Applied Artificial Intelligence

An International Journal

ISSN: (Print) (Online) Journal homepage: https://www.tandfonline.com/loi/uaai20

Automatic Detection of Oil Palm Tree from UAV

Images Based on the Deep Learning Method

Xinni Liu, Kamarul Hawari Ghazali, Fengrong Han & Izzeldin Ibrahim
Mohamed

To cite this article: Xinni Liu, Kamarul Hawari Ghazali, Fengrong Han & Izzeldin
Ibrahim Mohamed (2021) Automatic Detection of Oil Palm Tree from UAV Images
Based on the Deep Learning Method, Applied Artificial Intelligence, 35:1, 13-24, DOI:
10.1080/08839514.2020.1831226

To link to this article: https://doi.org/10.1080/08839514.2020.1831226

Published online: 22 Oct 2020.

Submit your article to this journal

Article views: 2861

View related articles

View Crossmark data

Citing articles: 32 View citing articles

Full Terms & Conditions of access and use can be found at

https://www.tandfonline.com/action/journalInformation?journalCode=uaai20
APPLIED ARTIFICIAL INTELLIGENCE
2021, VOL. 35, NO. 1, 13–24
https://doi.org/10.1080/08839514.2020.1831226

Automatic Detection of Oil Palm Tree from UAV Images

Based on the Deep Learning Method
Xinni Liu, Kamarul Hawari Ghazali, Fengrong Han, and Izzeldin Ibrahim Mohamed
Faculty of Electrical and Electronics Engineering, Universiti Malaysia Pahang, Pekan, Malaysia

ABSTRACT
Palm oil is a major contributor to Malaysia’s GDP in the agricul­
ture sector. The sheer vastness of oil palm plantations requires
a huge effort to administer. An oil palm plantation in regards to
the irrigation process, fertilization, and planning for planting
new trees require an audit process to correctly count the oil
palm trees. Currently, the audit is done manually using aerial
view images. Therefore, an effective and efficient method is
imperative. This paper proposes a new automatic end-to-end
method based on deep learning (DL) for detection and counting
oil palm trees from images obtained from unmanned aerial
vehicle (UAV) drone. The acquired images were first cropped
and sampled into small size of sub-images, which were divided
into a training set, a validation set, and a testing set. A DL
algorithm based on Faster-RCNN was employed to build the
model, extracts features from the images and identifies the oil
palm trees, and gives information on the respective locations.
The model was then trained and used to detect individual oil
palm tree based on data from the testing set. The overall
accuracy of oil palm tree detection was measured from three
different sites with 97.06%, 96.58%, and 97.79% correct oil palm
detection. The results show that the proposed method is more
effective, accurate detection, and correctly counts the number
of oil palm trees from the UAV images.

Introduction
The most important economic crop in Malaysia and other tropical countries
such as Indonesia, Nigeria, and Thailand are the oil palm trees. It is one of the
main contributors to Malaysia’s Gross Domestic Product (GDP) and foreign
exchange incomes. Palm oil has also become the main source of vegetable oil
due to its high production yield compared to rapeseed, sunflower, and soybean
(Hansen et al. 2015). Malaysia has a total of 4.49 million hectares of oil palm
plantations, which produces approximately 17.73 million tons of palm oil
each year (Nambiappan et al. 2018). Hence, one of the key tasks in plantation
management is to count the number of oil palm trees, also known as the oil
palm tree audit. The process allows the plantation manager to estimate the

CONTACT Xinni Liu [email protected] Faculty of Electrical and Electronics Engineering, Universiti
Malaysia Pahang, Pekan, Malaysia
© 2020 Taylor & Francis
14 X. LIU ET AL.

