Analysis of UAS-LiDAR Ground Points Classification in Agricultural Fields Using Traditional Algorithms and PointCNN

Efficient tree modeling from airborne LiDAR point clouds

Chapter 5 - Data Preprocessing and Feature Extraction

A Light Detection and Ranging (LiDAR) sensor mounted on an Unmanned Aerial Vehicle (UAV) can map the overflown environment in point clouds. Mapped canopy heights allow for the estimation of crop biomass in agriculture. The work presented in this paper contributes to sensory UAV setup design for mapping and textual analysis of agricultural fields. LiDAR data are combined with data from Global Navigation Satellite System (GNSS) and Inertial Measurement Unit (IMU) sensors to conduct environment mapping for point clouds. The proposed method facilitates LiDAR recordings in an experimental winter wheat field. Crop height estimates ranging from 0.35–0.58 m are correlated to the applied nitrogen treatments of 0–300 . The LiDAR point clouds are recorded, mapped, and analysed using the functionalities of the Robot Operating System (ROS) and the Point Cloud Library (PCL). Crop volume estimation is based on a voxel grid with a spatial resolution of 0.04 × 0.04 × 0.001 m. Two different flight patterns are evaluated at an altitude of 6 m to determine the impacts of the mapped LiDAR measurements on crop volume estimations.

This paper presents a new algorithm for building an indoor map by integrating point clouds of 2D light detection and ranging (LIDAR) scanners in indoor environments. Iterative closest point (ICP) algorithm is one of the well-known methods for such purpose and often used for mobile robot SLAM. However, the algorithm is designed based on dense (or continuous) measurement of the same space with known relative positions of measurement points and angles, and it does not often work efficiently if the measurement is sparse and/or LIDAR locations are unknown. Such situations are seen when some installed LIDARs in a room are used to build a background indoor map for object tracking, or mobile LIDARs are used by technicians to build a digital indoor map, where each space is captured only at a few locations with different angles. To tackle this issue, our method extracts line segments and edge points as features from given LIDAR point clouds and finds shape coincidences commonly contained in a pair of given point clouds to identify positional relationships between LIDARs. By this information, these point clouds can be integrated into common 2D coordinates. Indoor map generation is realized by sequentially applying this integration procedure to every pair of point clouds. Also, the experiments on real data show that our method can identify the relative positions of LIDARs with 10cm-order errors in average, and by sequentially applying the point-cloud integration, the generated maps have only 3% errors.

Plant height is a morphological characteristic of plant growth that is a useful indicator of plant stress resulting from water and nutrient deficit. While height is a relatively simple trait, it can be difficult to measure accurately, especially in crops with complex canopy architectures like cotton. This paper describes the deployment of four nadir view ultrasonic transducers (UTs), two light detection and ranging (LiDAR) systems, and an unmanned aerial system (UAS) with a digital color camera to characterize plant height in an upland cotton breeding trial. The comparison of the UTs with manual measurements demonstrated that the Honeywell and Pepperl+Fuchs sensors provided more precise estimates of plant height than the MaxSonar and db3 Pulsar sensors. Performance of the multi-angle view LiDAR and UAS technologies demonstrated that the UAS derived 3-D point clouds had stronger correlations (0.980) with the UTs than the proximal LiDAR sensors. As manual measurements require increased time and labor in large breeding trials and are prone to human error reducing repeatability, UT and UAS technologies are an efficient and effective means of characterizing cotton plant height.

By LIDAR raw data to obtain high-precision digital elevation model, the first and most important step is to carry out the filtering of point cloud data, which is the key step of point cloud data generating to the digital terrain model (DTM). The algorithm in the article carries the special space index out to the point cloud, and builds the topology relation between the points. Organize the Light Detection and Ranging (LIDAR) cloud point used quadtree. The algorithm is based on stream and judge the ground point with the principle of slope and the point under the triangle. LIDAR data in ANYANG for the study area are used to test the algorithm. Results show that the method can efficiently extract ground points from LIDAR points cloud on urban area.

