Application of Geomatics Techniques for Cultural Heritage Mapping
and Creation of an Unsafe Buildings' Cadastre
VINCENZO BARRILE*, EMANUELA GENOVESE, GIUSEPPE MARIA MEDURI
Geomatics Lab, Department of Civil Engineering, Energy, Environment, and Materials (DICEAM),
Mediterranea University of Reggio Calabria,
Via Graziella Feo di Vito - 89124, Reggio Calabria,
ITALY
*Corresponding Author
Abstract: - Mapping of Cultural Heritage is a crucial process aiming at safeguarding and promoting the unique
identity, history, and traditions of a particular community or region. This practice involves the documentation,
conservation, and interpretation of various aspects of Cultural Heritage, which can be conducted through
Geomatics techniques including the use of various tools and methods to collect, analyze, and visualize spatial
data related to heritage sites. The same techniques can be used for the identification and subsequent cataloging
of unsafe buildings thus creating a cadastre useful for authorities, urban planners, and building management
organizations to identify, monitor and address unsafe structures. In this context, this paper presents an
automatic, innovative, and experimental system through which it has been possible to map the Cultural
Heritage in a fraction of the province of Reggio Calabria and, at the same time, to build a cadastre of unsafe
structures. A prototype drone was programmed to acquire the images, subsequently pre-processed using
commercial software and analyzed using Machine Learning techniques and dedicated software. An Open GIS
(Geographic Information System), then, made it possible to view the archaeological heritage sites and the
dangerous and damaged buildings, with identified and cataloged cracks. In relation to the monitoring of
Cultural Heritage and old, unsafe buildings, several different technologies including Light Detection and
Ranging (LiDAR) and high-resolution satellite imagery are being successfully used, which involve, however,
data processing complexity and the need for specialized expertise. By overcoming the challenges of these
traditional methods, this proposed approach holds promise in facilitating comprehensive Cultural Heritage
monitoring and management even in smaller and less resource-rich areas. The use of drones for data acquisition
and integration into a well-implemented GIS, in fact, could offer a potential solution to monitor Cultural
Heritage and assess the condition of existing buildings, while saving time and costs in the process.
Key-Words: - UAV, Big Data, Machine Learning, Cultural Heritage, Digital Archaeology, Buildings, GIS
Received: February 27, 2023. Revised: June 9, 2023. Accepted: August 9, 2023. Published: September 11, 2023.
1 Introduction
Mapping cultural heritage involves identifying,
documenting, and spatially representing significant
cultural sites, monuments, landscapes, and artifacts.
The need to map Cultural Heritage arises from
several reasons: preservation of cultural heritage
that represents a community's history and identity;
protection of cultural sites to identify those at risk
and take protective measures to prevent their
degradation; cultural and tourism promotion to
support the local economy and raise community
awareness. This process can be accomplished
through various geomatics techniques, including
Geographic Information Systems (GIS) that enable
the collection, analysis, and visualization of spatial
data related to Cultural Heritage allowing for the
creation of maps displaying the distribution and
characteristics of heritage sites and providing
valuable information for planning and management
purposes; aerial imagery techniques with advanced
technologies such as Light Detection and Ranging
(LiDAR) and high-resolution satellite imagery, that
can capture high-resolution images of Cultural
Heritage sites, aiding in the identification of
archaeological remains, historical buildings, and
cultural landscapes, [1], [2], [3]. These techniques
offer an efficient and effective method to acquire
and manage high-quality geospatial data while
simultaneously creating a real register of unsafe
buildings. These technologies can generate, in fact,
detailed three-dimensional models of buildings and
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
798
Volume 19, 2023
cultural sites and, at the same time, identify
buildings that may present risks or be unsafe.
In the literature, many articles concern the
application of Geomatics in the monitoring of
Cultural Heritage and the acquisition and creation of
three-dimensional models of unsafe or vulnerable
buildings. Different remote sensing technologies are
explored for Cultural Heritage monitoring, [4],
along with the use of different geospatial data and
methodologies for Cultural Heritage management
and accurate models of objects and buildings, [5],
[6]. As known, a commonly used approach is to
combine accurate LiDAR elevation data with
detailed visual information from satellite imagery.
