structure by adding a 2D convolution branch with masking in the feature fusion step: MFSCNN. To retain speed we only use MFSCNN to boost model training and still utilize Fast-SCNN for inference. Our results indicate potential, with a 4.6% increase in mean f1-score and an 8% decrease in uncertainty for the road marking class after multiple trials. Additionally, this research aims to support and increase research interest in lower-cost LiDARs for mobile mapping.

Potential of Low-Cost Light Detection and Ranging (LiDAR) Sensors: Case Studies for Enhancing Visitor Experience at a Science Museum

A low-cost light detection and ranging (LiDAR) device has several advantages including being able to perform a wide range of angle measurements, less privacy concerns, and robustness to illumination variance owing to its use of infrared (IR) light. In this study, to enhance the visitor experience at a science museum, three case studies using low-cost LiDAR sensors are presented: (1) an interactive floor projection to learn about the phases of the Moon; (2) an information kiosk with touchless interaction and visitor tracking; and (3) a visitor tracking box with horizontal and vertical scanning. The proposed kiosk system uses a mirror to reflect a portion of the scanning plane of the LiDAR sensor, to allow the capture of touchless interactions, track visitor positions, and count the number of nearby visitors. The visitor tracking box also uses two detection planes reflected by a mirror: the vertical plane is for counting visitors crossing the scanning plane and the horizontal plane is for tracking visitor positions to generate the corresponding heat maps for the visualization of museum hotspots. A series of evaluation experiments were conducted at a science museum, whereby an accuracy of 85% was obtained to estimate the number of visitors, with an accuracy increasing in counting people taller than 140 cm. The interactive floor received a visitor rating of 4.3–4.4 on a scale of 1–5.

Longitudinal Degradation of Pavement Marking Detectability for Mobile LiDAR Sensing Technology in Real-World Use

Recent advancements in vehicle automation and driver-assistance systems that detect pavement markings has increased the importance of the detectability of pavement markings through various sensor modalities across weather and road conditions. Among the sensing techniques, light detection and ranging (LiDAR) sensors have become popular for vehicle-automation applications. This study used low-cost mobile multi-beam LiDAR to assess the performance of several types of pavement marking materials installed on a limited-access highway in various conditions, and quantified the degradation in detection performance over three years. Four marking materials, HPS-8, polyurea, cold plastic, and sprayable thermoplastic, were analyzed in the current study. LiDAR reflectivity data extracted from a total of 210 passes through the test sections were analyzed. A new detectability score based on LiDAR intensity data was proposed to quantify the marking detectability. The results showed that the pavement marking detectability varied across the material types over the years. The results provide guidance for selecting materials and developing maintenance schedules when marking detectability by LiDAR is a concern.

Feasibility of Low-Cost LiDAR Scanner Implementation in Forest Sampling Techniques

Despite the growing impact of remote sensing technology in forest inventories globally, there is a continuous need for ground measurements on sample plots. Even though the newest volume assessment methodology requires fewer sample plots, the accuracy of ground-recorded data influences the final accuracy of forest stand modeling. Therefore, effective and economically justified tools are in the continuous interest of foresters. In the presented research, a consumer-grade light detection and ranging (LiDAR) sensor mounted on iPad was used for forest inventory sample plot data collection—including tree location and diameter breast height. In contrast to other similar research, feasibility and user-friendliness were also documented and emphasized. The study was conducted in 63 real sample plots used for the inventory of Polish forests. In total, 776 trees were scanned in 3 types of forest stands: pine, birch, and oak. The root mean square error was 0.28 m for tree locations and 0.06 m for diameter breast height. Various additional analyses were performed to describe the usage of an iPad in tree inventories. It was contended that low-cost LiDAR scanners might be successfully used in real forest conditions and can be considered a reliable and easy-to-implement tool in forest inventory measurements.

Comparative Analysis of SLAM Algorithms for Mechanical LiDAR and Solid-State LiDAR

With the advancement of light detection and ranging (LiDAR) technology in recent years, various new types of LiDAR have emerged, and the price of LiDAR equipment has gradually decreased. At present, low-cost solid-state LiDARs are gradually occupying the market. To evaluate the performance of two LIDARs for simultaneous localization and mapping. This study investigated the application of solid-state LiDAR and mechanical LiDAR in localization and mapping systems and comparatively analyzed their advantages and disadvantages. We selected some classic open-source algorithms [such as LiDAR odometry and mapping (A-LOAM)] to evaluate the performance of mechanical LiDAR and solid-state LiDAR in localization. The experimental data are adopted from some representative open-source data (such as KITTI data) and real data collected by Shenzhen University. The results showed that the localization accuracy of solid-state LiDAR was lower than that of mechanical LiDAR when the mobile robot moved to the corner and faced square to the wall at close range. Moreover, the localization accuracy of solid-state LiDAR was the same as or even higher than that of mechanical LiDAR when the mobile robots had small changes in the field of view (FOV) and the mobile robot moved along straight lines or other tracks.

