ArticlePDF Available

Abstract and Figures

LiDAR ( Light detection and ranging ) technology is an alternative to current manual methods of canopy geometry estimations in orange trees. The objective of this work was to compare different types of canopy volume estimations of orange trees, some inspired on manual methods and others based on a LiDAR sensor. A point cloud was generated for 25 individual trees using a laser scanning system. The convex-hull and the alpha-shape surface reconstruction algorithms were tested. LiDAR derived models are able to represent orange trees more accurately than traditional methods. However, results differ significantly from the current manual method. In addition, different 3D modeling algorithms resulted in different canopy volume estimations. Therefore, a new standard method should be developed and established.
Content may be subject to copyright.
This document is the preprint of the full paper presented at the 11th European Conference on Precision
Agriculture ECPA and is to be published at the journal Advances in Animal Biosciences Volume 8 Issue 2
with DOI:
Orange tree canopy volume estimation by manual and LiDAR-based methods
A. F. Colaço1*; R. G. Trevisan1; J. P. Molin1, J. R. Rosell-Polo2; A. Escolà2
1. University of São Paulo, ‘Luiz de Queiroz’ College of Agriculture, Biosystems Engineering
Department, Piracicaba-SP, Brazil;
2. University of Lleida Agrotecnio Center, School of Agrifood and Forestry Science and
Engineering, Department of Agricultural and Forest Engineering, Research Group on
AgroICT & Precision Agriculture, Lleida - Catalonia, Spain.
LiDAR (Light detection and ranging) technology is an alternative to current manual methods
of canopy geometry estimations in orange trees. The objective of this work was to compare
different types of canopy volume estimations of orange trees, some based on manual methods
and others based on a LiDAR sensor. A point cloud was generated for 25 individual trees using
a laser scanning system. The convex-hull and the alpha-shape surface reconstruction algorithms
were tested. LiDAR derived models are able to represent orange trees more accurately than
traditional methods. However, results differ significantly from the current manual method. In
addition, different 3D modeling algorithms resulted in different canopy volume estimations.
Therefore, a new standard method should be developed and established.
Keywords: tree crops; laser scanner; convex-hull; alpha-shape; citrus
Canopy volume is an indicator of growth, health and yield potential in tree crops. It is also used
for estimating sparing and fertilizer requirements. The current methods for canopy volume
estimation in Brazilian orange groves are quite simplistic. One of the most used considers the
tree volume as the volume of a cube enclosing the whole tree. Each side of such a cube is
measured manually with a measuring tape. Besides its inaccuracy, the manual method is time
consuming and requires a significant number of sampled trees for an adequate representation
of the whole grove.
One alternative for the manual method is the ranging sensor (Dworak et al, 2011). Such
technology permits not only a higher accuracy on the estimation of canopy geometric
parameters but also higher amount of collected data. These data can be georeferenced and
acquired throughout the entire field in order to characterize spatial variability. Once spatial
variability of canopy volume is known, inputs can be applied in a variable-rate approach
according to the tree size variation. Such applications can be carried out at the same time as
sensor readings are acquired (i.e in “real time”) (Escolà et al. 2013). For these reasons, ranging
sensors meet the needs of precision horticulture and represent great potential to enhance
management in tree crops.
Two types of ranging sensors are mostly investigated in research, the ultrasonic and the LiDAR
(Light detection and ranging) sensors. These sensors are usually mounted facing the side of the
tree row being able to estimate the distance to the vegetation at different heights along the
canopy. LiDAR sensors are considered a better solution than ultrasonic sensors because they
This document is the preprint of the full paper presented at the 11th European Conference on Precision
Agriculture ECPA and is to be published at the journal Advances in Animal Biosciences Volume 8 Issue 2
with DOI:
are usually more accurate, more rapid, and permit distance measurements in multiple directions
from one single sensor.
In the past decade, research has developed data acquisition and processing methods based on
LiDAR technology aiming at providing 3D models of trees and retrieve canopy volume
information (Rosell and Sanz, 2012). Rosell et al. (2009) described a mobile terrestrial laser
scanner (MTLS) in which raw LiDAR sensor data was transformed into a 3D point cloud
representing the laser beam impacts on the canopy. Further works showed how to extract
geometric canopy information from 3D point clouds obtained by similar data acquisition
systems (Escolà et al., 2016). Different methods are available for computing canopy volume
from point clouds. Auat Cheein et al. (2015) classified such methods into two main approaches,
one referred as the occupancy grid, in which small regular sized objects are created inside the
point cloud structure; and another based on connecting the outer points of the point cloud in
order to reconstruct the shape of the object formed by the point cloud structure. Both approaches
were tested by the authors and were considered viable methods for estimating canopy volume.
Orange groves in Brazil cover approximately 500,000 ha of land (CONAB, 2013). Spray
applications are crucial operations in the management of the groves and might occur at least
once a month during the cropping season. Spraying prescriptions are currently based on manual
and poorly accurate measurements of canopy volume. Sensor-based estimation should greatly
improve the management of these groves.