3D Modeling Approach of Building Construction based on Point Cloud Data Using LiDAR Byeongjun Oh, Minju Kim, Chanwoo Lee, Hunhee Cho and Kyung-In Kang Pages 906-912 (2019 Proceedings of the 36th ISARC, Banff, Canada, ISBN 978-952-69524-0-6, ISSN 2413-5844) Abstract: LiDAR (Light Detection and Ranging) emerges as a mapping technology that provides fast, accurate, and reliable data with geometric representation of construction facilities. The technology has received high recognition especially since the importance of digital transformation in construction projects has been emphasized. However, the current state of 3D technologies including LiDAR encounters difficulty in recognizing and extracting accurate information on the as-built status of the buildings and construction sites. As a preliminary study for the development of a 3D architectural geometric representation of building and environment, this paper proposes a 3D modeling approach based on point cloud data obtained by LiDAR technology. This paper suggests a novel method for data acquisition on as-built status of construction sites and buildings during construction-operation phases. Furthermore, a field test has been performed for visualizing and modeling of the indoors of a residential house. The results of this paper are expected to inaugurate adaptation of LiDAR technology during the as-built process, and further implementation of digital technology after construction phase in construction projects. Keywords: LiDAR; 3D modeling; building construction; digital transformation; point cloud data DOI: https://doi.org/10.22260/ISARC2019/0121 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley

Differential LiDAR (Light Detection and Ranging) from repeated surveys has recently emerged as an effective tool to measure three-dimensional (3D) change for applications, such as quantifying slip and spatially distributed warping associated with earthquake ruptures, and examining the spatial distribution of beach erosion after hurricane impact. Currently, the primary method for determining 3D change from LiDAR is through the use of the iterative closest point (ICP) algorithm and its variants. However, all current studies using ICP have assumed that all LiDAR points in the compared point clouds have uniform accuracy. This assumption is simplistic given that the error for each LiDAR point is variable, and dependent upon time varying factors such as target range, angle of incidence, and aircraft trajectory accuracy. Therefore, to rigorously determine spatial change, it would be ideal to model the random error for every LiDAR observation in the differential point cloud, and use these error estimates as apriori weights in the ICP algorithm. To test this approach, we implemented a rigorous LiDAR observation error propagation method to generate estimated random error for each point in a LiDAR point cloud, and then determine 3D displacements between two point clouds using an anisotropic weighted ICP (A-ICP) algorithm. The algorithm was evaluated by qualitatively and quantitatively comparing point clouds with synthetic fault ruptures between a uniform weight and anistropically weighted ICP algorithm. Then post-earthquake slip is estimated for the 2010 El Mayor-Cucapah Earthquake (EMC), using pre- and post-event LiDAR. Based on the analysis, Moving Window A-ICP is able to better estimate the synthetic surface ruptures, and provides a smoother estimate of actual displacement for the EMC earthquake.