Focal Combo Loss for Improved Road Marking Extraction of Sparse Mobile LiDAR Scanning Point Cloud-Derived Images Using Convolutional Neural Networks

Road markings are reflective features on roads that provide important information for safe and smooth driving. With the rise of autonomous vehicles (AV), it is necessary to represent them digitally, such as in high-definition (HD) maps generated by mobile mapping systems (MMSs). Unfortunately, MMSs are expensive, paving the way for the use of low-cost alternatives such as low-cost light detection and ranging (LiDAR) sensors. However, low-cost LiDAR sensors produce sparser point clouds than their survey-grade counterparts. This significantly reduces the capabilities of existing deep learning techniques in automatically extracting road markings, such as using convolutional neural networks (CNNs) to classify point cloud-derived imagery. A solution would be to provide a more suitable loss function to guide the CNN model during training to improve predictions. In this work, we propose a modified loss function—focal combo loss—that enhances the capability of a CNN to extract road markings from sparse point cloud-derived images in terms of accuracy, reliability, and versatility. Our results show that focal combo loss outperforms existing loss functions and CNN methods in road marking extractions in all three aspects, achieving the highest mean F1-score and the lowest uncertainty for the two distinct CNN models tested.

LiCaS3: A Simple LiDAR–Camera Self-Supervised Synchronization Method

Recent advances in robotics and deep learning demonstrate promising 3-D perception performances via fusing the light detection and ranging (LiDAR) sensor and camera data, where both spatial calibration and temporal synchronization are generally required. While the LiDAR–camera calibration problem has been actively studied during the past few years, LiDAR–camera synchronization has been less studied and mainly addressed by employing a conventional pipeline consisting of clock synchronization and temporal synchronization. The conventional pipeline has certain potential limitations, which have not been sufficiently addressed and could be a bottleneck for the potential wide adoption of low-cost LiDAR–camera platforms. Different from the conventional pipeline, in this article, we propose the LiCaS3, the first deep-learning-based framework, for the LiDAR–camera synchronization task via self-supervised learning. The proposed LiCaS3 does not require hardware synchronization or extra annotations and can be deployed both online and offline. Evaluated on both the KITTI and Newer College datasets, the proposed method shows promising performances. The code will be publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/KleinYuan/LiCaS3</uri> .

Extrinsic Calibration of Multiple 3D LiDAR Sensors by the Use of Planar Objects.

Three-dimensional light detection and ranging (LiDAR) sensors have received much attention in the field of autonomous navigation owing to their accurate, robust, and rich geometric information. Autonomous vehicles are typically equipped with multiple 3D LiDARs because there are many commercially available low-cost 3D LiDARs. Extrinsic calibration of multiple LiDAR sensors is essential in order to obtain consistent geometric information. This paper presents a systematic procedure for the extrinsic calibration of multiple 3D LiDAR sensors using plane objects. At least three independent planes are required within the common field of view of the LiDAR sensors. The planes satisfying the condition can easily be found on objects such as the ground, walls, or columns in indoor and outdoor environments. Therefore, the proposed method does not require environmental modifications such as using artificial calibration objects. Multiple LiDARs typically have different viewpoints to reduce blind spots. This situation increases the difficulty of the extrinsic calibration using conventional registration algorithms. We suggest a plane registration method for cases in which correspondences are not known. The entire calibration process can easily be automated using the proposed registration technique. The presented experimental results clearly show that the proposed method generates more accurate extrinsic parameters than conventional point cloud registration methods.

Integration Time and Time-Bin Width in Ranging Histograms for a Photon-Counting LiDAR

High-performance light detection and ranging (LiDAR) modules are highly demanded for advanced driving assistance system and autonomous driving. With CMOS-fabricated single-photon avalanche diodes (SPADs) and pulsed-operated semiconductor lasers, photon-counting based vehicle LiDARs are one of the most promising candidates for low-cost solution. The high data rate and the long integration time of SPAD LiDARs are two of main obstacles for realizing commercially affordable 3-D imagers. In this work, we develop an evaluation method for the minimum ranging time and investigate the time-bin width effect on the ranging precision. A simple formula for predicting the shortest integration time is proposed and compared with the experimental data. We also demonstrate that a proper time-bin width can reduce the data rate and required memory size without degrading the distance resolution. Our work paves the way for making low-cost vehicle LiDARs through system optimizing and engineering.