yield of plantation and plan the weeding and fertilization strategy (Huth et al.
2014). The audit also facilitates the irrigation improvement process, planting
of new trees, and managing old and dead trees (Kattenborn et al. 2014).
Recent studies show that there are three main methods of classification and
detection of oil palm trees which are image processing, machine learning, and
deep learning (DL). Implementation of the image processing method is more
direct in which the algorithm is used to extract the features of an object such as
shape, edge, and color, then perform direct manipulation or transformation of
the pixel values of the images. The challenging part of image processing in
object detection is when the object is crowded in one place, overlapped with
other objects or the background is complex (Sheng et al. 2012). In reference
(Nam et al. 2016), Scale Invariant Feature Transform (SIFT) based on image
processing methods was used to detect oil palm trees. SIFT key points were
extracted together with local binary patterns to analyze the texture of the
overall region from aerial images. The method achieved 91.11% accuracy of
oil palm tree detection. More progressive image processing method has been
used to mask areas of palm oil plantations (Korom et al. 2014). The features of
the oil palm trees were derived using the vegetation indices and kappa
statistics. Optimal thresholding was used to distinguish between a tree and
non-tree region. The method yielded a 77% accuracy of oil palm tree detection.
In reference (Manandhar, Hoegner, and Stilla 2016), the oil palm tree shape
feature was represented by the result of the circular autocorrelation of the
polar shape matrix. The shape feature was extracted using the sliding window
method. An algorithm to detect the local maximum was used to detect the
palm trees in different tough scenarios. The average detection accuracy
obtained was 84%.
For the machine learning methods, hand-crafted features are still needed by
the simple trainable classifier to segment the oil palm tree image as individual
tree crowns and extract the feature before applying a predefined classier for
detection and classification. In reference (Rizeei et al. 2018), object-based
image analysis (OBIA) and support vector machine (SVM) method were
used for oil palm tree counting in Worldview-3 satellite image and range
(LiDAR) airborne imagery. The oil palm tree detection result was 98% on
the testing site, but only satellite and LiDAR airborne imageries were used in
this method. Machine learning methods are highly dependent on hand-crafted
features. When dealing with new data, new hand-crafted features based on the
new data are required, which can be costly. The extraction method is then
repeated with the new features; however, the process proves to be tedious
(Fassnacht et al. 2016).
Presently, DL methods have been widely used in many applications, parti­
cularly in image detection and classification (Alliez et al. 2017; Kemker,
Salvaggio, and Kanan 2018; Rezaee et al. 2018). DL is essentially a subset of
machine learning which belongs to the broader family of artificial intelligence.
 APPLIED ARTIFICIAL INTELLIGENCE 15

DL is based on artificial neural network (ANN) that has a network of numer­

ous hidden layers. Unlike machine learning algorithms that almost always
require structured data, deep learning has networks that are capable of super­
vised or unsupervised learning from labeled or unlabeled data. Li et al. (Li et al.
2016) used DL to classify oil palm trees from high-resolution remote sensing
images collected by the QuickBird satellite. A sliding window and post-
processing approaches were used to detect the oil palm trees. This method
achieved a detection accuracy of 96%. Maciel et al. (Zortea et al. 2018) trained
two independent convolutional neural networks with two input sizes 32 × 32
and 64 × 64 for capturing both the coarse and fine details of the oil palm tree
image. The estimated probabilities for each oil palm tree were combined by
averaging the results from two detection networks, and the overall accuracies
for the method were in the range between 91.2% and 98.8%. Both of the two
methods used DL image classification methods.
From the previous studies in (Korom et al. 2014; Manandhar, Hoegner, and
Stilla 2016; Nam et al. 2016), the drawback is essentially on the accuracy of the
detection. DL methods have proven to increase the accuracy percentage (Li
et al. 2016; Zortea et al. 2018). In this paper, an oil palm tree image detection
algorithm using a DL Faster RCNN approach is described. The input images
are aerial images from the UAV drone, which is presently widely used in
modern precision agriculture.

Deep Learning Method for Oil Palm Tree Counting

Deep Learning Method Overview

The method proposed in this paper employed state-of-the-art DL based on the

Faster RCNN approach to build and train the oil palm tree detection model
(Ren et al. 2017). High-resolution drone images were cropped into multiple
sub-images and were arranged into training, validation, and testing data.
Figure 1 shows the flowchart of the proposed DL method. Figure 2 shows
the sample of the original high-resolution oil palm tree image in a plantation.
The images in the training dataset go through a random process of brightness
enhancement for augmentation purposes. The augmentation process increases
the total number of the training dataset, which reduces the overfitting problem
(Guo et al. 2016). The training dataset and the validation dataset were made
into labeled data. Next, the convolutional neural network (CNN) was imple­
mented based on the Faster RCNN framework. The labeled images in the
training dataset were used to train the network and measure the detection
accuracy based on the testing dataset. The network parameters of the Faster
RCNN were tuned continuously until the best combinations which contribute
to a high percentage of detection were obtained. These combinations were also
used for accuracy analysis.
16 X. LIU ET AL.