This process includes collecting LiDAR data from
aircraft-mounted sensors to obtain precise three-
dimensional points, processing the data to filter and
classify terrain features, acquiring high-resolution
satellite imagery to obtain detailed images of the
Earth's surface, processing the images to improve
their quality and alignment, and integrating LiDAR
data and satellite imagery.
Such approaches are often limited by the
complexity of the process or the lack of trained
personnel to interpret the acquired images, not
allowing the application of such methodologies to
smaller and more limited case studies. Additionally,
it should be noted that access to and processing of
LiDAR/Satellite data can be costly, especially if
frequent monitoring over time is desired. So, optical
imaging and LIDAR solutions are certainly accurate
and reliable tools, but costly and time-consuming, as
well as computationally expensive to process. An
alternative to these solutions could be Unmanned
Automated Vehicles (UAVs): they make it possible
to perform continuous visual inspections of
buildings, overcoming the aforementioned problems
and reducing the margin of error associated with
human operators. However, this technological
solution generates a large amount of data and
information (Big Data), necessitating more effective
and automated methods to evaluate only the
information useful for analysis and discard the
excess data, thus avoiding overloading the archives
without risking increasing or decreasing the margin
of error.
Despite various types of research in the literature
on evaluating the stability conditions of buildings
through drone data acquisition, [7], [8], creating
high-resolution 3D models of structures, [9], and
assessing the structural safety of buildings using
UAV photogrammetry, [10], there are still few
studies on using drones and machine learning
techniques for automatically construct a cadastre
displaying cultural heritage and creating a real
catalog of unsafe buildings in a given area.
For this reason, the proposed research focuses on
the study and development of an automatic system
to monitor, inspect, and map the main
archaeological sites of the area under study and
subsequently identify the cracks in buildings to
constantly update and obtain the safety status of
buildings through a GIS platform. A new automated
UAV system for monitoring and capturing large
amounts of data (Big Data) is created: a prototype
drone and an innovative recharging basis, called
Smart Grid, are implemented through which images
are collected and transmitted for elaboration. For the
pre-processing phase, KNIME software was used to
manage the amount of geo-referenced data acquired.
Then, KNIME software and traditional machine
learning techniques are applied to the images to
recognize the presence of cracks. Three
Convolutional Neural Networks are created for
crack recognition, using the Support Vector
Machine technique. Finally, on the GIS platform,
open and updatable thematic cartography is obtained
through which it is possible to represent the
characteristic elements of building geometry,
cracks’ status, their relevance, and interventions
made in the most important historical buildings.
This paper differs from related ones published in
the technical literature for several reasons: first, it
presents a technological innovation through the
implementation of an advanced, automated system
that takes advantage of cutting-edge digital
technologies. Furthermore, compared to the
technologies listed above, the proposed system has a
low economic impact while still maintaining good
accuracy compared to traditional visual inspection
methods conducted by human operators. Finally, an
additional distinguishing feature is the joint use of
different Geomatics methods, allowing multiple
objectives in monitoring buildings and conserving
Cultural Heritage to be achieved.
2 Materials and Methods
This work serves a dual purpose: the visualization
and cataloging of Cultural Heritage and the
identification of vulnerable and unsafe buildings and
structures present in the study area. To achieve these
goals, an automatic system for the acquisition of
images of Cultural Heritage and buildings and
subsequent visualization through GIS after
appropriate treatment, elaboration, and analysis of
the acquired data is created and implemented. The
process involved distinct phases: the first consists of
the acquisition of images by a drone also using an
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
799
Volume 19, 2023
innovative recharging and experimental data
transmission basis (Smart Grid); the second phase
involves the processing of the acquired data through
commercial software and machine learning
algorithms and finally, the last phase consists of the
visualization of the information obtained in an open-
source GIS. The entire system is described in the
flowchart in Fig. 1.