The hypothesis of this work is that LiDAR-based methods for canopy geometry estimation
should be more accurate than manual methods. However, because different methods and
algorithms can be used for processing LiDAR data, different results might be achieved
evidencing the need for stablishing new standard methods of canopy volume estimation.
The objective of this work was to compare estimations of orange tree canopy volume by six
different methods; two based on traditional manual methods and four based on LiDAR
technology using different processing algorithms.
Material and Methods
Data acquisition
A mobile terrestrial laser scanner was developed based on a 2D LMS 200 LiDAR sensor (Sick,
Waldkirch, Germany) and an RTK (Real Time Kinematic) GR3 GNSS receiver (Topcon,
Tokyo, Japan). The system was mounted on an ATV vehicle as shown in Figure 1. The LiDAR
sensor collected distance values in 181 directions every 13.3 ms (75 Hz) at one-degree angular
steps along a vertical plane of the tree canopy. The vehicle moved along the two sides of the
tree row at 3.3 m s-1.
A commercial orange grove located in the state of São Paulo, Brazil, was scanned using the
developed system. 25 trees inside the grove were selected for this study. The variety of the trees
was “Valencia” grafted to “Swingle” rootstock. Trees were six years old at the time of data
acquisition (October of 2015).
Data processing
The first step of data processing consisted in creating a georeferenced 3D point cloud
representing the laser beam impacts over the canopy. Del-Moral-Martínez et al. (2015) give
details about this process. The following step is to exclude points that did not represent the
target tree canopy (soil and neighboring plants). This step was carried out using tools for
selecting and deleting points available in the CloudCompare 2.6.2 software. With the final point
cloud from each of the 25 selected trees, the next step was to compute the canopy volume. Two
This document is the preprint of the full paper presented at the 11th European Conference on Precision
Agriculture ECPA and is to be published at the journal Advances in Animal Biosciences Volume 8 Issue 2
with DOI:
types of surface reconstruction algorithms were applied, the convex-hull and the alpha-shape,
using the R software packages grDevices and the alphashape3d, respectively. Both algorithms
connect the outer points of the cloud in order to produce the surface of the enveloping object.
Unlike the convex-hull, the alpha-shape permits the creation of concave objects. The level of
concavity is given by setting the index α (lower index results in greater concavities). Three
indexes were tested: 0.25, 0.50 and 0.75.
Two types of canopy volume estimation based on traditional manual methods were also tested.
The first one, which is the most common among Brazilian orange growers, consisted in
measuring the volume of a cube that encloses the entire tree. This method is hereafter referred
as the cube-fit. The second, referred as the cylinder-fit, considered the canopy volume as two-
thirds the volume of a cylinder that encloses the tree. The dimensions of the cube and cylinder
were not measured manually as it would be normal. Instead, it was collected directly from the
point cloud using distance-measuring tools available in the CloudCompare 2.6.2 software.
Figure 1 LiDAR sensor and GNSS receiver mounted on an ATV vehicle (a); LiDAR sensor
(in blue) facing the side of the tree row (b)
Results and Discussion
After the LiDAR scanning and the point cloud generation, the average number of points
representing each tree was 12,100 distributed into approximately 60 perpendicular transects.
The 3D models from the proposed algorithms applied to a single tree are shown in Figure 2. It
is noticeable how the convex-hull model apparently produced a larger object, which occurs
because salient branches enlarges the hull structure. As expected, concavities of the canopy
were better represented by the alpha-shape algorithm. Because this algorithm permits the
representation of concave structures, it is reasonable to consider it a suitable model for
representing the tree canopy. However, the index α should be appropriately set (not too high
neither too low). A low index might produce disconnected structures forming holes inside the
canopy, which is not desirable (see alpha-shapes with α set to 0.25 and 0.50 in Figure 2). A
guideline for setting α is to choose a value that produces the smallest volume while keeping the
canopy as a whole. That result was obtained when α was set to 0.75.
This document is the preprint of the full paper presented at the 11th European Conference on Precision
Agriculture ECPA and is to be published at the journal Advances in Animal Biosciences Volume 8 Issue 2
with DOI:
Figure 2 3D canopy structure of a single tree modeled by different algorithms. Top: point
cloud section and selected single tree. Middle: Alpha shape models (left, α=0.25; right, α=0.75).
Bottom left: Alpha shape model, α=0.50. Bottom right: Convex-hull model.
The volumes for each of the 25 individual trees calculated by the proposed algorithms and by
the manual methods are showed in Figure 3. The plant IDs were given based on a rank from the
smallest to the largest tree according to the alpha-shape = 0.75) and convex-hull
computation. It is to be noticed that this ranking is roughly followed by all the other algorithms.
Generally, the manual methods produced a ranking with some disagreement with the other
algorithms, which indicated a certain level of randomness in the manual measurements. The
rough simplification of the canopy structure by the manual method based on the cube-fit
overestimated the canopy volume in relation to all the other algorithms. The measurements
from the cylinder-fit method were mainly close to the ones computed with the alpha-shape with
index of 0.50, but sometimes closer to index 0.75 and other to 0.25.