Figure 1. Flowchart of the proposed DL method.

Figure 2. High-resolution of a palm tree image used.

 APPLIED ARTIFICIAL INTELLIGENCE 17

Faster RCNN

The Faster RCNN model consisted of the convolution network, region pro­
posal network (RPN), region of interest (ROI) pooling, softmax classification,
and bounding box regression. Figure 3 shows the training process of the
method using the datasets described in Section 2.1. Once the network was
trained, the performance of the network model was tested using the validation
and testing dataset.
For the network training, the labeled training dataset was introduced to the
convolution layer, which will extract the deep features of the image to produce
the feature map of the input image. The feature map was then fed into the RPN
layer. The RPN was trained to yield the region with probable oil palm trees.
The probable region is marked by an orange box which contains the prob­
ability score of oil palm trees. The obtained feature map and the proposed
region were fed into the ROI layer to generate proposed regions based on the
previously obtained feature map. The information is then fed to the fully
connected layer and by using the softmax classification and bounding box
regression, the final tree detection was obtained. The final network was
validated and tested.
The loss function during the training contains the classification loss, Lcls and
the region loss, Lreg is shown by Equation (1), where i indicates the bounding
box index, pi is the foreground softmax probability, and p�i is the probability
for ground truth box, ti indicates the predicted bounding box, ti� is the corre­
sponding ground truth box for the foreground bounding box. The training
aims to minimize the loss. Ncls indicates the number of class and Nreg indicates
the number of the proposal regions, parameter μ is used to balance the
difference between Ncls and Nreg . The classification loss Lcls was calculated as
the loss after softmax classification, the regression loss Lreg for bounding box
regression was calculated by Smooth L1 loss, �shown as� Equation (2).
Parameter ti� is the ground truth box while ti ¼ tx ; ty ; tw; th indicates the
parameter of the predicted bounding box. The non-maximum suppression
was used to further obtain the proposed region containing the oil palm trees.

Figure 3. The training process of faster RCNN.

18 X. LIU ET AL.

1 X � 1 X � �
Lðfpi g; fti gÞ ¼ Lcls pi ; p�i þ μ pi Lreg ti; ti� (1)
Ncls i Nreg i

� X �
Lreg ti ; ti� ¼ SmoothL1 ti ti� (2)
i2fx;y;w;hg

�
0:5X 2 if jXj < 1
SmoothL1ðXÞ ¼ (3)
jXj 0:5otherwise

Experimental Analysis
Dataset
In this research, the aerial view image data were acquired by a drone services
company. The images were of a 22 hectares oil palm tree plantation. The drone
has a band order of red, blue, and green (RGB) and its ground sample distance
(GSD) is 5 cm per pixel. The plantation contains different age groups of trees
between 2 and 16 years old. The oil palm trees are crowded in some areas,
overlapped with some other vegetation, or sparsely distributed in other areas,
as shown in Figure 4. The original image is 7837 × 23608, which was cropped
into 700 sub-images with 600 × 500 pixels; 500 of these images were set as the
training data, 100 images were chosen as the validation dataset and another
100 images as the testing dataset. For the DL network to achieve optimum
accuracy, the training dataset should consist of all possible conditions of the oil

Figure 4. Oil palm tree plantation.

 APPLIED ARTIFICIAL INTELLIGENCE 19

(a)Crowded palm trees (b)Overlapped with other vegetation

(c)Sparsely distributed trees (d)Boundary with few trees

Figure 5. The training samples.

palm trees in terms of age, surrounding vegetation, and background. Shown in

Figure 5 are the samples of training dataset with different ages and distribution
of trees; crowded mature palm trees, overlapped with other vegetation, spar­
sely distributed and boundaries with a few palm trees.

