Accurate individual tree crown (ITC) segmentation from scanned point clouds is a fundamental task in forest biomass monitoring and forest ecology management. Light detection and ranging (LiDAR) as a mainstream tool for forest survey is advancing the pattern of forest data acquisition. In this study, we performed a novel deep learning framework directly processing the forest point clouds belonging to the four forest types (i.e., the nursery base, the monastery garden, the mixed forest, and the defoliated forest) to realize the ITC segmentation. The specific steps of our approach were as follows: first, a voxelization strategy was conducted to subdivide the collected point clouds with various tree species from various forest types into many voxels. These voxels containing point clouds were taken as training samples for the PointNet deep learning framework to identify the tree crowns at the voxel scale. Second, based on the initial segmentation results, we used the height-related gradient information to accurately depict the boundaries of each tree crown. Meanwhile, the retrieved tree crown breadths of individual trees were compared with field measurements to verify the effectiveness of our approach. Among the four forest types, our results revealed the best performance for the nursery base (tree crown detection rate r = 0.90; crown breadth estimation R² > 0.94 and root mean squared error (RMSE) < 0.2m). A sound performance was also achieved for the monastery garden and mixed forest, which had complex forest structures, complicated intersections of branches and different building types, with r = 0.85, R² > 0.88 and RMSE < 0.6 m for the monastery garden and r = 0.80, R² > 0.85 and RMSE < 0.8 m for the mixed forest. For the fourth forest plot type with the distribution of crown defoliation across the woodland, we achieved the performance with r = 0.82, R² > 0.79 and RMSE < 0.7 m. Our method presents a robust framework inspired by the deep learning technology and computer graphics theory that solves the ITC segmentation problem and retrieves forest parameters under various forest conditions.

Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR) data is of great significance to forest resource assessment and smart management. After proof-of-concept studies, advanced deep learning methods have been shown to have high efficiency and accuracy in remote sensing data analysis and geoscience problem solving. This study proposes a novel concept for synergetic use of the YOLO-v4 deep learning network based on heightmaps directly generated from airborne LiDAR data for ITC segmentation and a computer graphics algorithm for refinement of the segmentation results involving overlapping tree crowns. This concept overcomes the limitations experienced by existing ITC segmentation methods that use aerial photographs to obtain texture and crown appearance information and commonly encounter interference due to heterogeneous solar illumination intensities or interlacing branches and leaves. Three generative adversarial networks (WGAN, CycleGAN, and SinGAN) were employed to generate synthetic images. These images were coupled with manually labeled training samples to train the network. Three forest plots, namely, a tree nursery, forest landscape and mixed tree plantation, were used to verify the effectiveness of our approach. The results showed that the overall recall of our method for detecting ITCs in the three forest plot types reached 83.6%, with an overall precision of 81.4%. Compared with reference field measurement data, the coefficient of determinationR²was ≥ 79.93% for tree crown width estimation, and the accuracy of our deep learning method was not influenced by the values of key parameters, yielding 3.9% greater accuracy than the traditional watershed method. The results demonstrate an enhancement of tree crown segmentation in the form of a heightmap for different forest plot types using the concept of deep learning, and our method bypasses the visual complications arising from aerial images featuring diverse textures and unordered scanned points with irregular geometrical properties.

Rubber trees in southern China are often impacted by natural disturbances that can result in a tilted tree body. Accurate crown segmentation for individual rubber trees from scanned point clouds is an essential prerequisite for accurate tree parameter retrieval. In this paper, three plots of different rubber tree clones, PR107, CATAS 7-20-59, and CATAS 8-7-9, were taken as the study subjects. Through data collection using ground-based mobile light detection and ranging (LiDAR), a voxelisation method based on the scanned tree trunk data was proposed, and deep images (i.e., images normally used for deep learning) were generated through frontal and lateral projection transform of point clouds in each voxel with a length of 8 m and a width of 3 m. These images provided the training and testing samples for the faster region-based convolutional neural network (Faster R-CNN) of deep learning. Consequently, the Faster R-CNN combined with the generated training samples comprising 802 deep images with pre-marked trunk locations was trained to automatically recognize the trunk locations in the testing samples, which comprised 359 deep images. Finally, the point clouds for the lower parts of each trunk were extracted through back-projection transform from the recognized trunk locations in the testing samples and used as the seed points for the region’s growing algorithm to accomplish individual rubber tree crown segmentation. Compared with the visual inspection results, the recognition rate of our method reached 100% for the deep images of the testing samples when the images contained one or two trunks or the trunk information was slightly occluded by leaves. For the complicated cases, i.e., multiple trunks or overlapping trunks in one deep image or a trunk appearing in two adjacent deep images, the recognition accuracy of our method was greater than 90%. Our work represents a new method that combines a deep learning framework with point cloud processing for individual rubber tree crown segmentation based on ground-based mobile LiDAR scanned data.