This document is the preprint of the full paper presented at the 11th European Conference on Precision
Agriculture ECPA and is to be published at the journal Advances in Animal Biosciences Volume 8 Issue 2
with DOI:
Figure 3 Canopy volume of 25 individual trees computed by different methods. Plant IDs
were given based on a rank from the smallest to the largest tree according to the alpha-shape
(α = 0.75) and convex-hull computation.
Table 1 shows the descriptive statistics of the measurements of the 25 orange trees. A noticeable
difference in all statistical parameters between different computation methods is evident. As
expected, the convex-hull model resulted in the highest mean canopy volume among the
proposed algorithms, followed by the alpha-shape with higher index α. The volume retrieved
from the alpha-shape with α set to 0.25 was significantly smaller than that of other algorithms,
due to disconnected structures formed by the model and significant voids inside the canopy, as
viewed in Figure 2. On the other end, the cube-fit method resulted in a significantly larger
volume than all evaluated methods. Regarding the cylinder-fit, because it considered only two
thirds of the cylinder, the final canopy volume is not as large as in the cube-fit method. The
cylinder-fit method got closer results to the alpha-shape with index of 0.5, which, as noticed in
Figure 1, produced voids inside the 3D model.
It is also noticeable from Table 1 that the manual methods presented lower coefficient of
variation than the 3D modeling algorithms, with exception to the alpha-shape with index 0.25.
That might occur because the cube-fit and cylinder-fit represent the tree using less complex
figures which are less variable and often do not represent the actual volume of the canopy, i. e.,
trees with different volume in reality might present similar volumes when these methods are
Table 1 Descriptive statistics of canopy volume of 25 individual trees by different methods
St. Dev.
------------------------------ m³ ----------------------------
α-shape (i=0.25)
α-shape (i=0.50)
α-shape (i=0.75)
Manual (cylinder-fit)
Manual (cube-fit)
This document is the preprint of the full paper presented at the 11th European Conference on Precision
Agriculture ECPA and is to be published at the journal Advances in Animal Biosciences Volume 8 Issue 2
with DOI:
LiDAR-based methods provided more realistic representation of the canopies than current
manual methods and should be considered as a new standard for canopy volume estimations.
Important differences among the evaluated methods of canopy volume estimation in orange
trees were found. The average canopy volume retrieved by the cube-fit method (the current
practice in Brazilian orange groves) was approximately 150% larger than the volume from the
alpha-shape with 0.75 index. The alpha-shape modeling with α set to 0.75 might be considered
an adequate method since it permitted the representation of concave structures of the canopy
without creating disconnected objects or voids inside the canopy.
Manual inspired methods were less capable of representing tree size variability than LiDAR-
based ones.
Testing more 3D modeling options in a larger amount of sampled trees are still needed.
Nevertheless, some guidelines and promising results were presented in this study.
Auat Cheein, F. A., Guivant, J., Sanz, R., Escolà, A., Yandún, F., Torres-Torriti, M., Rosell-
Polo, R. R. (2015). Real-time approaches for characterization of fully and partially
scanned canopies in groves. Computers and Electronics in Agriculture, v. 118, p. 361
de safra brasileira: laranja, terceiro levantamento, dezembro/2013. Brasília, 16p.
Del-Moral-Martínez, I., Arnó, J., Escolà, A., Sanz., Masip-Vilalta, J., Company-Mesa, J.,
Rosell-Polo, J. R. (2015). Georeferenced Scanning System to Estimate the LeafWall
Area in Tree Crops. Sensors, v. 15, n. 4, p. 83828405.
Dworak, V.; Selbeck, J.; Ehlert, D. (2011). Ranging sensors for vehicle-based measurement
of crop stand and orchard parameters: a review. Transactions Of The Asabe, v. 54, n. 4,
p. 14971510.
Escolà, A., Martínez-Casasnovas, J. A., Rufat, J., Arnó, J., Arbonés, A., Sebé, F., Pascual, M.,
Gregorio, E., Rosell-Polo, J. R. (2016). Mobile terrestrial laser scanner applications in
precision fruticulture/horticulture and tools to extract information from canopy point
clouds. Precision Agriculture, in press. DOI: 10.1007/s11119-016-9474-5
Escolà, A., Rosell-Polo, J. R., Planas, S., Gil, E., Pomar, J., Camp, F., Solanelles, F. (2013).
Variable rate sprayer. Part 1 Orchard prototype: Design, implementation and
validation. Computers and Electronics in Agriculture, 95, 122135.
Rosell, J. R., Llorens, J., Sanz, R., Arnó, J., Ribes-Dasi, M., Masip, J., Escolà, A., Camp, F.,
Solanelles, F., Gràcia, F., Gil, E., Val, L., Planas, S., Palacín, J. (2009). Obtaining the
three-dimensional structure of tree orchards from remote 2D terrestrial LIDAR
scanning. Agricultural and Forest Meteorology, 149(9), 15051515.
Rosell, J. R.; Sanz, R. (2012). A review of methods and applications of the geometric
characterization of tree crops in agricultural activities. Computers and Electronics in
Agriculture, v. 81, p. 124141.