Faster RCNN Parameter Configuration

The popular classical VGG16 network trained from ImageNet was used as the
backbone of the convolution network (Karen Simonyan 2014). The weights of
first 1–5 convolutional layer remain unchanged while the weights of the 6th-
7th convolutional layer were converted to the fully connected layers. The
weights were changed accordingly, where 6th full connected layer has 512
kernels of 7 × 7 and 7th full connected layer has 4096 kernels of 1 × 1, the ROI
pooling size is 7, all the dropout layers and the 8th full connected layer were
removed. The parameter configuration during Faster RCNN network training
is shown in Table 1. The RPN network yielded 300 proposal boxes using the
initial parameter values shown in Table 1. The softmax function was used to
classify the proposal feature maps as an object or backgrounds. The bounding
box regression method was used to obtain a more accurate proposal box.
There are two classes in this study, namely the object and the background. The
object is the oil palm tree while the background is the vegetation, empty land,
and boundary.
20 X. LIU ET AL.

Table 1. Parameter set of faster

RCNN.
Parameters Value
Learning rate 0.001
Momentum 0.9
Gamma 0.1
Weight decay 0.0005
Proposal boxes 300

Experiment Result and Accuracy Assessment

Experiment Results
The results of the presented model based on the Faster RCNN model are
shown in Figure 6. The detected oil palm trees were marked with red rectangle
boxes together with the confidence scores which indicates the score of the
confidence that the object is oil palm tree. The oil palm trees not detected were
manually marked with blue rectangle boxes. Figure 6a shows an image of
mature and crowded oil palm trees. All of the oil palm trees were successfully
detected, and the confidence score for oil palm trees is more than 0.9. Figure
6b shows similar mature oil palm trees but they were overlapped with other
vegetation, only one tree was not detected, and the confidence score obtained
for this image is more than 0.97. In Figure 6c, only three small oil palm trees

(a) Crowded palm tree (b) Overlapped with vegetations

(c) Sparely distributed palm tree (d) Boundary with few palm trees

Figure 6. Detection results on four samples. (a) Crowded palm tree, (b) overlapped with vegeta­
tions, (c) sparely distributed palm tree, (d) boundary with few palm trees.
 APPLIED ARTIFICIAL INTELLIGENCE 21

were not detected, and the confident score four small detected oil palm trees
are 0.70, 0.73, 0.86, and 0.63, respectively, while for the other detected oil palm
trees it is more than 0.9. Figure 6d shows young oil palm trees on the boundary
which were all successfully detected, and the confidence score is more than
0.92. It can be seen that Figure 6b, d have few palm trees, but the background
of Figure 6d is clearer and simpler than 6(b) and 6(c), so all the oil palm trees
are successfully detected in 6(c). Based on the characteristic of the detection
image and the detection result, it is observed that oil palm trees that appear
small in the images and oil palm trees that overlapped with other vegetation
are more difficult to detect.

Accuracy Assessment

Accuracy assessment was done by comparing the detected and the non-
detected tree to the number of actual trees in the image to measure the
precision, recall, and overall accuracy. The process was conducted manually.
The precision, recall, and overall accuracy (OA) are described by Equations
(4)-(6), where TP is the true positive detection result, indicating the total
number of correctly detected oil palm trees, FP is the false positive detection
result, which gives the number of objects incorrectly detected as oil palm trees,
and FN is the false negative detection result, which expresses the number of oil
palm trees that were not detected.
TP
Precision ¼ (4)
TP þ FP

TP
Recall ¼ (5)
TP þ FN

Precision þ Recall
OA ¼ (6)
2
The result of 100 testing dataset is given in Table 2. A total of 2326 oil palm
trees were correctly detected, 56 other vegetation were detected as oil palm
trees, and 60 oil palm trees were not detected. The precision, recall and OA are
97.65%, 97.49%, and 97.57%, respectively.
The performance of the proposed method was tested against the traditional
machine learning methods, i.e. ANN-based (Fadilah et al. 2012) and SVM-
based methods (Dalponte et al. 2015). Three other sites were selected for the
validation purposes; site A where most of the palm trees overlap with other

Table 2. Detection result of the testing set.

