Canopy Volume Extraction of Citrus reticulate Blanco cv. Shatangju Trees Using UAV Image-Based Point Cloud Deep Learning

UAV-based individual plant detection and geometric parameter extraction in vineyards

Accurately characterizing vineyard parameters is crucial for precise vineyard management and breeding purposes. Various macroscopic vineyard parameters are required to make informed management decisions, such as pesticide application, defoliation strategies, and determining optimal sugar content in each berry by assessing biomass. In this paper, we present a novel approach that utilizes point cloud data to detect trunk positions and extract macroscopic vineyard characteristics, including plant height, canopy width, and canopy volume. Our approach relies solely on geometric features and is compatible with different training systems and data collected using various 3D sensors. To evaluate the effectiveness and robustness of our proposed approach, we conducted extensive experiments on multiple grapevine rows trained in two different systems. Our method provides more comprehensive canopy characteristics than traditional manual measurements, which are not representative throughout the row. The experimental results demonstrate the accuracy and efficiency of our method in extracting vital macroscopic vineyard characteristics, providing valuable insights for yield monitoring, grape quality optimization, and strategic interventions to enhance vineyard productivity and sustainability.

A Cross-Source Point Cloud Registration Algorithm Based on Trigonometric Mutation Chaotic Harris Hawk Optimisation for Rockfill Dam Construction

A high-precision three-dimensional (3D) model is the premise and vehicle of digitalising hydraulic engineering. Unmanned aerial vehicle (UAV) tilt photography and 3D laser scanning are widely used for 3D model reconstruction. Affected by the complex production environment, in a traditional 3D reconstruction based on a single surveying and mapping technology, it is difficult to simultaneously balance the rapid acquisition of high-precision 3D information and the accurate acquisition of multi-angle feature texture characteristics. To ensure the comprehensive utilisation of multi-source data, a cross-source point cloud registration method integrating the trigonometric mutation chaotic Harris hawk optimisation (TMCHHO) coarse registration algorithm and the iterative closest point (ICP) fine registration algorithm is proposed. The TMCHHO algorithm generates a piecewise linear chaotic map sequence in the population initialisation stage to improve population diversity. Furthermore, it employs trigonometric mutation to perturb the population in the development stage and thus avoid the problem of falling into local optima. Finally, the proposed method was applied to the Lianghekou project. The accuracy and integrity of the fusion model compared with those of the realistic modelling solutions of a single mapping system improved.

Automatic instance segmentation of orchard canopy in unmanned aerial vehicle imagery using deep learning

The widespread use of unmanned aerial vehicles (UAV) is significant for the effective management of orchards in the context of precision agriculture. To reduce the traditional mode of continuous spraying, variable target spraying machines require detailed information about tree canopy. Although deep learning methods have been widely used in the fields of identifying individual trees, there are still phenomena of branches extending and shadows preventing segmenting edges of tree canopy precisely. Hence, a methodology (MPAPR R-CNN) for the high-precision segment method of apple trees in high-density cultivation orchards by low-altitude visible light images captured is proposed. Mask R-CNN with a path augmentation feature pyramid network (PAFPN) and PointRend algorithm was used as the base segmentation algorithm to output the precise boundaries of the apple tree canopy, which addresses the over- and under-sampling issues encountered in the pixel labeling tasks. The proposed method was tested on another miniature map of the orchard. The average precision (AP) was selected to evaluate the metric of the proposed model. The results showed that with the help of training with the PAFPN and PointRend backbone head that AP_seg and AP_box score improved by 8.96% and 8.37%, respectively. It can be concluded that our algorithm could better capture features of the canopy edges, it could improve the accuracy of the edges of canopy segmentation results.