... Thus highlighting both the considerable amount of resources used for pest and disease control, but also the potential to reduce pesticides and save costs. Current plant protection spray practices are based largely on manual and imprecise measurements of canopy volume [2,3]. Non-destructive laser scanning of trees can potentially contribute to a precise and thus sustainable application of plant protection products to the target area by collecting tree-specific canopy data [4]. ...
... To reproduce the shape of the apple tree crowns, we estimated tree volume using the alpha-shape reconstruction algorithm, which Colaço et al. [3] identified as well suited for approximating entire individual trees. Each shape is a well-defined polytope derived from the Delaunay triangulation of the point set, with an "alpha" parameter determining the level of detail obtained in the triangulation [20]. ...
... We found it challenging to set a suitable alpha value for our tree volume estimation (visualized in Fig. 4). Most studies recommend setting the alpha parameter to a value that produces the smallest volume while keeping the canopy as one solid component without holes [3,21]. By fitting an increasing alpha-shape parameter value across the tree row (Fig. 4), the effect of the alpha-shape parameter value was explored for the research trees. ...
Full-text available
Precision orchard management requires non-destructive sensor technologies to identify key sources of variation in apple yield and quality so operations such as fruit thinning, root-pruning as well as harvesting can be better targeted and optimised. We compared the data quality of two light detection and ranging (LiDAR) scanners to assess their ability to estimate the volume of ‘Braeburn’ apple trees. Scanner one was a high-quality tractor-mounted LiDAR (SICK, LDMRS 400001, Düsseldorf, Germany) and the second system consisted of two lower-cost SICK LiDAR sensors fitted on a commercial orchard sprayer. To compare the two scanner systems, two tree row sections with different growth vigour were created by targeted root pruning to reduce annual shoot growth. LiDAR scans and reference assessments were made at the end of the growing season. In addition, LiDAR data were obtained at two tractor speeds: 1.5 and 7.0 km/h (standard spraying speed). Results show key canopy features like the beginning/end of rows or large gaps can be detected with the lower-cost sensors. However, tractor speed had a major effect on data quality. At 1.5 km/h, alpha-shaped tree volumes of the high-quality LiDAR show a high correlation (R² = 0.84) with the reference assessments, whereas the data quality of the lower-cost sensors was not high enough to represent the tree volume with the alpha-shape algorithm (R² = 0.09). Moreover, this work raises the question of how precise a sensor-based tree volume needs to be determined to describe heterogeneity in an orchard. Specifically, how to best match sensor data to manual methods of canopy measurement and allow sensor data to be used for multiple applications.
... The canopy volume is the basis for the calculation of the precise variable for the spraying amount [13][14][15]. The main canopy volume calculation methods are the regular geometry method [16,17], slice method [18][19][20], alpha-shape algorithm [21], convex hull algorithm [22], and voxel simulation method [23][24][25]. The regular geometry method describes the canopy as a stack of one or more regular geometries, a method which is more suitable for regularly shaped fruit trees. ...
... The volume value calculated by constructing the canopy contour is larger than the actual value, which is reflected in the verification of the convex hull algorithm and alpha shape algorithm, as well as the methods proposed by Cai and Gu [21,22,27,28]. Comparative analysis shows that the CADA method reduces the amount counted in the outer margin voids and improves the detection accuracy. ...
Full-text available
The canopy volume of fruit trees is an important input for the precise and varying application of pesticides in orchards. The fixed mesh division method is mostly used to calculate canopy volumes with variable target-oriented spraying. To reduce the influence of the working speed on the detection accuracy under a fixed mesh width division, the cuboid accumulation of divided areas (CADAs), which is a light detection and ranging (LiDAR) online detection method for a fruit tree canopy volume based on dynamic mesh division, is proposed in this paper. In the method, the area is divided according to the number of unilateral nozzles of the sprayer in the canopy height direction of the fruit tree, and the mesh width is dynamically adjusted according to the change in the working speed in the moving direction of the sprayer. To verify the accuracy and applicability of the method, the simulation canopy and peach tree canopy detection experiments were carried out. The test results show that the CADA method can be used to calculate the contour and volume of the canopy. However, detection errors easily occur at the edge of the canopy, resulting in a detection error of 8.33% for the simulated canopy volume. The CADA method has a good detection accuracy under different moving speeds and fruit tree canopy sizes. At a speed of 1 m/s, the detection accuracy of the canopy volume reaches 99.18%. Compared with the existing canopy volume calculation methods based on the alpha-shape algorithm and canopy meshing-profile characterization (CMPC), the detection accuracy of the CADA method is 2.73% and 7.22% better, respectively. This method can not only reduce the influence of the moving speed on the detection accuracy of the canopy volume, but also improve the detection accuracy. Thus, this method can provide theoretical support for the research and development of target-oriented variable spraying control systems for orchards.
... Researchers have explored different sensing techniques like 2D/3D light detection and ranging (LiDAR) [11] [5] [12] [13] [14], and RGB as well as multispectral imagery [15] [16] [7] for estimation of tree/vine canopy volume. Digital 3D reconstruction of the canopy can provide an accurate estimation of its volume [17]. ...
