We introduceTreeStructor, a novel approach for isolating and reconstructing forest trees. The key novelty is a deep neural model that uses neural ranking to assign pre-generated connectable 3D geometries to a point cloud.TreeStructoris trained on a large set of synthetically generated point clouds. The input to our method is a forest point cloud (FPC) that we first decompose into point clouds that approximately represent trees (TPC) and then into point clouds that represent their parts (PPC). We use a point cloud encoder-decoder to compute embedding vectors that retrieve the best-fitting surface mesh for eachPPCfrom a large set of predefined branch parts. Finally, the retrieved meshes are connected and oriented to obtain individual surface meshes of all trees represented by theFPC. We qualitatively and quantitatively validate that our method can reconstruct forest trees with unprecedented accuracy and visual fidelity.TreeStructoroutperforms the state-of-the-art reconstruction method for around 6% on quantitative metrics and 12% less error compared with QSM on low-quality scanned data. The code and data are available at https://lewkesy.github.io/TreeStructor/.

Presents corrections to the paper, (Errata to “TreeStructor: Forest Reconstruction With Neural Ranking”).

Woody Debris (WD) plays an important role in forest ecosystems. It provides critical habitat for plants, animals, and insects, but it is also a source of fuel contributing to fire propagation and sometimes leads to catastrophic wildfire. Traditional field surveys for WD assessments are usually restricted to transects and sample plots. Light Detection and Ranging (LiDAR) point clouds emerge as a valuable source for the development of comprehensive WD detection strategies. Although results from previous studies on LiDAR-based WD detection approaches have been promising, there is still a lack of general strategy for handling point clouds acquired by different platforms with varying characteristics (e.g., point density) in different forest types. In this study, we propose a general morphological WD detection strategy which requires few intuitive thresholds, making it applicable to multi-platform LiDAR datasets in both plantation and natural forests.

Segmenting major woody parts is a critical prerequisite to derive structural and biophysical attributes of trees. Static Terrestrial laser scanning (TLS) has been widely used due to its accurate and non-destructive scanning capability; wood parts segmentation has been experimented using the raw radiometric feature. However, due to the challenges of fixed scanning positions and occlusion, using TLS to capture an entire tree is time-consuming. Additionally, the raw intensity of TLS data cannot accurately represent objects’ physical characteristics. Here, using LiDAR data acquired by an inhouse developed backpack Mobile Mapping System (MMS), we introduce a fast and fully unsupervised method that combines automatic thresholding of normalized radiometric and geometric features to extract major woody parts in the point clouds. We show that using MMS LiDAR data, our method can achieve higher performance than existing methods for major woody parts segmentation on 14 trees with different sizes and species in both leaf-on and leaf-off seasons.

Unmanned aerial vehicles (UAVs) equipped with imaging and ranging sensors have become an effective remote sensing data acquisition tool for digital agriculture. Among potential products derived from UAVs, high-resolution orthophotos play an important role in several phenotyping activities, such as canopy cover estimation and flowering date identification. Current structure from motion (SfM) tools for image-based 3-D reconstruction and orthophoto generation cannot perform well when working with large-scale imagery over mechanized agricultural fields. This failure is mainly due to their inability to identify enough conjugate points among overlapping images captured at low altitudes. This study addresses such limitation through a new strategy that uses plant row segments as linear features in the triangulation process. The linear features are derived in two steps. First, an automated approach is implemented to extract plant row segments from the LiDAR data which are then back-projected to the imagery using available trajectory and system calibration parameters. In the second step, a machine-assisted strategy is used to adjust the line segments in image space for deriving accurate linear features. In the proposed framework, the triangulation process is conducted by investigating two mathematical models—referred to as object-space and image-space coplanarity constraints—for incorporating linear features in the bundle adjustment (BA). The orthophoto is generated using the refined trajectory and system calibration parameters derived from the BA process. Several experimental results over an agricultural filed show that the proposed framework outperforms commonly used SfM tools, e.g., Pix4D Mapper Pro and Agisoft Metashape in terms of generating orthophotos with high visual quality and geolocation accuracy. Also, results indicate that the object-space coplanarity constraint is more robust against potential noise in line measurements when compared to the image-space coplanarity model. However, both models lead to high absolute accuracy in the range of ±2–4 cm when the noise level in the image measurements of points along the line is reasonable, i.e., ~5–10 pixels.

