=Paper=
{{Paper
|id=Vol-2665/paper11
|storemode=property
|title=Monitoring of the recreation effects on land cover with the use of an unmanned aerial vehicle on the example of the Strelnaya Mountain in Samara Region
|pdfUrl=https://ceur-ws.org/Vol-2665/paper11.pdf
|volume=Vol-2665
|authors=Olga Belova,Anna Denisova,Natalya Vlasova,Lyudmila Kavelenova,Evgeny Korchikov,Victor Fedoseev,Tatyana Chap
}}
==Monitoring of the recreation effects on land cover with the use of an unmanned aerial vehicle on the example of the Strelnaya Mountain in Samara Region ==
https://ceur-ws.org/Vol-2665/paper11.pdf
Monitoring of the Recreation Effects on Land Cover
with the Use of an Unmanned Aerial Vehicle on the
Example of the Strelnaya Mountain in Samara
Region
Olga Belova Anna Denisova Natalya Vlasova
Samara National Research University Samara National Research University Samara National Research University
Samara, Russia Samara, Russia Samara, Russia
bam.post@gmail.com anna3138@yandex.ru nwlasova@mail.ru
Lyudmila Kavelenova Evgeny Korchikov Victor Fedoseev
Samara National Research University Samara National Research University Samara National Research University
Samara, Russia Samara, Russia Samara, Russia
lkavelenova@mail.ru evkor@inbox.ru vicanfed@gmail.com
Tatyana Chap
Zhigulevsky State Nature Reserve
Samara, Russia
chap.t@yandex.ru
Abstract—Strelnaya Mountain is one of the objects most scientific importance, including endemics - 27 (5 narrow
exposed to recreational stress in the Zhigulevsky State Nature Zhiguli endemics), relics - 46, included in the Red Book - 17,
Reserve. Until recently, monitoring studies of the recreational described for the first time from the reserve - 16 species and
pressure carried out by university staff have been limited to 5 varieties [2]. Here, the presence of 229 bird species (about
either inspecting plant communities from the metal decking 80% of the Samara region avifauna) was reliably established,
installed on the trace, or descending to the surface of the slope 150 species are regularly found on the territory and at the
and move along it with the risk of injuring vulnerable borders of the reserve. The fauna of mammals includes 48
vegetation cover. The use of unmanned aerial vehicles (UAVs) species belonging to 6 orders, 15 families, and 34 genera
opens up new prospects for quick and efficient identification of
(about 63% of the number of Samara region mammalian
points affected by recreational exposure, including those
remote from the floor, without contacting the slope surface.
species). The invertebrate fauna of the reserve includes more
The first experience of integrating ground-based and UAV- than 7 thousand species, among which 14 species are
based monitoring was carried out in 2019. We shot the recognized as rare and included in the Red Book of the
Strelnaya Mountain in spring and autumn using UAVs. The Russian Federation, 120 species are in the Red Book of the
obtained images were classified using the support vector Samara Region [3, 4].
machines method with radial basis functions into "trace" and The Strelnaya Mountain is one of the sites of the
"non-trace" classes. As a result, it was possible to
Zhigulevsky state reserve most exposed to recreational
automatically select trampled slope sections with a high degree
pressure. The high conservation value of Strelnaya Mountain
of accuracy. The preliminary results of the work are presented.
is determined by the fact that it presents almost all the
Keywords—remote sensing images, unmanned aerial phytocenotic and floristic diversity of the rocky steppes -
vehicles, trace classification relict plant communities of Zhiguli, which are adjoined by
mountain oak forests and pine forests. Starting from the 50s
I. INTRODUCTION of the XX century, a trail-path network was formed on
The society interest in wildlife objects, including those Strelnaya Mount in consequence to oil production in Zhiguli
confined to specially protected territories of various statuses, during the war years. Since 1966, in the revival reserve, the
demonstrates growth in the wideworld. The protected areas, free visits restriction to the mountains was introduced. An
characterized in natural heritage objects richness, are greatly excursions practice for tourists took its beginning these
important in terms of biological diversity and other valuable years, since that an excursion route has been operating here.