Optimization of UAV-Based Imaging and Image Processing Orthomosaic and Point Cloud Approaches for Estimating Biomass in a Forage Crop

Forage and field peas provide essential nutrients for livestock diets, and high-quality field peas can influence livestock health and reduce greenhouse gas emissions. Above-ground biomass (AGBM) is one of the vital traits and the primary component of yield in forage pea breeding programs. However, a standard method of AGBM measurement is a destructive and labor-intensive process. This study utilized an unmanned aerial vehicle (UAV) equipped with a true-color RGB and a five-band multispectral camera to estimate the AGBM of winter pea in three breeding trials (two seed yields and one cover crop). Three processing techniques—vegetation index (VI), digital surface model (DSM), and 3D reconstruction model from point clouds—were used to extract the digital traits (height and volume) associated with AGBM. The digital traits were compared with the ground reference data (measured plant height and harvested AGBM). The results showed that the canopy volume estimated from the 3D model (alpha shape, α = 1.5) developed from UAV-based RGB imagery’s point clouds provided consistent and high correlation with fresh AGBM (r = 0.78–0.81, p < 0.001) and dry AGBM (r = 0.70–0.81, p < 0.001), compared with other techniques across the three trials. The DSM-based approach (height at 95th percentile) had consistent and high correlation (r = 0.71–0.95, p < 0.001) with canopy height estimation. Using the UAV imagery, the proposed approaches demonstrated the potential for estimating the crop AGBM across winter pea breeding trials.

Comparison of Aerial and Ground 3D Point Clouds for Canopy Size Assessment in Precision Viticulture

In precision viticulture, the intra-field spatial variability characterization is a crucial step to efficiently use natural resources by lowering the environmental impact. In recent years, technologies such as Unmanned Aerial Vehicles (UAVs), Mobile Laser Scanners (MLS), multispectral sensors, Mobile Apps (MA) and Structure from Motion (SfM) techniques enabled the possibility to characterize this variability with low efforts. The study aims to evaluate, compare and cross-validate the potentiality and the limits of several tools (UAV, MA, MLS) to assess the vine canopy size parameters (thickness, height, volume) by processing 3D point clouds. Three trials were carried out to test the different tools in a vineyard located in the Chianti Classico area (Tuscany, Italy). Each test was made of a UAV flight, an MLS scanning over the vineyard and a MA acquisition over 48 geo-referenced vines. The Leaf Area Index (LAI) were also assessed and taken as reference value. The results showed that the analyzed tools were able to correctly discriminate between zones with different canopy size characteristics. In particular, the R2 between the canopy volumes acquired with the different tools was higher than 0.7, being the highest value of R2 = 0.78 with a RMSE = 0.057 m3 for the UAV vs. MLS comparison. The highest correlations were found between the height data, being the highest value of R2 = 0.86 with a RMSE = 0.105 m for the MA vs. MLS comparison. For the thickness data, the correlations were weaker, being the lowest value of R2 = 0.48 with a RMSE = 0.052 m for the UAV vs. MLS comparison. The correlation between the LAI and the canopy volumes was moderately strong for all the tools with the highest value of R2 = 0.74 for the LAI vs. V_MLS data and the lowest value of R2 = 0.69 for the LAI vs. V_UAV data.

Logging Trail Segmentation via a Novel U-Net Convolutional Neural Network and High-Density Laser Scanning Data

Logging trails are one of the main components of modern forestry. However, spotting the accurate locations of old logging trails through common approaches is challenging and time consuming. This study was established to develop an approach, using cutting-edge deep-learning convolutional neural networks and high-density laser scanning data, to detect logging trails in different stages of commercial thinning, in Southern Finland. We constructed a U-Net architecture, consisting of encoder and decoder paths with several convolutional layers, pooling and non-linear operations. The canopy height model (CHM), digital surface model (DSM), and digital elevation models (DEMs) were derived from the laser scanning data and were used as image datasets for training the model. The labeled dataset for the logging trails was generated from different references as well. Three forest areas were selected to test the efficiency of the algorithm that was developed for detecting logging trails. We designed 21 routes, including 390 samples of the logging trails and non-logging trails, covering all logging trails inside the stands. The results indicated that the trained U-Net using DSM (k = 0.846 and IoU = 0.867) shows superior performance over the trained model using CHM (k = 0.734 and IoU = 0.782), DEMavg (k = 0.542 and IoU = 0.667), and DEMmin (k = 0.136 and IoU = 0.155) in distinguishing logging trails from non-logging trails. Although the efficiency of the developed approach in young and mature stands that had undergone the commercial thinning is approximately perfect, it needs to be improved in old stands that have not received the second or third commercial thinning.