Estimating Leaf Water Content through Low-Cost LiDAR

In recent years, rapid development has been achieved in technologies and sensors related to autonomous driving and assistive technologies. In this study, low-cost light detection and ranging (LiDAR) was used to estimate leaf water content (LWC) by measuring LiDAR reflectance instead of morphological measurement (e.g., plant size), which is the conventional method. Experimental results suggest that reflection intensity can be corrected using the body temperature of LiDAR, when using reflection intensity observed by LiDAR. Comparisons of corrected LiDAR observation data and changes in reflectance attributed to leaf drying suggest that the reflectance increases with leaf drying in the 905 nm band observed with a hyperspectral camera. The LWC is estimated with an R2 of 0.950, RMSE of 6.78%, and MAPE of 18.6% using LiDAR reflectance. Although the 905 nm wavelength used by LiDAR is not the main water absorption band, the reflectance is closely related to the leaf structure; therefore, it is believed that the reflectance changes with structural changes accompanying drying, which allows for the indirect estimation of LWC. This can help utilize the reflectance of the 905 nm single-wavelength LiDAR, which, to the best of our knowledge has not been used in plant observations for estimating LWC.

3D-CSTM: A 3D continuous spatio-temporal mapping method

3D mapping is now essential for urban infrastructure resource monitoring, autonomous driving, and the fulfillment of digital earth. LiDAR-based Simultaneous Localization And Mapping (SLAM) technology has been widely studied because of its efficient application in the reconstruction of the 3D environments that benefitted from its sensor characteristic. However, the sparsity of low cost LiDAR (Light Detection And Ranging) sensor provides great challenge for it. Insufficient or poor distribution of the constraints as well as the motion distortion in one scan of point cloud would deteriorate the pose estimation in SLAM. In this paper, a novel 3D mapping method based only on the LiDAR data is proposed to enhance the performance of SLAM-based 3D point clouds map reconstruction. The proposed system consists of two main modules: localization module for rapid ego-motion estimation within the surrounding environment, and mapping module for accurate point clouds fusion. As for the localization, scan-to-map point cloud registration scheme are adopted where structural features are firstly extracted to provide valid correspondences. What’s more, an effective method is figured out to balance the cost factors for the optimization function of pose estimation in the process. This further handles the degenerated cases for cloud registration. Focusing on improving the quality of the map, a spline motion model is integrated with non-rigid point cloud fusion to facilitate the continuous and nonrepetitive mapping of the environment. Extensive experiments are carried out for the verification of our system including large-scale outdoor and long-corridor scenes. According to the experimental results, our system has achieved 0.78‰closure error and 27.5% improvement in the APE (Absolute Pose Errors), outperforming the state-of-the-art LiDAR-based SLAM (e.g. LeGO-LOAM) frameworks in our test sites. To specifically verify the performance of 3D mapping, the precision of 3D points is quantified through comparing with the high-precision point cloud maps collected by MLS (Mobile Laser Scanning) and TLS (Terrestrial Laser Scanning). The RMS of point-to-plane distances have improved 20% based on the fitted Weibull distribution. In addition, some ablation tests are conducted to reveal the efficacy of different components in our system.

A new range‐only measurement‐based glass line feature extraction method

This letter addresses a new range-only measurement-based glass line feature extraction method, which allows a low-cost light detection and ranging (LiDAR) sensor to detect glass-like objects without intensity and multi-echo data. The principle that the emitted LiDAR ray incidence angle with respect to a glass surface is close to 0° is concerned. The geometric relationship between the sensor and glass objects is also considered for successful glass feature extraction. The extracted features are accumulated and reformulated for the generation of glass line features using the RANdom SAmple Consensus algorithm (RANSAC). Two experiments with different robot paths were conducted in a glass environment. The results showed that the proposed method accurately represented glass objects without any false-positive glass feature.