Fig. 1: Flowchart showing the proposed
methodology.
The task of acquiring the images for the related
processing and subsequent training of the neural
networks was assigned to a remotely piloted drone,
while to better test the transfer of the data acquired
in flight to the Smart Grid it was decided to build a
drone prototype. For the construction of the drone,
the Raspberry Pi 3 model B was used to which the
Navio 2 module was integrated, providing access to
tools such as the gyroscope, barometer, and power
management. Additionally, to ensure piloting
capabilities, PX4 Autopilot was integrated and for
the radio interface, the Service Set Identifier was
directly connected to the Smart Grid to guarantee
wireless access only to authorized devices. The
prototype drone only lacks the flight-related module
which was compensated by the commercial drone
used to acquire the pre-established images from the
flight plan set through the QGroundControll
application, allowing for mission planning and
management. The commercial drone used for image
acquisition is the remotely piloted Mavic Air 2. The
UAV used for image acquisition is presented in Fig.
2.
Fig. 2: UAV used for image acquisition.
The characteristics of this drone are well known. It
is equipped with a high resolution enabling it to
acquire video in 4K with 60 fps and capture images
with a 48 Megapixel CMOS sensor ½”.
Additionally, it also has sophisticated features like
Active Track 3.0, Spotlight, and Point of Interest
3.0, [11], [12]. After the commercial drone
completed its flight and collected the information,
the data was transferred to the prototype drone to
test the functionality of the drone-smart grid
communication. The prototype drone sends all data
to the Smart Grid via SSH protocol, and the data is
transmitted to the server through the SFTP protocol
for processing. The innovation of this research study
also lies in the creation of the Smart Grid, i.e., a
wireless charging base for drones. Besides
recharging the drone’s battery to guarantee greater
flight range, the Smart Grid also allows for
considerable efficiency in transferring information
from the platform drone and vice versa. The
physical hardware used for the Smart Grid is PC
Engines Alix. Furthermore, charging modules for
the drone and all the components used for internet
access were physically created. The drone is
recharged via this platform through a magnetic
coupling system allowing the connection between
the charging module on the smart grid and the drone
battery. The drone can recognize the location of the
smart grid platform for the connection but also
establish the point on which to land with an
accuracy of the order of a millimeter: the drone will
thus be able to recharge completely autonomously.
This type of open communication was chosen for
different reasons:
• To allow immediate communication once the
drone gets close enough to the transmitting
platform.
• To operate in a restricted area of action with a
range of two meters.
The advantages of this innovative method of
communication are numerous, including energy
savings, greater efficiency, and the possibility of
multiple connections.
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
800
Volume 19, 2023
Thus, a large amount of data was obtained. Big Data
are primarily informational resources, i.e., organized
data, [13], [14]. However, this data has such a large
volume, speed, and variety that it requires data
analytics techniques to transform it into actionable
insights.
The second phase of the research, in fact,
focused on the treatment and processing of Big Data
(images). The pre-processing phase was conducted
using commercial software called KNIME or
Konstanz Information Miner. This is a free, open-
source platform under the GPLv3 license used for
data analysis, reporting, and integration [15], [16].
The advantages of this platform are various:
- It facilitates the creation of ETL and Data
Preparation flows.
- It includes more than 200 configurable
Machine Learning algorithms.
- It offers a user-friendly interface and
immediate usability.
- It is designed for team collaboration.
- It integrates Python and R languages.
While KNIME is not a complete big data
management system like Hadoop or Apache Spark,
it can be used as a complementary big data
management tool within a larger data analytics
workflow, leveraging its data analysis,
manipulation, and integration capabilities.