Leaf area is an important plant canopy structure parameter with important ecological significance. Light detection and ranging technology (LiDAR) with the application of a terrestrial laser scanner (TLS) is an appealing method for accurately estimating leaf area; however, the actual utility of this scanner depends largely on the efficacy of point cloud data (PCD) analysis. In this paper, we present a novel method for quantifying total leaf area within each tree canopy from PCD. Firstly, the shape, normal vector distribution and structure tensor of PCD features were combined with the semi-supervised support vector machine (SVM) method to separate various tree organs, i.e., branches and leaves. In addition, the moving least squares (MLS) method was adopted to remove ghost points caused by the shaking of leaves in the wind during the scanning process. Secondly, each target tree was scanned using two patterns, i.e., one scan and three scans around the canopy, to reduce the occlusion effect. Specific layer subdivision strategies according to the acquisition ranges of the scanners were designed to separate the canopy into several layers. Thirdly, 10% of the PCD was randomly chosen as an analytic dataset (ADS). For the ADS, an innovative triangulation algorithm with an assembly threshold was designed to transform these discrete scanning points into leaf surfaces and estimate the fractions of each foliage surface covered by the laser pulses. Then, a novel ratio of the point number to leaf area in each layer was defined and combined with the total number of scanned points to retrieve the total area of the leaves in the canopy. The quantified total leaf area of each tree was validated using laborious measurements with a LAI-2200 Plant Canopy Analyser and an LI-3000C Portable Area Meter. The results showed that the individual tree leaf area was accurately reproduced using our method from three registered scans, with a relative deviation of less than 10%. Nevertheless, estimations from only one scan resulted in a deviation of >25% in the retrieved individual tree leaf area due to the occlusion effect. Indeed, this study provides a novel connection between leaf area estimates and scanning sensor configuration and supplies an interesting method for estimating leaf area based on PCD.

This paper presents a novel framework to extract metro tunnel cross sections (profiles) from Terrestrial Laser Scanning point clouds. The entire framework consists of two steps: tunnel central axis extraction and cross section determination. In tunnel central extraction, we propose a slice-based method to obtain an initial central axis, which is further divided into linear and nonlinear circular segments by an enhanced Random Sample Consensus (RANSAC) tunnel axis segmentation algorithm. This algorithm transforms the problem of hybrid linear and nonlinear segment extraction into a sole segmentation of linear elements defined at the tangent space rather than raw data space, significantly simplifying the tunnel axis segmentation. The extracted axis segments are then provided as input to the step of the cross section determination which generates the coarse cross-sectional points by intersecting a series of straight lines that rotate orthogonally around the tunnel axis with their local fitted quadric surface, i.e., cylindrical surface. These generated profile points are further refined and densified via solving a constrained nonlinear least squares problem. Our experiments on Nanjing metro tunnel show that the cross sectional fitting error is only 1.69 mm. Compared with the designed radius of the metro tunnel, the RMSE (Root Mean Square Error) of extracted cross sections’ radii only keeps 1.60 mm. We also test our algorithm on another metro tunnel in Shanghai, and the results show that the RMSE of radii only keeps 4.60 mm which is superior to a state-of-the-art method of 6.00 mm. Apart from the accurate geometry, our approach can maintain the correct topology among cross sections, thereby guaranteeing the production of geometric tunnel model without crack defects. Moreover, we prove that our algorithm is insensitive to the missing data and point density.