Mobile 3D Mapping with a Low-Cost UAV-Based LIDAR System

Recently, many UAVs (unmanned aerial vehicles) based on LiDAR (light detection and ranging) systems have been developed for various purpose because of the effective of LIDAR technique and low-cost UAV. In this study, the accuracy of point clouds generated by the developed for a low-cost UAV-based LiDAR systems is evaluated. The system consisting of a multi-beam laser scanner- Velodyne VLP 16 and DJI M600 UAV. The experimental site is undulation with less object in Nagaoka city, Niigata Prefecture, Japan Twelve reflectance makers are arranged as ground control point for the positioning evaluating process. The observed data was collected on Nov. 8th, 2019 with three different flight height at 10m, 20m and 30m. For generating the point clouds, the mounting parameters and sensor parameters are combined. The generated point clouds are corrected by applying bias correction and the 7 parameters transformation. The result is validated using three different experimental setups with three various flight height which indicate that the most accurate and reliable results are obtained. As a result, the point clouds after calibrating attained an accuracy of approximate 0.2 m in vertical and horizontal for both correction methods. In conclusion, the point cloud accuracy is not good enough for generating the topographic map at large scale. However, the stable results and the present accuracy are good for other purposes with less accuracy requirement such as monitoring the crop growth.

A LiDAR Sensor-Based Spray Boom Height Detection Method and the Corresponding Experimental Validation.

Sprayer boom height (Hb) variations affect the deposition and distribution of droplets. An Hb control system is used to adjust Hb to maintain an optimum distance between the boom and the crop canopy, and an Hb detection sensor is a key component of the Hb control system. This study presents a new, low-cost light detection and ranging (LiDAR) sensor for Hb detection developed based on the principle of single-point ranging. To examine the detection performance of the LiDAR sensor, a step height detection experiment, a field ground detection experiment, and a wheat stubble (WS) height detection experiment as well as a comparison with an ultrasonic sensor were performed. The results showed that the LiDAR sensor could be used to detect Hb. When used to detect the WS height (HWS), the LiDAR sensor primarily detected the WS roots and the inside of the WS canopy. HWS and movement speed of the LiDAR sensor (VLiDAR) has a greater impact on the detection performance of the LiDAR sensor for the WS canopy than that for the WS roots. The detection error of the LiDAR sensor for the WS roots is less than 5.00%, and the detection error of the LiDAR sensor for the WS canopy is greater than 8.00%. The detection value from the LiDAR sensor to the WS root multiplied by 1.05 can be used as a reference basis for adjusting Hb, and after the WS canopy height is added to the basis, the value can be used as an index for adjusting Hb in WS field spraying. The results of this study will promote research on the boom height detection method and autonomous Hb control system.

FAST-FUSION: An Improved Accuracy Omnidirectional Visual Odometry System with Sensor Fusion and GPU Optimization for Embedded Low Cost Hardware

The main task while developing a mobile robot is to achieve accurate and robust navigation in a given environment. To achieve such a goal, the ability of the robot to localize itself is crucial. In outdoor, namely agricultural environments, this task becomes a real challenge because odometry is not always usable and global navigation satellite systems (GNSS) signals are blocked or significantly degraded. To answer this challenge, this work presents a solution for outdoor localization based on an omnidirectional visual odometry technique fused with a gyroscope and a low cost planar light detection and ranging (LIDAR), that is optimized to run in a low cost graphical processing unit (GPU). This solution, named FAST-FUSION, proposes to the scientific community three core contributions. The first contribution is an extension to the state-of-the-art monocular visual odometry (Libviso2) to work with omnidirectional cameras and single axis gyro to increase the system accuracy. The second contribution, it is an algorithm that considers low cost LIDAR data to estimate the motion scale and solve the limitations of monocular visual odometer systems. Finally, we propose an heterogeneous computing optimization that considers a Raspberry Pi GPU to improve the visual odometry runtime performance in low cost platforms. To test and evaluate FAST-FUSION, we created three open-source datasets in an outdoor environment. Results shows that FAST-FUSION is acceptable to run in real-time in low cost hardware and that outperforms the original Libviso2 approach in terms of time performance and motion estimation accuracy.

Frequency-multiplexing photon-counting multi-beam LiDAR

We report a frequency-multiplexing method for multi-beam photon-counting light detection and ranging (LiDAR), where only one single-pixel single-photon detector is employed to simultaneously detect the multi-beam echoes. In this frequency-multiplexing multi-beam LiDAR, each beam is from an independent laser source with different repetition rates and independent phases. As a result, the photon counts from different beams could be discriminated from each other due to the strong correlation between the laser pulses and their respective echo photons. A 16-beam LiDAR system was demonstrated in three-dimensional laser imaging with 16 pulsed laser diodes at 850 nm and one single-photon detector based on a Si-avalanche photodiode. This frequency-multiplexing method can greatly reduce the number of single-photon detectors in multi-beam LiDAR systems, which may be useful for low-cost and eye-safe LiDAR applications.