nature components conservation. This circumstance imposes According to many years of Zhigulevsky Reserve employees
restrictions associated with proactive planning of research carried out in the pedestrian area of the excursion
conservation measures on the forms of ecotourism route (1983-2008), natural communities underwent a marked
organization [1]. transformation and degradation in the result of the
recreational impact. The path network expanded, the area of
Zhiguli Mountains, having relatively small values of the knocked-out areas increased, the land cover was locally
area and absolute heigh, sufficiently demonstrate the plant destroyed on the slopes along the path, significant changes in
communities mosaic structure inherent in mountain the composition and structure of communities occurred.
ecosystems themselves, and the vertical zonality is traced
here much weaker. The combination of natural complexes In recent decades the population interest in visiting
within the Zhigulevsky State Reserve boundaries contains a natural heritage unique places has significantly increased.
unique formation of plants, animals, lichens, including That is why not only national parks that carry out ecotourism
endemic and relict species In particular, 178 out of 1022 activities according to their status [5] but also state reserves
vascular plants species of the reserve flora are of special are faced with the task to organize a regulated visit to their
Copyright © 2020 for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)
Image Processing and Earth Remote Sensing
territory taking into account the permissible recreational load the substrate and destroy the plants, disruption of the
and minimizing damage to natural communities. substrate connectivity provokes an increase in soil washout
by rain and melt water. In place of mountain steppe
In 2012, a metal hiking trail flooring with a railing was perennials damaged by trampling, the local invasions of
installed, expanding on the stony slope in the form of an various ruderal (weed) plants was noted.
observation platform, where the information stands located.
At the top of the mountain, the flooring forms a large Using visual fixation of the vegetation cover state on the
viewing platform, which is raised on the supports in front of trial plots during field surveys, we found that new paths
the mountain to a height exceeding the height of the peak appear on the sides of the excursion floor and the existing
(Fig. 1). This construction aims to prevent the ability of ones expand in the result of chronic rules violation by
visitors to walk freely along the vulnerable mountain slopes. visitors on the excursion trail. In parallel with the emergence
Since 2013, on the entrustment of the Zhiguli State Reserve of new hiking trails along the floor, overgrowth and
direction, specialists from the Chair of Ecology, Botany and disappearance of paths that lost attractiveness for visitors
Nature Protection of Samara University have been take place, but the movement along the slope has become
conducting monitoring studies to identify possible spatially more pronounced. The restoration of previously
ecosystems changes after the excursion trail arranging. disturbed plant communities occurs unambiguously where
there are areas inaccessible to visitors - under the floor. The
The named excursion trail flooring was supposed to species involved in the vegetation renewal of disturbed areas
minimize the negative recreation impact on natural show an alternation of their presence and abundance, which
ecosystems with a significant increase in the accepted can be considered a reflection of the cenopopulations
tourists flow, and natural overgrowth during the self-healing development features. The excursion route visitors
of plant groups was expected to restore vegetation cover in increasingly use mountain slopes for selfies and mini-picnics
areas disturbed during its construction. Monitoring studies behind the viewing platform. The pressure on it has become
were aimed to establish whether the vegetation cover higher last year than it was before the flooring device (Fig.
disturbed earlier (with the existence of a pedestrian path or 2).
during the construction) is adequately restored, which
species are restoration participants, and whether the new trail
fully performs its environmental functions.
Fig. 2. Warning plate and violation of the conduct rules by visitors on the
Strelnaya Mountain.
Fig. 1. General view of the parts of excursion trail flooring in Strelnaya II. THE USE OF UAVS IN MONITORING OF RECREATIONAL
Mountain.
PRESSURE EFFECT ON THE PLANT COVER STATE IN
The implementation of ground-based monitoring studies STRELNAYA MOUNTAIN
in Strelnaya Mountain allowed us to identify a basic list of The plant cover monitoring is traditionally based on
vascular plant species that form plant associations, as well as ground surveys. Its advantages are detailed description (high
ruderal species. The vegetation cover disturbed during the spatial resolution, in fact, with the coverage of single plant
construction of the flooring is restored under the flooring due specimens on the trial plots) and the high significance of the
to the growth of individuals located near the flooring and the information received. On the other side, field surveys always
development of new seedlings from soil seed bank. The have a limited area coverage, large in the case of studies
degree of trampling has increased. Jumping from the floor in during routes, and much smaller when using long-term
front of the supports of the observation deck, visitors break stationary sites. The results of field surveys often do not
VI International Conference on "Information Technology and Nanotechnology" (ITNT-2020) 45
Image Processing and Earth Remote Sensing
allow accurate data extrapolation to the entire landscape, The images obtained (Fig. 4) were analyzed for the
especially if the objects of interest are distributed not evenly. possibility of automatic detection of illegal traces.