... Tree canopy volume can be used to evaluate crop development, vigor, and yield potential, where trees with a larger TCV produce more fruit than smaller canopy volumes (Colaço et al., 2017). The TCV of Hamlin trees was inherently larger for trees budded on Cleopatra rootstocks than on Swingle rootstocks irrespective of nutrient treatments. ...
Full-text available
Citrus production in Florida declined steadily because of Huanglongbing (i.e., HLB, citrus greening) caused by the bacteria Candidatus Liberibacter asiaticus. The objectives of the study were to determine whether leaf tissue nutrient concentration, tree growth, fruit yield, and juice content were improved with split applications of essential nutrients on selected rootstocks on Florida sandy soils. The treatments were arranged in a split‐split plot design where the nitrogen (N) was fertigated in 20 splits and the Ca + Mg nutrients were also split three times coinciding with the spring, summer, and late summer flush seasons on trees budded on two rootstocks of ‘Hamlin’ citrus trees [ Citrus sinensis (L.) Osbeck]. A significant difference in leaf N, calcium (Ca), and magnesium (Mg) concentration were detected between rootstocks when trees received the highest N rate and remained within the optimum range of critical nutrition concentration even with the lowest N rate, suggesting a lower N requirement with split N applications. Yet, leaf Mg concentration remained in the minimum range implying a low soil Mg pool. For Ca, Mg, and Ca + Mg treatments, we recorded 1.41×, 1.23×, and 1.23× and 1.22×, 1.26×, and 1.30× greater tree canopy volumes (TCV) on Cleopatra and Swingle rootstocks, respectively, as compared with control trees. Significantly greater fruit yield was detected for trees budded on Cleopatra rootstocks that received either Ca or Ca + Mg treated trees with 59.7 and 63.0 kg tree –1 as compared with the control trees (36.9 kg tree –1 ), respectively. A magnitude of 1.14× more average fruit weight than control trees was noted for trees budded on Swingle rootstock in response to Mg nutrition. Therefore, the application of essential nutrients has a positive impact to ameliorate tree growth and nutrient deficiency associated with Candidatus Liberibacter asiaticus‐induced problems, thereby improving tree growth and yield.
Full-text available
Plant physiological status is the interaction between the plant genome and the prevailing growth conditions. Accurate characterization of plant physiology is, therefore, fundamental to effective plant phenotyping studies; particularly those focused on identifying traits associated with improved yield, lower input requirements, and climate resilience. Here, we outline the approaches used to assess plant physiology and how these techniques of direct empirical observations of processes such as photosynthetic CO2 assimilation, stomatal conductance, photosystem II electron transport, or the effectiveness of protective energy dissipation mechanisms are unsuited to high-throughput phenotyping applications. Novel optical sensors, remote/proximal sensing (multi- and hyperspectral reflectance, infrared thermography, sun-induced fluorescence), LiDAR, and automated analyses of below-ground development offer the possibility to infer plant physiological status and growth. However, there are limitations to such ‘indirect’ approaches to gauging plant physiology. These methodologies that are appropriate for the rapid high temporal screening of a number of crop varieties over a wide spatial scale do still require ‘calibration’ or ‘validation’ with direct empirical measurement of plant physiological status. The use of deep-learning and artificial intelligence approaches may enable the effective synthesis of large multivariate datasets to more accurately quantify physiological characters rapidly in high numbers of replicate plants. Advances in automated data collection and subsequent data processing represent an opportunity for plant phenotyping efforts to fully integrate fundamental physiological data into vital efforts to ensure food and agro-economic sustainability.
The critical components for applying the correct amount of agrochemicals are fruit tree characteristics such as canopy height, canopy volume, and canopy coverage. An unmanned aerial vehicle (UAV)-based tree canopy characteristics measurement system was developed using image processing approaches. The UAV captured images using a high-resolution red-green-blue (RGB) camera. A digital surface model (DSM) and a digital terrain model (DTM) were generated from the captured images. A tree canopy height map was generated from the subtraction of DSM and DTM. A total of 24 apple trees were randomly targeted to measure the canopy characteristics. Region of interest (ROI) was generated across the boundary of each targeted tree. The height of all pixels within each ROI was computed separately. The pixel with maximum height was considered as the height of the respective tree. For computing canopy volume, the sum of all pixel heights from individual ROI was multiplied by the square of ground sample distance (GSD) of 5.69 mm•pixel⁻¹. A segmentation method was employed to calculate the canopy coverage of the individual trees. The segmented canopy pixel area was divided by the total pixel area within the ROI. The results showed an average relative error of 0.2 m (6.64%) while comparing automatically measured tree height with ground measurements. For tree canopy volume, a mean absolute error of 0.25 m³ and a root mean square error of 0.33 m³ were achieved. The study estimated the possible agrochemical requirement for spraying the fruit trees, ranging from 0.1 to 0.32 liter based on tree canopy volumes. The overall investigations suggest that the UAV-based tree canopy characteristics measurements could be a potential tool to calculate the pesticide requirement for precision spraying applications in tree fruit orchards.