High-Accuracy and high-efficiency 3-D sensing and associated data processing techniques are urgently needed for today’s roadway inventory, infrastructure health monitoring, autonomous driving, connected vehicles, urban modeling, and smart cities. 3D geospatial data acquired by digital photogrammetry or laser scanning or LiDAR systems have become one of the most critical data sources to support the above-mentioned applications. While progress has been made to applying 3D sensory data to those applications related to intelligent transportation systems (ITS), such as road network extraction, platform localization, obstacle avoidance, high-definition map generation, and transportation infrastructure inventory, many essential questions remain regarding the processing and understanding such massive 3D datasets in ITS-related applications. The authors have selected four articles for review in this Special issue. A summary of these articles is outlined below.

Lane width evaluation is one of the crucial aspects in road safety inspection, especially in work zones where a narrow lane width can result in a reduced roadway capacity and also, increase the probability of severe accidents. Using mobile mapping systems (MMS) equipped with laser scanners is a safe and cost-effective method for rapidly collecting detailed information along road surface. This paper presents an approach to derive lane width estimates using point clouds acquired from a geometrically-calibrated mobile mapping system. Starting from an accurate LiDAR point cloud, the road surface is extracted with the assistance of trajectory elevation data. Lane markings are identified based on the intensity data. Next, the lane marking centerline is derived and clustered to identify areas with ambiguous or missing lane markings and finally, use the normal (or, unambiguous) lane markings to estimate the lane width. The derived lane width estimates are used to develop a reporting mechanism for areas with narrow lanes, ambiguous lane markings, missing lane markings, and/or wide lanes.

This paper presents a framework to build a joint 2-D-3-D traffic sign landmark data set for geo-localization using mobile laser scanning (MLS) data. The MLS data include 3-D point clouds and corresponding multi-view images. First, an integrated method, based on a deep learning network and the retro-reflective properties of traffic signs, is developed to accurately extract traffic signs from MLS point clouds. Next, the semantic and spatial properties of the traffic signs (type, location, position, and geometric characteristics) are obtained. Then, a joint 2-D-3-D traffic sign landmark data set is built, and a semantic-spatial organization graph is used to organize the traffic sign data set. Last, based on the traffic sign landmark data set, a geo-localization method for a driving car is proposed to estimate the driving trajectory. It can be used for auxiliary positioning of autonomous vehicles. Experimental results demonstrate the reliability of our proposed method for traffic sign detection and the potential of building 2-D-3-D traffic sign landmark data set for driving trajectory estimation from MLS data.

Due to the advances in technological and industrial fields, remote sensing has been adopted to a considerable extent in precision agricultural applications. Over the past few years, remote sensing utilized Mobile Mapping Systems (MMS) as the platforms for agricultural data collection. For accurate generation of georeferenced products using such MMSs, there should be a robust calibration approach that can accurately estimate the mounting parameters of the involved sensors, i.e., LiDAR unit, camera, and hyperspectral push-broom scanner. In this paper, we propose novel calibration approaches for various sensors onboard a UAV platform - 1) simultaneous estimation of lever arm and boresight angles relating LiDAR unit and camera to the GNSS/INS unit, and 2) estimation of boresight angles relating hyperspectral push-broom scanner and the GNSS/TNS unit.

High throughput phenotyping is rapidly gaining widespread popularity due to its ability to non-destructively extract plant traits, such as plant height, canopy density, leaf and plant structure, and so on. In this study, we focus on developing a UAV-based LiDAR system to acquire accurate time-series 3D point clouds for monitoring two specific plant traits - plant height and canopy cover - which are integral for enhancing crop genetic improvement to meet the needs of future generations. Furthermore, the obtained estimates are validated by comparing the results with those obtained from wheel-based LiDAR data.

Biomass estimation is fundamental for a variety of plant ecological studies. Direct measurement of aboveground biomass by clipping and sorting is destructive, time-consuming and laborious, thus reducing the ability of extensive sampling. Various plant traits, such as plant height, canopy cover, and leaf and plant structure contribute towards its biomass. In this study, we focus on exploiting wheel-based LiDAR data over an agricultural field to perform growth monitoring and canopy cover estimation, which would play a crucial role in the future to develop a non-invasive technique for biomass prediction.

Over the past few years, developments in mobile mapping technology, specifically Unmanned Aerial Vehicles (UAVs), have made accurate 3D mapping more feasible, thus emerging as an economical and practical mobile mapping platform. LiDAR-based UAV mapping systems are gaining widespread recognition as an efficient and cost-effective technique for rapid collection of 3D geospatial data. To derive point clouds with high positional accuracy, estimation of mounting parameters relating the laser scanners to the onboard GNSS/INS unit is the foremost and necessary step. In this paper, we first devise an optimal flight and target configuration by conducting a rigorous theoretical analysis of the potential impact of bias in mounting parameters of a LiDAR unit on the resultant point cloud. Then, we propose a LiDAR system calibration strategy that can directly estimate the mounting parameters for spinning multibeam laser scanners onboard a UAV through an outdoor calibration procedure.