Another disadvantage of using traditional field studies is that
they require significant time and efforts investments to cover
large areas [6].
On the contrary, methods based on remote sensing (RS)
provide data collection over large spatial limits and are less
time-consuming than traditional ground surveys. Various
optical systems (IKONOS, Quickbird, RapidEye, etc.) can
provide images with very high resolution of fewer than five
meters per pixel [7, 8]. However, many remote sensing
products are very expensive to obtain, while free data
available from the satellites of NASA Landsat series and the
Sentinel missions of the European Space Agency have a low
spatial resolution and, therefore, are limited, for example, to
changes in the earth cover and habitat mapping [9, 10].
The contradiction between the capabilities of remote
sensing materials and the need for detailed natural
ecosystems picture can be eliminated in certain respects due
to the emergence of a new segment of RS - small unmanned
aerial vehicles (UAVs), or drones that were originally
developed and used primarily in the military and defense
industries. Their development, according to experts, led to
the appearance of the so-called dronosphere [11], the space
between the levels of manned air activity and the earth
surface. The boundaries of the dronosphere currently depend
on technical characteristics and rules, but they usually
include direct proximity to the earth. Currently, the rapid Fig. 3. Trial surveys of the excursion route on the Strelnaya Mountain and
development of UAVs makes them more accessible for many the adjacent sections of the slope using UAVs (May 27, October 3, 2019).
research purposes. In particular, data obtained using UAVs
can provide digital images without clouds and with very high
resolution for vegetation monitoring at the landscape level or
characterizing small-scale landscapes [12]. There is
monitoring experience using UAV surveys of protected plant
populations [13].
Monitoring of the recreational effect on Strelnaya
Mountain in ground-based organisation forms for several
years was limited by the inspection of plant communities
from the excursion trail flooring, which made it possible to
assess the plant populations state in close proximity to it, or
by moving on the slope surface with the injury risk of
vulnerable vegetation cover and thin soil layer on the crushed
stone substrate. The use of UAVs opens up new prospects
for the remote, efficient, and quick identification of points
affected by recreation exposure, including those remote from
the floor, without contact with the slope surface. In 2019
(Fig. 3), test spring and autumn surveys of Strelnaya
Mountain were carried out using UAVs.
The shooting was carried out with the help of the
Phantom 4 PRO aircraft. Characteristics of the camera - 3
optical bands RGB, the resolution depends on the height of
shooting: for spring shots the resolution is 0.0107m/pixel, for
autumn shots - from 0.019 to 0.037 m/pixel (the territory was
shot by three spans) [14]. Frames of one span were combined
with DroneDeploy, the software for drones designed for Fig. 4. Mountain Strelnaya UAV (from up to bottom): the photo captured
automatic processing of the received data. Further, the spans on May 27, 2019, photo captured on October 3, 2019.
were combined in a semi-handheld mode in ScanEx Image
Processor v 4.2 application. The acquired images represent: III. TRACE CLASSIFICATION USING SUPPORT VECTOR
in spring - the area of approximately 2700 m2, in autumn - MACHINES WITH RADIAL BASIS FUNCTIONS
the area of 88600 m2. Altitude difference was several tens of To classify traces along the tour route in a conservation
meters from the height of Mountain Strelnaya (351 meters area, we applied a support vector machines method with
above sea level). radial basis functions (SVM RBF) implemented in software
VI International Conference on "Information Technology and Nanotechnology" (ITNT-2020) 46
Image Processing and Earth Remote Sensing
package Matlab R2017b. SVM RBF is frequently used for
the two-class problem, especially in the case of nonlinear
boundary between classes [15].