NRLI-UAV: Non-rigid registration of sequential raw laser scans and images for low-cost UAV LiDAR point cloud quality improvement

Accurate registration of light detection and ranging (LiDAR) point clouds and images is a prerequisite for integrating the spectral and geometrical information collected by low-cost unmanned aerial vehicle (UAV) systems. Most registration approaches take the directly georeferenced LiDAR point cloud as a rigid body, based on the assumption that the high-precision positioning and orientation system (POS) in the LiDAR system provides sufficient precision, and that the POS errors are negligible. However, due to the large errors of the low-precision POSs commonly used in the low-cost UAV LiDAR systems (ULSs), dramatic deformation may exist in the directly georeferenced ULS point cloud, resulting in non-rigid transformation between the images and the deformed ULS point cloud. As a result, registration may fail when using a rigid transformation between the images and the directly georeferenced LiDAR point clouds. To address this problem, we proposed NRLI-UAV, which is a non-rigid registration method for registration of sequential raw laser scans and images collected by low-cost UAV systems. NRLI-UAV is a two-step registration method that exploits trajectory correction and discrepancy minimization between the depths derived from structure from motion (SfM) and the raw laser scans to achieve LiDAR point cloud quality improvement. Firstly, the coarse registration procedure utilizes global navigation satellite system (GNSS) and inertial measurement unit (IMU)-aided SfM to obtain accurate image orientation and corrects the errors of the low-precision POS. Secondly, the fine registration procedure transforms the original 2D-3D registration to 3D-3D registration. This is performed by setting the oriented images as the reference, and iteratively minimizing the discrepancy between the depth maps derived from SfM and the raw laser scans, resulting in accurate registration between the images and the LiDAR point clouds. In addition, an improved LiDAR point cloud is generated in the mapping frame. Experiments were conducted with data collected by a low-cost UAV system in three challenging scenes to evaluate NRLI-UAV. The final registration errors of the images and the LiDAR point cloud are less than one pixel in image space and less than 0.13 m in object space. The LiDAR point cloud quality was also evaluated by plane fitting, and the results show that the LiDAR point cloud quality is improved by 8.8 times from 0.45 m (root-mean-square error [RMSE] of plane fitting) to 0.05 m (RMSE of plane fitting) using NRLI-UAV, demonstrating a high level of automation, robustness, and accuracy.

A Simultaneous Localization and Mapping (SLAM) Framework for 2.5D Map Building Based on Low-Cost LiDAR and Vision Fusion

The method of simultaneous localization and mapping (SLAM) using a light detection and ranging (LiDAR) sensor is commonly adopted for robot navigation. However, consumer robots are price sensitive and often have to use low-cost sensors. Due to the poor performance of a low-cost LiDAR, error accumulates rapidly while SLAM, and it may cause a huge error for building a larger map. To cope with this problem, this paper proposes a new graph optimization-based SLAM framework through the combination of low-cost LiDAR sensor and vision sensor. In the SLAM framework, a new cost-function considering both scan and image data is proposed, and the Bag of Words (BoW) model with visual features is applied for loop close detection. A 2.5D map presenting both obstacles and vision features is also proposed, as well as a fast relocation method with the map. Experiments were taken on a service robot equipped with a 360° low-cost LiDAR and a front-view RGB-D camera in the real indoor scene. The results show that the proposed method has better performance than using LiDAR or camera only, while the relocation speed with our 2.5D map is much faster than with traditional grid map.

Probabilistic Prediction of Pedestrian Crossing Intention Using Roadside LiDAR Data

Pedestrians are vulnerable road users that need proactive protection. While both autonomous and connected vehicle technologies aim to deliver greater safety benefits, current designs heavily rely on vehicle-based or on-board sensors and lack strategic real-time interactions with pedestrians who do not have any communication means. As pedestrians are passively protected by the system, they might be put into hazardous situations when vehicle-mounted sensors fail to detect their presence. This paper is part of ongoing research that uses roadside light detection and ranging (LiDAR) sensors to develop a human-in-the-loop system that brings pedestrians into the connected environment. To proactively protect pedestrians, accurate prediction of their intention for crossings at locations, such as unsignalized intersections and street mid-blocks is critical, and this paper presents a modified Naive Bayes approach for this purpose. It features a probabilistic approach to overcoming the common deficiencies in deterministic methods and provides valuable comparisons between feature-based data processing methods, such as artificial neural network (ANN) and model-based Naive Bayes approach. A case study was conducted by using a low-cost 16-line LiDAR sensor installed at the roadside. Pedestrians' crossing intention was predicted at a range of 0.5-3 s before actual crossings. The results satisfactorily demonstrated the properties of the modified Naive Bayes model, as well as its higher flexibility, compared with the ANN approaches in practice.