Information on a crop’s three-dimensional (3D) structure is important for plant phenotyping and precision agriculture (PA). Currently, light detection and ranging (LiDAR) has been proven to be the most effective tool for crop 3D characterization in constrained, e.g., indoor environments, using terrestrial laser scanners (TLSs). In recent years, affordable laser scanners onboard unmanned aerial systems (UASs) have been available for commercial applications. UAS laser scanners (ULSs) have recently been introduced, and their operational procedures are not well investigated particularly in an agricultural context for multi-temporal point clouds. To acquire seamless quality point clouds, ULS operational parameter assessment, e.g., flight altitude, pulse repetition rate (PRR), and the number of return laser echoes, becomes a non-trivial concern. This article therefore aims to investigate DJI Zenmuse L1 operational practices in an agricultural context using traditional point density, and multi-temporal canopy height modeling (CHM) techniques, in comparison with more advanced simulated full waveform (WF) analysis. Several pre-designed ULS flights were conducted over an experimental research site in Fargo, North Dakota, USA, on three dates. The flight altitudes varied from 50 m to 60 m above ground level (AGL) along with scanning modes, e.g., repetitive/non-repetitive, frequency modes 160/250 kHz, return echo modes (1n), (2n), and (3n), were assessed over diverse crop environments, e.g., dry corn, green corn, sunflower, soybean, and sugar beet, near to harvest yet with changing phenological stages. Our results showed that the return echo mode (2n) captures the canopy height better than the (1n) and (3n) modes, whereas (1n) provides the highest canopy penetration at 250 kHz compared with 160 kHz. Overall, the multi-temporal CHM heights were well correlated with the in situ height measurements with an R2 (0.99–1.00) and root mean square error (RMSE) of (0.04–0.09) m. Among all the crops, the multi-temporal CHM of the soybeans showed the lowest height correlation with the R2 (0.59–0.75) and RMSE (0.05–0.07) m. We showed that the weaker height correlation for the soybeans occurred due to the selective height underestimation of short crops influenced by crop phonologies. The results explained that the return echo mode, PRR, flight altitude, and multi-temporal CHM analysis were unable to completely decipher the ULS operational practices and phenological impact on acquired point clouds. For the first time in an agricultural context, we investigated and showed that crop phenology has a meaningful impact on acquired multi-temporal ULS point clouds compared with ULS operational practices revealed by WF analyses. Nonetheless, the present study established a state-of-the-art benchmark framework for ULS operational parameter optimization and 3D crop characterization using ULS multi-temporal simulated WF datasets.

Routine bridge inspections require labor intensive and highly subjective visual interpretation to determine bridge deck surface condition. Light Detection and Ranging (LiDAR) a relatively new class of survey instrument has become a popular and increasingly used technology for providing as-built and inventory data in civil applications. While an increasing number of private and governmental agencies possess terrestrial and mobile LiDAR systems, an understanding of the technology’s capabilities and potential applications continues to evolve. LiDAR is a line-of-sight instrument and as such, care must be taken when establishing scan locations and resolution to allow the capture of data at an adequate resolution for defining features that contribute to the analysis of bridge deck surface condition. Information such as the location, area, and volume of spalling on deck surfaces, undersides, and support columns can be derived from properly collected LiDAR point clouds. The LiDAR point clouds contain information that can provide quantitative surface condition information, resulting in more accurate structural health monitoring. LiDAR scans were collected at three study bridges, each of which displayed a varying degree of degradation. A variety of commercially available analysis tools and an independently developed algorithm written in ArcGIS Python (ArcPy) were used to locate and quantify surface defects such as location, volume, and area of spalls. The results were visual and numerically displayed in a user-friendly web-based decision support tool integrating prior bridge condition metrics for comparison. LiDAR data processing procedures along with strengths and limitations of point clouds for defining features useful for assessing bridge deck condition are discussed. Point cloud density and incidence angle are two attributes that must be managed carefully to ensure data collected are of high quality and useful for bridge condition evaluation. When collected properly to ensure effective evaluation of bridge surface condition, LiDAR data can be analyzed to provide a useful data set from which to derive bridge deck condition information.

Robust multi-task learning network for complex LiDAR point cloud data preprocessing

The intelligent road is an important component of the intelligent vehicle infrastructure cooperative system, the latest development of intelligent transportation systems. As an advanced sensor, Light Detection and Ranging (LiDAR) has gradually been used to collect high-resolution micro-traffic data on the roadside of intelligent roads. Furthermore, a fusion of multiple LiDARs has become a current hot spot to extend the data collection range and improve detection accuracy. This paper focuses on point cloud registration in a complex traffic environment and proposes a three-dimensional (3D) registration method based on traffic signs and prior knowledge of traffic scenes. Traffic signs with their reflective films are used as reference targets to register 3D point cloud data from roadside LiDARs. The proposed method consists of a vertical registration and a horizontal registration. For the vertical registration, we propose a panel rotation algorithm to rotate the initial point cloud to register it vertically, converting the 3D point cloud registration into a two-dimensional (2D) rigid body transformation. For the vertical registration, our system registers traffic signs from different LiDARs. Our method has been verified in some actual scenarios. Compared with previous methods, the proposed method is automatic and does not need to search reference targets manually. Furthermore, it is suitable for actual engineering use and can be applied to sparse point cloud data from LiDAR with few beams, realizing point cloud registration of large disparity.