This paper proposes a multiunit light detection and ranging (LiDAR) system calibration procedure to directly estimate the mounting parameters relating multiple spinning multibeam laser scanners to the global navigation satellite system/inertial navigation system (GNSS/INS) unit onboard a mobile terrestrial platform in order to derive point clouds with high-positional accuracy. This procedure is based on the use of conjugate planar/linear features in overlapping point clouds derived from different drive runs. In order to increase the efficiency of semiautomatic conjugate feature extraction from LiDAR data, specifically designed calibration boards covered by highly reflective surfaces that could be easily deployed and set up within outdoor environments are used in this paper. To ensure the accuracy of the estimated mounting parameters, an optimal configuration of target primitives and drive runs is determined by analyzing the potential impact of bias in mounting parameters of a LiDAR unit on the resultant point cloud for different orientations of target primitives and different drive run scenarios. This impact is also verified experimentally by simulating a bias in each mounting parameter separately. Finally, the optimal configuration is used within an experimental setup to evaluate the performance of the proposed calibration procedure through the a posteriori variance factor of least squares adjustment and the quality of fit of adjusted point cloud to linear/planar surfaces before and after the calibration process. The proposed calibration approach attained an accuracy of 1.42 cm, which is better than the accuracy expected based on the specifications of the involved hardware components, i.e., the LiDAR and GNSS/INS units.

Light Detection and Ranging (LiDAR) systems have been widely adopted for the acquisition of dense and accurate topographic data over extended areas. Although the utilization of this technology has increased in different applications, the development of standard methodologies for the quality control (QC) of LiDAR data has not followed the same trend. In other words, a lack in reliable, practical, cost-effective, and commonly acceptable QC procedures is evident. A frequently adopted procedure for QC is comparing the LiDAR data to ground control points. Aside from being expensive, this approach is not accurate enough for the verification of horizontal accuracy, unless specifically designed LiDAR targets are used. This paper is dedicated to providing accurate, economical, and convenient internal QC procedures for the evaluation of LiDAR data, which is captured from parallel flight lines. The underlying concept of the proposed methodologies is that, in the absence of systematic and random errors in system parameters and measurements, conjugate surface elements in overlapping strips should perfectly match each other. Consistent incompatibilities and the quality of fit between conjugate surface elements in overlapping strips can be used to detect systematic errors in the system parameters/measurements and to evaluate the noise level in the LiDAR point cloud, respectively. Experimental results from real data demonstrate that all the proposed methods, with one exception, produce compatible estimates of systematic discrepancies between the involved data sets, as well as good quantification of inherent noise.

Despite the recent developments in light detection and ranging systems, discrepancies between strips on overlapping areas persist due to the systematic errors. This letter presents an algorithm that can be used to detect and adjust such discrepancies. To achieve this, extracting conjugate features from the strips is a prerequisite step. In this letter, linear features are chosen as conjugate features because they can be accurately extracted from man-made structures in urban area and more easily extracted than the point features. Based on such a selection strategy, a simple and robust algorithm is proposed that is generally applicable for extracting such features. The algorithm includes methods that can be used to establish observation equations from similarity measurements of the extracted features. Then, several transformations are selected and used to adjust the strips. Following the transformation, the fitness of linear features is tested to determine whether the discrepancies have been resolved; the results are then evaluated statistically. The results demonstrate that the algorithm is effective in reducing the discrepancies between the strips.

Many photogrammetric and GIS applications work with surfaces that are commonly acquired by different sensors, from different viewpoints, and/or at different times. Manipulation of these data requires them to be relative to the same reference frame, and therefore surface matching is a necessary procedure for these applications. Similar to remote sensing, medical image analyses also deal with surfaces such as in studies of disease progression where changes between anatomical surfaces are detected. Magnetic resonance imaging (MRI), a medical imaging modality, is used in this research to capture 3D data of knee joint structures to aid in the non-invasive monitoring of joint diseases. However, human subjects can be positioned differently each time, and disease progression might lead to anatomical changes. As a result, surface matching is an essential task for these applications. Due to the similarities between remote sensing and medical image analyses, the major objective of this research is to translate and modify methods originally developed for geographic data to create new techniques that are feasible for accurate co-registration of MR 3D data. The proposed methodology is based on a voting scheme that can simultaneously establish the correspondence between datasets and estimate the transformation parameters. The matching is performed locally, and only matched features will contribute to the determination of the transformation parameters. Preliminary experiments were conducted on bone surfaces, and an average normal distance between surface elements of 0.201 mm was achieved after registration. This is quite good considering the MR image resolution, and it also shows that the proposed matching strategy is feasible and reliable when applied to MR data.