Accurate canopy mapping and head-volume estimation of large areas of broccoli is an important prerequisite for precision farming since it provides important phenotypic traits associated with field management, environmental control, and yield prediction. Currently, the detection and characterization of broccoli mostly rely on ground surveys and human interpretation, which is often time- and labor-intensive. Recent developments based on unmanned aerial vehicle (UAV) remote sensing offer low cost, timely, and flexible data acquisition, thereby providing a potential alternative technique to enhance in situ field surveys. The combination of UAV data and deep learning has led to a series of breakthroughs in rapid and automated collection of simultaneous multisensor and multimodal plant phenotyping data. However, their application for monitoring broccoli remains problematic when faced with the significant spatial scale involved and the variety of vegetation species. To address this problem, we propose herein a fast and reliable semi-automatic workflow based on deep learning to process UAV RGB imagery and LiDAR point clouds and thereby remotely detect and characterize broccoli canopy and heads. First, we explore the use of TransUNet to differentiate canopy and non-canopy regions in RGB images at the individual-plant scale. The results demonstrate that TransUNet consistently achieves the highest accuracy (average returned Precision, Recall, F1 score, and IoU of 0.917, 0.864, 0.901, and 0.895, respectively) compared with three CNN-based and two shallow learning-based approaches. In addition, TransUNet performs best in terms of robustness against variations in training samples. Subsequently, to estimate the volume of broccoli heads, a point cloud transformer (PCT) network is developed for point cloud segmentation. Improving upon the results of three existing methods PointNet, PointNet++, and K-means that were applied to the same datasets, the best-performing PCT produced a precision of 0.914, an overall recall of 0.899, an overall F1 score of 0.901, and an overall IoU of 0.879. A regression analysis indicates that the PCT estimates had R² = 0.875, RMSE = 18.62, and rRMSE = 3.64 %, which is also superior to the results from other comparison approaches. Collectively, the wide application of such technology would facilitate applied research in plant phenotyping and precision agro-ecological applications and field management.
Currently, air-assisted spraying is the most widely used high-efficiency pesticide spraying method used for treating fruit trees. Airflow from fans transports droplets into the canopy through kinetic energy. However, it changes the shape of the canopy and affects the deposition of droplets in the canopy. In this paper, through wind tunnel experiments, the drag forces exerted on three fruit trees (pear, peach and camellia) with different morphological characteristics were tested under different windspeeds. Changes in frontal area, canopy edge displacement, and optical porosity were recorded to determine the response of the trees that had different reconfiguration capabilities to the airflow and investigate the influence of porosity on morphological changes. The relationship between the drag force and windspeed was fitted through a power function, and the mean Vogel exponent for the pear, peach and camellia trees were −0.43, −0.54, and −0.31, respectively. Experimental results showed that the Vogel number of the same species of tree decreased with increasing porosity, and the morphological response of the canopy to the airflow was affected by the Vogel exponent. Canopy porosity had a significant impact on the Vogel exponent and the morphological changes of the canopy decreasing Vogel exponent with increasing porosity.
As an important part of urban greening, the canopy of street trees has ecological benefits, such as oxygen production, noise reduction, and dust reduction. The living vegetation volume (LVV) can reflect the spatial structure of the canopy intuitively and enables the estimation of the ecological service value of street trees. Terrestrial laser scanning (TLS) has shown excellent performance for providing three-dimensional data of individual trees with high precision, enabling the accurate quantification of the LVV. In this study, we divided the LVV into the total living vegetation volume (tLVV) and the effective living vegetation volume (eLVV); the latter does not include branches. The eLVV of 40 ginkgo trees separated in two roads in Nanjing was calculated from TLS data. A novel method named LAIM for accurate eLVV calculation based on point cloud data was proposed. The point cloud data of individual tree was segmented along the Z-axis and image processing methods were used. With this, eLVV of each tree was obtained. The results were compared with data obtained from a clustered point cloud generated using convex hulls. The Bland-Altman analysis was used to investigate the consistency of the two methods. Furthermore, we used correlation analysis and all-subsets regression to choose the variables, and the eLVV was fitted using six models. Finally, we evaluated O2 production, CO2 and SO2 absorption by the street trees based on eLVV, the ecological benefits of street trees were quantified. The results showed the following: (1) The number of layers and the dilation size of the point cloud were crucial parameters in the LAIM. (2) For ginkgo trees, the mean difference between the eLVV obtained from the LAIM and the convex hull method was -0.53 to 0.19 m³, indicating that the results were highly consistent for the two methods. (3) The eLVV fitting performance was better for the exponential function model (R²=0.8523, RMSE=0.6838 m³) and linear model (R²=0.8361, RMSE=0.7224 m³). The tree height and crown width significantly affected the eLVV estimation. (4) The evaluation about ecological benefits of Zhaoyang Road was better than Cuizhu Road. The quantified ecological benefits were conducive to road ecological evaluation. This study quantified the eLVV of individual trees using TLS, highlighting the importance of live vegetation in urban greening. The results can provide technical support for estimating the ecological service value of urban street trees.