Autonomous vehicles (AVs) and robots increasingly exploit light detection and ranging (LiDAR)-based 3-D object detection systems to detect obstacles in the environment. Correct detection and classification are important to ensure safe driving. Although previous work has demonstrated the feasibility of manipulating point clouds to spoof 3-D object detectors, most of these attempts are performed digitally. In this article, we investigate the possibility of physically fooling LiDAR-based 3-D object detection by injecting adversarial point clouds using lasers. First, we develop a laser transceiver that can inject up to 4200 points, and can measure the scanning cycle of victim LiDARs to schedule the spoofing laser signals. By designing a control signal method that converts the coordinates of point clouds to control signals and an adversarial point cloud optimization method with physical constraints of LiDARs and attack capabilities, we manage to inject spoofing point cloud with desired point cloud shapes into the victim LiDAR physically. We can launch four types of attacks, i.e., naive hiding, record-based creating, optimization-based hiding, and optimization-based creating. Extensive experiments demonstrate the effectiveness of our attacks against two commercial LiDAR and three detectors. We further analyze the impact of our attacks on four fusion-based detectors. This article concludes with experiments on defense methods and discussion on potential defense strategies at both the sensor and AV system levels.

This research developed an automated software technique for identifying type, size, and location of man-made airfield damage including craters, spalls, and camouflets from a digitized three-dimensional point cloud of the airfield surface. Point clouds were initially generated from Light Detection and Ranging (LiDAR) sensors mounted on elevated lifts to simulate aerial data collection and, later, an actual unmanned aerial system. LiDAR data provided a high-resolution, globally positioned, and dimensionally scaled point cloud exported in a LAS file format that was automatically retrieved and processed using volumetric detection algorithms developed in the MATLAB software environment. Developed MATLAB algorithms used a three-stage filling technique to identify the boundaries of craters first, then spalls, then camouflets, and scaled their sizes based on the greatest pointwise extents. All pavement damages and their locations were saved as shapefiles and uploaded into the GeoExPT processing environment for visualization and quality control. This technique requires no user input between data collection and GeoExPT visualization, allowing for a completely automated software analysis with all filters and data processing hidden from the user.

Recent growth in unmanned aerial vehicle (UAV) technology have promoted the detailed mapping of individual tree species. However, the in-depth mining and comprehending of the significance of features derived from high-resolution UAV data for tree species discrimination remains a difficult task. In this study, a state-of-the-art approach combining UAV-borne light detection and ranging (LiDAR) and hyperspectral was used to classify 11 common tree species in a typical natural secondary forest in Northeast China. First, comprehensive relevant structural and spectral features were extracted. Then, the most valuable feature sets were selected by using a hybrid approach combining correlation-based feature selection with the optimized recursive feature elimination algorithm. The random forest algorithm was used to assess feature importance and perform the classification. Finally, the robustness of features derived from point clouds with different structures and hyperspectral images with different spatial resolutions was tested. Our results showed that the best classification accuracy was obtained by combining LiDAR and hyperspectral data (75.7%) compared to that based on LiDAR (60.0%) and hyperspectral (64.8%) data alone. The mean intensity of single returns and the visible atmospherically resistant index for red-edge band were the most influential LiDAR and hyperspectral derived features, respectively. The selected features were robust in point clouds with a density not lower than 5% (~5 pts/m2) and a resolution not lower than 0.3 m in hyperspectral data. Although canopy surface features were slightly different from original LiDAR features, canopy surface information was also important for tree species classification. This study proved the capabilities of UAV-borne LiDAR and hyperspectral data in natural secondary forest tree species discrimination and the potential for this approach to be transferable to other study areas.