Data TP FP FN Precision Recall OA
Testing set 2326 56 60 97.65% 97.49% 97.57%
22 X. LIU ET AL.

vegetations, site B where the palm tree in the plantation has small size, and site
C with most of the mature oil palm trees crowded. For the ANN- and SVM-
based methods, the images were cropped into individual oil palm trees with
background and then labeled as the training set which was used to train the
ANN and SVM network to obtain parameters to develop the ANN and SVM
models. The models were then implemented to detect the oil palm trees in the
test images using a sliding window method (Pibre et al. 2017). For the
proposed method, the input images of each site were cropped to 600 × 500
pixels or less than 600 × 500 pixels sub-images. These sub-images were then
fed into the aforementioned pretrained Faster RCNN model. The detection
results for site A, site B, and site C are shown in Tables 3, 4 and 5, respectively.
The detection results of all three sites show a similar pattern; the
proposed method has the highest TP, and the lowest FP and FN com­
pared to the results of the ANN- and SVM-based methods. The stark
difference between the FP results of the proposed method compared to
the two other methods is the most interesting result. The FP produced by
the traditional methods is tenfold more compared to the proposed
method. The huge number of FP could have easily contributed to the
low percentage of precision and OA of the ANN- and SVM-based
method. The detection results from all three sites show that the proposed
method has the highest precision number and OA percentage with
a difference of approximately 10% to 17%.

Table 3. Detection result of site A.

Approach TP FP FN Precision Recall OA
ANN 705 386 25 64.62% 96.58% 80.60%
SVM 697 325 33 68.20% 95.48% 81.84%
Proposed method 710 23 20 96.86% 97.26% 97.06%

Table 4. Detection result of site B.

Approach TP FP FN Precision Recall OA
ANN 834 365 36 69.56% 95.86% 82.71%
SVM 832 263 38 75.94% 95.63% 85.79%
Proposed method 845 25 25 97.13% 96.02% 96.58%

Table 5. Detection result of site C.

Approach TP FP FN Precision Recall OA
ANN 785 182 31 81.18% 96.20% 88.69%
SVM 788 225 28 77.79% 96.57% 87.18%
Proposed method 796 16 20 98.03% 97.55% 97.79%
 APPLIED ARTIFICIAL INTELLIGENCE 23

Conclusions
This study proposed a novel approach for detecting oil palm trees from UAV
images. It employed state-of-the-art DL based on the Faster RCNN and image
pre-processing method to detect oil palm trees from drone images of the
plantation. The performance of the proposed method was compared to tradi­
tional machine learning-based ANN and SVM methods on three different
sites. The overall accuracies obtained for the proposed method were more than
96%. The proposed method outperforms the other two machine learning
methods in terms of precision and overall accuracy. The results also showed
that the proposed method was effective and robust in the detection of oil palm
trees in various plantation conditions. The object detection was unsuccessful
when the size of the oil palm trees in the images was too small, there are
overlapping background and low resolution of the object. Nonetheless, based
on the model pretrained in this paper, it takes 1.5 hour to detect and count the
22 hectares oil palm tree plantation in this study, the results were promising
which suggests that it has the potential to be used in practical applications.

Funding
This work was supported by the University Malaysia Pahang, under Grant [number
PGRS1903142].

References
Dalponte, M., L. T. Ene, M. Marconcini, T. Gobakken, and E. Næsset. 2015. Semi-supervised
SVM for individual tree crown species classification. ISPRS Journal of Photogrammetry and
Remote Sensing 110:77–87. doi:10.1016/j.isprsjprs.2015.10.010.
Fadilah, N., J. M. Saleh, H. Ibrahim, and Z. A. Halim. 2012. Oil palm fresh fruit bunch ripeness
classification using artificial neural network. Paper presented at the 2012 4th International
Conference on Intelligent and Advanced Systems (ICIAS2012), Kuala Lumpur, Malaysia,
June 12–14.
Fassnacht, F. E., H. Latifi, K. Stereńczak, A. Modzelewska, M. Lefsky, L. T. Waser, and
A. Ghosh. 2016. Review of studies on tree species classification from remotely sensed data.
Remote Sensing of Environment 186:64–87. doi:10.1016/j.rse.2016.08.013.
Guo, Y., Y. Liu, A. Oerlemans, S. Lao, S. Wu, and M. S. Lew. 2016. Deep learning for visual
understanding: A review. Neurocomputing 187:27–48. doi:10.1016/j.neucom.2015.09.116.
Hansen, S. B., R. Padfield, K. Syayuti, S. Evers, Z. Zakariah, and S. Mastura. 2015. Trends in
global palm oil sustainability research. Journal of Cleaner Production 100:140–49.
doi:10.1016/j.jclepro.2015.03.051.
Huth, N. I., M. Banabas, P. N. Nelson, and M. Webb. 2014. Development of an oil palm
cropping systems model: Lessons learned and future directions. Environmental Modelling
and Software 62:411–19. doi:10.1016/j.envsoft.2014.06.021.
Kattenborn, T., M. Sperlich, K. Bataua, and B. Koch. 2014. Automatic single tree detection in
plantations using UAV-based photogrammetric point clouds. The International Archives of
24 X. LIU ET AL.