Full-text available
Brazilian fruit culture has a great influence on the social and economic sector in the most diverse regions of the country, generating employment and income in the exercise of its activities. As it is an activity carried out most often in a manual and conventional manner, fruit culture has a great potential for technological growth, especially when adopting the concepts applied by precision agriculture on the crops of grains, fibers and energy, creating a new segment, Precision Fruit Farming. The present work aims to carry out a bibliographic review on the main trends that have emerged in the last five years on Precision Fruit growing, highlighting its future perspectives and the history of technological evolution. 83 articles were analyzed, classified in different perennial cultures and applications, such as machine learning, remote sensing, robotics, using UAV to obtain different vegetation indexes, among others.
Full-text available
LiDAR sensors are widely used in many areas and, in recent years, that includes agricultural tasks. In this work, a self-developed mobile terrestrial laser scanner based on a 2D light detection and ranging (LiDAR) sensor was used to scan an intensive olive orchard, and different algorithms were developed to estimate canopy volume. Canopy volume estimations derived from LiDAR sensor readings were compared to conventional estimations used in fruticulture/horticulture research and the results prove that they are equivalent with coefficients of correlation ranging from r=0.56 to r=0.82 depending on the algorithms used. Additionally, tools related to analysis of point cloud data from the LiDAR-based system are proposed to extract further geometrical and structural information from tree row crop canopies to be offered to farmers and technical advisors as digital raster maps. Having high spatial resolution information on canopy geometry (i.e. height, width and volume) and on canopy structure (i.e. light penetrability, leafiness and porosity) may result in better orchard management decisions. Easily obtainable, reliable information on canopy geometry and structure may favour the development of decision support systems either for irrigation, fertilization or canopy management, as well as for variable rate application of agricultural inputs in the framework of precision fruticulture/horticulture.
Full-text available
This paper presents the use of a terrestrial light detection and ranging (LiDAR) system to scan the vegetation of tree crops to estimate the so-called pixelated leaf wall area (PLWA). Scanning rows laterally and considering only the half-canopy vegetation to the line of the trunks, PLWA refers to the vertical projected area without gaps detected by LiDAR. As defined, PLWA may be different depending on the side from which the LiDAR is applied. The system is completed by a real-time kinematic global positioning system (RTK-GPS) sensor and an inertial measurement unit (IMU) sensor for positioning. At the end, a total leaf wall area (LWA) is computed and assigned to the X, Y position of each vertical scan. The final value of the area depends on the distance between two consecutive scans (or horizontal resolution), as well as the number of intercepted points within each scan, since PLWA is only computed when the laser beam detects vegetation. To verify system performance, tests were conducted related to the georeferencing task and synchronization problems between GPS time and central processing unit (CPU) time. Despite this, the overall accuracy of the system is generally acceptable. The Leaf Area Index (LAI) can then be estimated using PLWA as an explanatory variable in appropriate linear regression models.
Full-text available
In recent years, LIDAR (light detection and ranging) sensors have been widely used to measure environmental parameters such as the structural characteristics of trees, crops and forests. Knowledge of the structural characteristics of plants has a high scientific value due to their influence in many biophysical processes including, photosynthesis, growth, CO2-sequestration and evapotranspiration, playing a key role in the exchange of matter and energy between plants and the atmosphere, and affecting terrestrial, above-ground, carbon storage. In this work, we report the use of a 2D LIDAR scanner in agriculture to obtain three-dimensional (3D) structural characteristics of plants. LIDAR allows fast, non-destructive measurement of the 3D structure of vegetation (geometry, size, height, cross-section, etc.). LIDAR provides a 3D cloud of points, which is easily visualized with Computer Aided Design software. Three-dimensional, high density data are uniquely valuable for the qualitative and quantitative study of the geometric parameters of plants. Results are demonstrated in fruit and citrus orchards and vineyards, leading to the conclusion that the LIDAR system is able to measure the geometric characteristics of plants with sufficient precision for most agriculture applications. The developed system made it possible to obtain 3D digitalized images of crops, from which a large amount of plant information – such as height, width, volume, leaf area index and leaf area density – could be obtained. There was a great degree of concordance between the physical dimensions, shape and global appearance of the 3D digital plant structure and the real plants, revealing the coherence of the 3D tree model obtained from the developed system with respect to the real structure. For some selected trees, the correlation coefficient obtained between manually measured volumes and those obtained from the 3D LIDAR models was as high as 0.976.
Efficient information management in orchard characterization leads to more efficient agricultural processes. In this brief, a set of computational geometry methods are presented and evaluated for orchard characterization; in particular, for the estimation of canopy volume and shape in groves and orchards using a LiDAR (Light Detection And Ranging) sensor mounted on an agricultural service unit. The proposed approaches were evaluated and validated in the field, showing they are convergent in the estimation process and that they are able to estimate the crown volume for fully scanned canopies in real time; for partially observed tree crowns, accuracy decreases up to 30% (the worst case). The latter is the major contribution of this brief since it implies that the automated service unit does not need to cover all alley-ways for an accurate modeling of the orchard, thus saving valuable resources.