Compared to other platforms KNIME has several
features that make it stand out in analyzing and
processing data. These features lie in the fact that
KNIME has in its basic version more than 200
machine learning algorithms implemented and
easily configured even by non-experts, it has an
intuitive interface, and it allows teamwork by
sharing programs and codes, configuring itself as a
useful and versatile tool. For preprocessing big data
in KNIME, a combination of standard KNIME
nodes together with the KNIME Image Processing
extension can be used. Some of the nodes used in
the pre-treatment phase of the images acquired by
drone are listed below:
- “Image Filter”: this node was used to improve
the quality, reduce the noise and adjust the contrast.
Additionally, it allowed the application of the
Gaussian filter, the median filter, and the Sobel
filter.
- “Image Compressor”: the images were reduced
in size to optimize storage space.
"Image Deduplicator": duplicate images within
the acquired dataset were removed.
Using KNIME, the images with characteristics
not compliant with the requests of the research in
question (blurry, duplicate, and redundant images)
were deleted, leaving only the useful ones.
In the following phase, images are elaborated both
with the KNIME software and traditional machine
learning algorithms. For the study under
consideration, images were subjected to machine
learning techniques that the authors had tested in
other publications, [17], [18], [19]. The acquired
images were segmented using Edge Detector and
Canny Filter and classified with the Support Vector
Machine (SVM), [20], [21], [22]. As known, the
Support Vector Machine (SVM) is a machine
learning algorithm used for classification and
regression. It is a supervised learning method that
can be employed to solve binary or multiclass
classification problems. This algorithm is
appreciated for its ability to deal with non-linear
data through the use of kernel functions, which
allow transforming the data into a high-dimensional
space where they can be separated by a hyperplane.
This makes SVM very versatile and suitable for a
wide range of classification problems. In fact, it has
proven to be effective in various domains, such as
image recognition, text classification, medical
diagnostics, and many other machine-learning
applications.
The SVM classification process involved two
distinct phases: 1) SVM Training and 2)
Performance testing. In the first phase, the
geometric characteristics of the connected
components assigned for SVM training were
computed. These features were then normalized
within a specific range. The Radial Basis Function
(RBF) kernel was chosen as a kernel trick due to the
moderate number of instances (connected regions)
and the infinite size of the transformed space with
RBF. Optimal training parameters for the SVM
were determined using grid search. To ensure
comprehensive learning of different types of cracks,
a triple cross-validation approach was employed.
The training set was divided into three equal
subsets, and the trained classifier was tested on two
subsets while using the remaining subset for
validation. The aim was to identify the most
effective parameters for predicting test data
accurately. Once the optimal parameters were
determined, SVM was trained using the "One
Against All" approach with the assistance of the
MATLAB LIBSVM library. In the second phase,
the performance of the SVM classifier was
evaluated on connected regions that were not used
during the SVM training phase. In our
experimentation, we used datasets consisting of
approximately 250,000 images. Therefore, using
Machine Learning techniques, we developed a
model capable of automatically recognizing and
identifying cracks in images. We have also
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
801
Volume 19, 2023
successfully created an open-source GIS application
that displays a map of buildings with identified
cracks and Cultural Heritage, along with the
trajectories of the drones. In this phase, the
structuring of the GIS is of significant importance to
effectively manage the acquired geospatial data and
the attributes related to the cracks. The GIS database
has been designed to be scalable and capable of
handling a large amount of data. Moreover, spatial
analyses have been conducted to identify potential
patterns among the cracks of the buildings in the
area, aiming to highlight high-risk areas.
Additionally, by interacting with the GIS interface
by means of layers, users can access all the acquired
images by clicking on the drone trajectory and
identify cracks and significant Cultural Heritage.
The peculiarity of this GIS is the ability to overlay
data about Cultural Heritage with data about unsafe
buildings, allowing for the identification of areas
with a high concentration of vulnerable cultural
sites. This integration of data provides a
comprehensive and interconnected view of cultural
heritage and structural safety issues of buildings.
3 Case Study
The proposed system has been evaluated in
Casignana, an Italian town of 710 inhabitants (Fig.