Photogrammetry, Remote Sensing and Spatial Information Sciences 40 (3):139. doi:10.5194/

isprsarchives-XL-3-139-2014.
Kemker, R., C. Salvaggio, and C. Kanan. 2018. Algorithms for semantic segmentation of
multispectral remote sensing imagery using deep learning. ISPRS Journal of
Photogrammetry Remote Sensing Letters 145:60–77. doi:10.1016/j.isprsjprs.2018.04.014.
Korom, A., M. Phua, Y. Hirata, and T. Matsuura. 2014. Extracting oil palm crown from
WorldView-2 satellite image. Paper presented at the IOP Conference Series: Earth and
Environmental Science, Volume 18, 8th International Symposium of the Digital Earth
(ISDE8) August 2013, Kuching, Sarawak, Malaysia 26–29.
Li, W., H. Fu, L. Yu, and A. Cracknell. 2016. Deep learning based oil palm tree detection and
counting for high-resolution remote sensing images. Remote Sensing 9 (1):22–35.
doi:10.3390/rs9010022.
Maggiori, E., Tarabalka, Y., Charpiat, G. and Alliez, P., 2017. Convolutional neural networks
for large-scale remote-sensing image classification. IEEE Transactions on Geoscience and
Remote Sensing, 55(2):645–657. doi:10.1109/TGRS.2016.2612821
Manandhar, A., L. Hoegner, and U. Stilla. 2016. Palm tree detection using circular autocorrela­
tion of polar shape matrix. ISPRS Annals of Photogrammetry, Remote Sensing Spatial
Information Sciences 3:465–72.
Nam, L., L. Huang, X. J. Li, and J. Xu. 2016. An approach for coverage path planning for UAVs.
Paper presented at the 2016 IEEE 14th international workshop on advanced motion control
(AMC), Auckland, New Zealand 411–416.
Nambiappan, B., A. Ismail, N. Hashim, N. Ismail, D. Nazrima, N. Abdullah, . . . N. Ain. 2018.
Malaysia: 100 years of resilient palm oil economic performance. Journal of Oil Palm Research
30 (1):13–25. doi:10.21894/jopr.2018.0014.
Pibre, L., M. Chaumon, G. Subsol, D. Lenco, and M. Derras. 2017. How to deal with
multi-source data for tree detection based on deep learning. Paper presented at the 2017
IEEE Global Conference on Signal and Information Processing (GlobalSIP), Montreal, QC,
Canada, November 14–16.
Ren, S., K. He, R. Girshick, and J. Sun. 2017. Faster R-CNN: Towards real-time object detection
with region proposal networks. IEEE Transactions on Pattern Analysis and Machine
Intelligence 39 (6):1137–49. doi:10.1109/TPAMI.2016.2577031.
Rezaee, M., Y. Zhang, R. Mishra, F. Tong, and H. Tong. 2018. Using a VGG-16 network for
individual tree species detection with an object-based approach. Paper presented at the 2018
10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS), Beijing, China.
Rizeei, H. M., H. Z. Shafri, M. A. Mohamoud, B. Pradhan, and B. Kalantar. 2018. Oil palm
counting and age estimation from WorldView-3 imagery and LiDAR data using an inte­
grated OBIA height model and regression analysis. Journal of Sensors 2018.
Sheng, G., W. Yang, T. Xu, and H. Sun. 2012. High-resolution satellite scene classification using
a sparse coding based multiple feature combination. International Journal of Remote Sensing
33 (8):2395–412. doi:10.1080/01431161.2011.608740.
Simonyan, K. and Zisserman, A., 2014. Very deep convolutional networks for large-scale image
recognition. arXiv preprint arXiv:1409.1556
Zortea, M., M. Nery, B. Ruga, L. B. Carvalho, and A. C. Bastos. 2018. Oil-palm tree detection in
aerial images combining deep learning classifiers. Paper presented at the IGARSS 2018–2018
IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, July
22–27.