Discussions in recent decades about dosage models for applying plant protection products in orchards have failed to reach a compromise solution. Furthermore, canopies are spatially variable, and a uniform dose may not be adequate for the entire orchard. Spraying at an adequate volume application rate on a site-specific basis would help reduce the amount of agrochemicals used in the framework of precision horticulture and precision fructiculture.An orchard sprayer prototype running a variable-rate algorithm to adapt the volume application rate to the canopy volume in orchards on a real-time and continuous basis was designed, implemented, and validated. An equivalent prototype was designed for vineyards and described in a companion paper (‘Variable rate sprayer. Part 2 – Vineyard prototype: Design, implementation and validation’). The orchard prototype was divided into three parts: the canopy characterization system (using a LiDAR sensor), the controller executing a variable-rate algorithm, and the actuators. The controller determines the intended flow rate by using an application coefficient (required liquid volume per unit canopy volume) to convert canopy volume into a flow rate. The sprayed flow rates are adjusted via electromagnetic variable-rate valves. The goal of the prototype was to keep the actual application coefficients as close as possible to the objective.Strong relationships were observed between the intended and the sprayed flow rates (R2 = 0.935) and between the canopy cross-sectional areas and the sprayed flow rates (R2 = 0.926). In addition, when spraying in variable-rate mode, the prototype achieved significantly closer application coefficient values to the objective than those obtained in conventional spraying application mode.
This paper presents the foundations and applications in agriculture of the main systems used for the geometrical characterization of tree plantations, including systems based on ultrasound, digital photographic techniques, light sensors, high-resolution radar images, high-resolution X-ray computed tomography, stereo vision and LIDAR sensors. Amongst these, LIDAR laser scanners and stereo vision systems are probably the most promising and complementary techniques for achieving 3D pictures and maps of plants and canopies. The information about the geometric properties of plants provided by these techniques has innumerable applications in agriculture. Some important agricultural tasks that can benefit from these plant-geometry characterization techniques are the application of pesticides, irrigation, fertilization and crop training. In the field of pesticide application, knowledge of the geometrical characteristics of plantations will permit a better adjustment of the dose of the product applied, improving the environmental and economic impact. However, it is still necessary to resolve several technological and commercial questions. The former include improving detection systems, especially with regard to developing software for the post-processing steps and improving the speed of calculation and decision making. Amongst the latter, it is essential to produce low cost sensors and control systems in order to facilitate large-scale deployment. Obtaining a precise geometrical characterization of a crop at any point during its production cycle by means of a new generation of affordable and easy-to-use detection systems, such as LIDAR and stereo vision systems, will help to establish precise estimations of crop water needs as well as valuable information that can be used to quantify its nutritional requirements. If accurate, this can provide valuable information on which to base more sustainable irrigation and fertilizer dosages. These would be able to meet crop needs and could also be used as part of specific management systems, based on prescription maps, for the application of variable quantities of water and fertilizers. The availability of measurement tools that allow a precise geometric characterization of plantations will also facilitate and enhance research aimed at developing better crop training systems that ensure an optimal distribution of light within the treetops and higher fruit quality. It is therefore of vital importance to continue devoting major efforts to the development of increasingly accurate, robust and affordable systems capable of measuring the geometric characteristics of plantations, which support the development of the different areas of a sustainable and precision agriculture.
In agricultural crop production, information important for optimizing production processes (precision farming) and reducing the environmental impact can be obtained from soils and plants with sensors. Ranging sensors are utilized in research activities that use remote-sensing techniques. In this work, three types of ranging sensors or measuring principles (light detection and ranging (LiDAR), radar, and ultrasonic) are evaluated for practical use with agricultural machinery to improve production processes. In the first part of this article, the fundamentals of the prescribed measuring principles are described. Based on the relevant literature, state-of-the-art sensor groups for measuring morphologic crop stand and orchard parameters are presented and discussed in the second section. In the third section, the sensors are assessed regarding their suitability for installation on agricultural machinery under field conditions; specifically, their functional parameters are evaluated (e.g., working distance, mounting height, inclination angle, resolution, and measurement frequency) along with experimental data obtained in scientific investigations. The positive test results in the application of the measuring principles presented in previous publications are reviewed and, based on a summary assessment, the LiDAR measuring principle is indicated as the preferred solution for vehicle-based measurement of crop stand and orchard parameters.
Acompanhamento de safra brasileira: laranja, terceiro levantamento, dezembro
  • Conab Companhia
  • De Abastescimento
CONAB. COMPANHIA NACIONAL DE ABASTESCIMENTO. (2013) Acompanhamento de safra brasileira: laranja, terceiro levantamento, dezembro/2013. Brasília, 16p.
Mobile terrestrial laser scanner applications in precision fruticulture/horticulture and tools to extract information from canopy point clouds. Precision Agriculture
  • A Escolà
  • J A Martínez-Casasnovas
  • J Rufat
  • J Arnó
  • A Arbonés
  • F Sebé
  • M Pascual
  • E Gregorio
Escolà, A., Martínez-Casasnovas, J. A., Rufat, J., Arnó, J., Arbonés, A., Sebé, F., Pascual, M., Gregorio, E., Rosell-Polo, J. R. (2016). Mobile terrestrial laser scanner applications in precision fruticulture/horticulture and tools to extract information from canopy point clouds. Precision Agriculture, in press. DOI: 10.1007/s11119-016-9474-5