3) located in the metropolitan city of Reggio
Calabria in Calabria, South Italy. It is situated in the
Locride region and is part of the municipalities of
the “Costa dei Gelsomini”. Casignana is a small
center of the Jonico hinterland, situated on a hill at
342 m on the eastern side of Aspromonte, east of
Reggio Calabria. Located between the mountain and
the sea (in Palazzi, on the coast, the remains of the
Roman Villa of Casignana arise), the village boasts
almost untouched environmental landscapes, which
have been made accessible through naturalistic
paths that branch off from the coast inland.
Fig. 3: Casignana (Reggio Calabria, Italy), case
study.
Part of its territory is included in the Eastern
Aspromonte Mountain Community. Due to its
history, the hamlet has some religious buildings and
an Archaeological area:
• The Chiesa Matrice, named after San Giovanni
Battista, is accessed from a balcony with a ladder
and has a high altar with a painting depicting the
Blessed Virgin Mary.
• The Church of Santissima Annunziata, located at
the entrance to the village, consists of a nave with a
bell tower equipped with two bells.
• The Roman villa, located in the Palazzi district, is
the most important archaeological park of the
Roman age.
Fig. 4, Fig. 5, and Fig. 6 show some of the
images captured by the drone once the autonomous
plan flight has been established with the
QGroundControll application. In this way, images
of the Cultural/Archaeological sites of interest were
imported into the GIS allowing the visualization of
the Cultural Heritage of the region on a thematic
and virtual map.
Fig. 4: Sanctuary Madonna Delle Grazie, Casignana
(Reggio Calabria, Italy).
Fig. 5: Palazzo Barletta, Casignana (Reggio
Calabria, Italy).
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
802
Volume 19, 2023
Fig. 6: Church of San Giovanni Battista di
Casignana, Casignana (Reggio Calabria, Italy).
Particularly performing was the use of the Smart
Grid charging and transmission station. Fig. 7 shows
the image collection process: once the flight plan
was established and transmitted, the images
captured by the drone were sent to the charging
station and then to the server via the aforementioned
protocols.
Fig. 7: Images collection process.
Fig. 8: GIS: Borgo Antico, Casignana (Reggio
Calabria, Italy).
As for data exchange, a narrow range of
coverage was chosen to avoid interference problems
and especially to make sure that data exchange takes
place close to the charging point. If data were
transferred from large distances from the access
point, the transmission energy would be greater than
for a short-range transmission. Therefore, it was
chosen that the data exchange would take place near
a charging point to ensure a continuous power
source for the drone and thus neglect the problem of
battery consumption during charging. Short-range
transfer via wifi technology, (in particular, 802.11g
protocol was used, which allows a peak data rate of
54 Mbit/s), allows the maximum data rate to be
achieved.
During the flight, the drone also acquired images
related to the state of buildings around the hamlet.
Fig. 9 displays some of the images acquired by the
drone and then used for the creation of one of the
three subsets used for the training and subsequently
validation of the Neural Network. At this stage, it is
of considerable importance to acquire a substantial
number of images so that the neural network can be
effectively trained to recognize the various types of
cracks.
(a) (b)
Fig. 9 (a and b): Images highlighting buildings’
cracks.
Therefore, the images are pre-elaborated,
segmented, and classified according to the two
methods proposed and described above to obtain
and extrapolate the information we needed. Fig. 10
shows the methodology applied to the classification
of building cracks, highlighting the detection of the
cracks.
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
803
Volume 19, 2023
Fig. 10: Classification of the different types of
cracks detected.
Three types of cracks were identified by the system:
- Type 1: structural cracks involving load-bearing
components of the building, such as load-bearing
walls, foundations, and beams.
- Type 2: horizontal and vertical cracks, of
particular concern that may be indicative of lateral
pressure or differential movement or uplift of the
ground.
- Type 3: surface cracks, caused by shrinkage and
uneven settlement.
Some of the key parameters for identifying the
three crack types were extent, thickness, and
location. In this way, this experimental system has
allowed to create automatically, the first updated
map on the GIS showing the network of buildings
that need interventions. For the specific case study,
a layer was created in QGIS (on satellite base map
with reference system EPSG: 3857) related to
unsafe buildings. Regular data acquisition can be
conducted without the need for human operators,
leading to streamlined operations, cost reductions,
and time savings. The acquired data is stored in a
database that includes the coordinates of the
buildings, categorized based on the study area, type,
and conditions. The database also provides
geometric information, as well as details regarding
the conservative and functional status of the
buildings.
Fig. 11 shows the first results: blue polygons
represent the principal Cultural Heritage of the area;
red polygons represent buildings with cracks of
Type1 (most dangerous buildings needing timely
interventions); orange polygons represent buildings
with cracks of Type2 (buildings that don’t need
timely interventions but must be monitored); and
green polygons represent buildings with cracks of
Type3 (buildings that are affected by minor
injuries). Similarly, Fig. 8. shows, in particular, the
open-source GIS interface highlighting the Cultural
Heritage site in Borgo Antico (RC).
Fig. 11: GIS visualization: Cultural Heritage and
three types of cracks detected.
The cataloging of cracks enables the
visualization and management of valuable
information about the structural stability and health
of the buildings, allowing for the diagnosis of
structural problems, assessment of building safety,
monitoring of the evolution of cracks, and most
importantly, planning maintenance or necessary
repairs. In this way, it is possible to ensure, through
a low-cost system, a comprehensive overview of
small communities that can be enhanced and
improved. The method also serves as a support for
public managers and municipal agencies in
visualizing and managing the cultural sites in the
area, facilitating the scheduling of any timely
maintenance work.
4 Conclusions
Digital and technological transformation plays a
crucial role in enhancing the preservation of our
cultural heritage while supporting the green
transition. Our innovative monitoring system for
cultural heritage, with low environmental impact,
addresses territorial inequalities and safeguards
cities, towns, and rural areas from the potential
socio-economic consequences associated with the
loss of cultural heritage. If designed to focus on
prevention and maintenance functions, our
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
804
Volume 19, 2023
experimental system can become an excellent tool
for public administrations. These administrations
can plan interventions based on the information
provided within the GIS. The system identifies
vulnerable buildings, those with significant damage
caused by dangerous cracks or other structural
problems. This information is crucial for public
authorities, as it enables them to assess potential
risks to the safety of people and structures. Through
an accurate assessment of the state of buildings,
authorities can prioritize interventions and allocate
resources in a targeted manner to ensure the safety
of people and preserve the building stock. Thus,
based on the findings of our research, it can be
concluded that digitalization plays a crucial role in
the mapping and management of cultural heritage,
enabling the preservation, understanding, and
promotion of these valuable testimonies of the
history and identity of a community or region.
With the advancement of technology and
ongoing research and innovation, it is expected that
new opportunities and solutions will emerge to
preserve and enhance our cultural heritage. Some of
these may include the development of timely alert
systems and the implementation of algorithms and
logic that enable drones to make decisions during
flight. By leveraging data acquired by drones and
developed analytical models, timely alert systems
could be implemented to notify the relevant
authorities in the event of imminent danger or
significant changes in the conditions of hazardous
buildings. This would enable a rapid and targeted
response to mitigate risks.
Other future developments in this research could
lead to increasingly sophisticated and effective
systems for the preservation of cultural heritage,
enabling the relevant authorities to plan targeted
maintenance interventions and helping to safeguard
historical evidence for future generations. These
developments could include the implementation of
advanced algorithms and logic that enable drones to
make decisions while in flight and provide timely
alerts to relevant authorities in case of imminent
danger or significant changes in the condition of
unsafe buildings. The system could be expanded to
a territorial level allowing even more cultural
heritage assets and vulnerable buildings to be
monitored and preserved. Additionally, integration
with other emerging technologies, such as
augmented reality or virtual reality, could provide
an even more immersive experience in the
enjoyment and preservation of cultural heritage.
Looking ahead to future experiments and studies,
this research has developed an automatic and
experimental system aimed at creating a thematic
and virtual map in the GIS capable of visualizing
Cultural Heritage and vulnerable buildings in need
of interventions. The system not only documents the
existing building heritage but also incorporates
maintenance planning activities, such as identifying
buildings with high levels of damage caused by
dangerous cracks and scheduling interventions to
enhance safety. The databases will be enriched with
relevant additional information to support these
objectives. Consequently, we are studying how to
implement the building cadastre to facilitate
maintenance planning and restoration interventions.
Future developments will focus on improving
automation systems to streamline processes further.
References:
[1] Alsadik, B. (2022). Crowdsource drone
imagery–a powerful source for the 3D
documentation of cultural heritage at risk.
International Journal of Architectural
Heritage, 16(7), 977-987.
[2] Febro, J. D. (2020). 3D documentation of
cultural heritage sites using drone and
photogrammetry: a case study of Philippine
UNESCO-recognized Baroque churches.
International Transaction Journal of
Engineering, Management, & Applied
Sciences & Technologies, 11(8), 1-14.
[3] Nicu, I. C., Rubensdotter, L., Stalsberg, K., &
Nau, E. (2021). Coastal erosion of Arctic
cultural heritage in danger: A case study from
Svalbard, Norway. Water, 13(6), 784.
[4] Grammalidis, N., Çetin, E., Dimitropoulos,
K., Tsalakanidou, F., Kose, K., Gunay, O., ...
& Ersoy, C. (2011, August). A multi-sensor
network for the protection of cultural heritage.
In 2011 19th European Signal Processing
Conference (pp. 889-893). IEEE.
[5] Chen, F., Guo, H., Tapete, D., Cigna, F., Piro,
S., Lasaponara, R., & Masini, N. (2022). The
role of imaging radar in cultural heritage:
From technologies to applications.
International Journal of Applied Earth
Observation and Geoinformation, 112,
102907.
https://doi.org/10.1016/j.jag.2022.102907
[6] Remondino, F., & El‐Hakim, S. (2006).
Image‐based 3D modelling: a review. The
photogrammetric record, 21(115), 269-291.
https://doi.org/10.1111/j.1477-
9730.2006.00383.x
[7] Pan, Y., Dong, Y., Wang, D., Chen, A., & Ye,
Z. (2019). Three-dimensional reconstruction
of structural surface model of heritage bridges
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
805
Volume 19, 2023
using UAV-based photogrammetric point
clouds. Remote Sensing, 11(10), 1204.
https://doi.org/10.3390/rs11101204
[8] Rakha, T., & Gorodetsky, A. (2018). Review
of Unmanned Aerial System (UAS)
applications in the built environment:
Towards automated building inspection
procedures using drones. Automation in
Construction, 93, 252-264.
https://doi.org/10.1016/j.autcon.2018.05.002
[9] Pádua, L., Adão, T., Hruška, J., Marques, P.,
Sousa, A., Morais, R., ... & Peres, E. (2018,
April). UAS-based photogrammetry of
cultural heritage sites: A case study
addressing Chapel of Espírito Santo and
photogrammetric software comparison. In
Proceedings of the International Conference
on Geoinformatics and Data Analysis (pp. 72-
76). https://doi.org/10.1145/3220228.3220243
[10] Bae, J., Lee, J., Jang, A., Ju, Y. K., & Park,
M. J. (2022). SMART SKY Eye system for
preliminary structural safety assessment of
buildings using unmanned aerial vehicles.
Sensors, 22(7), 2762.
https://doi.org/10.3390/s22072762
[11] Yousef, M., Iqbal, F., & Hussain, M. (2020,
April). Drone forensics: A detailed analysis of
emerging DJI models. In 2020 11th
International Conference on Information and
Communication Systems (ICICS), pp. 066-
071. IEEE.
[12] Lan, J. K. W., & Lee, F. K. W. (2022,
February). Drone Forensics: A Case Study on
DJI Mavic Air 2. In 2022 24th International
Conference on Advanced Communication
Technology (ICACT) (pp. 291-296). IEEE.
[13] Meier, Patrick. 2015. Digital Humanitarians.
How Big Data Is Changing the Face of
Humanitarian Response. New York:
Routledge. doi:10.1201/b18023.
[14] Ofli, Ferda, Patrick Meier, Muhammad Imran,
Carlos Castillo, Devis Tuia, Nicolas Rey,
Julien Briant, Pauline Millet, Friedrich
Reinhard, Matthew Parkan and Stéphane
Joost. 2016. “Combining Human Computing
and Machine Learning to Make Sense of Big
(Aerial) Data for Disaster Response.” Big
Data 4(1):47-59.
[15] Morent, D., Stathatos, K., Lin, W. C., &
Berthold, M. R. (2011, August).
Comprehensive PMML preprocessing in
KNIME. In Proceedings of the 2011
workshop on Predictive markup language
modeling, pp. 28-31.
[16] Berthold, M. R., Cebron, N., Dill, F., Gabriel,
T. R., Kötter, T., Meinl, T., ... & Wiswedel, B.
(2009). KNIME-the Konstanz information
miner: version 2.0 and beyond. AcM
SIGKDD explorations Newsletter, 11(1), 26-
31.
[17] Barrile, V., Genovese, E., & Meduri, G.M.
(2023). Geomatics Methods and Soft
Computing Techniques for the Management
of Public Transport and Distribution of
Medical Goods. WSEAS Transactions on
Environment and Development 19:418-426.
DOI: 10.37394/232015.2023.19.39.
[18] Barrile, V., Bilotta, G., Genovese, E., Meduri,
G.M., & Fotia, A. (2022). UAVs and GIS: An
Innovative System for Monitoring Structures.
WSEAS Transactions on Systems and Control
17:616-625. DOI:
10.37394/23203.2022.17.68.
[19] Barrile, Vincenzo, Meduri, Giuseppe Maria,
Bilotta, Giuliana. 2014. “Experimentations
and integrated applications laser scanner/GPS
for automated surveys.” WSEAS Transactions
on Signal Processing, 10 (1), pp. 471-480.
[20] Barrile, Vincenzo, Bilotta, Giuliana. 2014.
“Self-localization by laser scanner and GPS in
automated surveys.” Lecture Notes in
Electrical Engineering, 307, pp. 293-311.
DOI: 10.1007/978-3-319-03967-1_23
[21] Angiulli, Giovanni, Barrile, Vincenzo,
Cacciola, Matteo. 2005. “SAR imagery
classification using Multi-class Support
Vector Machines.” Journal of
Electromagnetic Waves and Applications, 19
(14), pp. 1865-1872. DOI:
10.1163/156939305775570558.
[22] V. Barrile, G.M. Meduri, G. Bilotta, Laser
scanner surveying techniques aiming to the
study and the spreading of recent architectural
structures, Proceedings of the 2nd WSEAS
International Conference on Engineering
Mechanics, Structures and Engineering
Geology, EMESEG '09, 2009, pp. 25-28.
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
806
Volume 19, 2023
Contribution of Individual Authors to the
Creation of a Scientific Article (Ghostwriting
Policy)
The authors equally contributed to the present
research, at all stages from the formulation of the
problem to the final findings and solution.
Sources of Funding for Research Presented in a
Scientific Article or Scientific Article Itself
No funding was received for conducting this study.
Conflict of Interest
The authors have no conflict of interest to declare.
Creative Commons Attribution License 4.0
(Attribution 4.0 International, CC BY 4.0)
This article is published under the terms of the
Creative Commons Attribution License 4.0
https://creativecommons.org/licenses/by/4.0/deed.en
_US
WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT
DOI: 10.37394/232015.2023.19.75
Vincenzo Barrile, Emanuela Genovese,
Giuseppe Maria Meduri
E-ISSN: 2224-3496
807
Volume 19, 2023