We provided a classification for two classes «trace» and
«no trace». The outlier probability parameter of the classifier
was set to 0.3. The training set for class «no trace» included
small parts of background area such as grass, trees and the
coverage of the tour route. For class «trace», training set
included images of calcareous soil without grass. Calcareous
rocks are the main component of the soil in the region of
study. It has a white color that makes trace visually
recognizable in RGB spectral range.
As for features, we applied a local average of RGB
spectral channels in 3×3 pixels window. Averaging is used to
suppress noise in the image before classification.
We included fragments of both images obtained in May
and October into the training set because weather and
lighting conditions were too different for both scenes.
Moreover, the spectral response of vegetation was also
Fig. 6. The results of trace classification with the grass background (from
different due to the different phenological characteristics of left to right): autumn image, classification of the autumn image, spring
the plants during the growing stage in May and the image, classification of the spring image.
senescence stage in October. For training and classification,
we used normalized features with zero mean and unit In most cases, classification results match to the reference
variance. Normalization allows decreasing the impact of data selected by experts. The classification result and its
different brightness ranges in different spectral channels. The comparison with the experts’ trace contour are shown in
number of pixels in the training set was 7681: 1180 for class Fig.7. The automatically detected trace is a little wider than
«trace» and 6501 for class «no trace». The example of the experts’ contour. To describe the trace classification
features scattering plot for the training set is shown in Fig.5. accuracy we used the following measure (1):
Sa Se
E ffic ie n c y
Se
where S a - the number of pixels classified as trace, S e - the
number of pixels selected as a trace by the expert. In this
experiment trace classification accuracy was 87.5%.
Fig. 5. Scattering plot of the training set:
class «trace» - red dots, class «no trace» - blue dots.
Before training and classification, we applied decimation
of UAV images in eight times. As a result, the images for
classification had worse spatial resolution than the original
UAV images. The necessity of decimation is explained by
the data redundancy in terms of trace shape estimation and
high computational load. The sampling ratio was selected as
a maximum value for which traces can be visually
recognized on the image.
We tested our classifier on parts of traces with different
width. The test images were obtained from both UAV
images. The classification results of one trace part are shown
in Fig. 6.
In spring image there are more grass parts on the trace
than in the autumn image where the trace looks more
trodden. This confirms the assumption that this part of the Fig. 7. Comparison of the trace classification with the reference trace
slope is used for unauthorized tourist visits. contour (from up to bottom): autumn image with trace contour,
classification result with trace contour.
VI International Conference on "Information Technology and Nanotechnology" (ITNT-2020) 47
Image Processing and Earth Remote Sensing
The final experiment aimed to classify the entire region
of interest to find unknown traces. As a result, the algorithm
found trace parts which were not used in a training set.
SVM-RBF classifier finds traces using simple brightness
features in both autumn and spring images. However, bare
slopes with the same type of soil are also classified as traces.
Thus, further analysis of traces requires trace shape
estimation using morphological filters of the classified
images.
The classification results of autumn and spring images
are shown in Fig. 8 and Fig. 9 correspondingly. Note, that the
tour route coverage is not classified as trace because it is
made of metal and it has the different spectral responses in
RGB channels in comparison with trace.
a)
b)
Fig. 9. Trace classification: a) classification results, b) spring UAV image.
a)
IV. CONCLUSION
The research aimed to find out how effective the use of
UAV remote sensing for recreational stress monitoring on
the example of Strelnaya Mountain. To detect traces we
applied SVM-RBF classification. As a result, the classifier
found the traces selected by the experts during the ground
survey and additionally some parts of bare slopes that are the
examples of false detection. But it can be considered a false
detection only conditionally, as the algorithm was configured
to search for trampled (naked, devoid of vegetation) soil. To
reduce false detection the analysis of trace shape should be
performed using morphological image filtration.
Nevertheless, the trace classification gives successful results,
in particularly, the trace detection shape accuracy was about
87.5%.
We also should say about one more task - determination
of vegetation composition, both existing and arising. This
task has not been solved yet. This is due to insufficient
resolution even of such highly detailed images as UAV
b) images, as well as the small number of data. It is planned to
repeat surveying of Strelnaya Mountain several times a
Fig. 8. Trace classification: a) classification result, b) autumn UAV image. season (spring, autumn) at least several years to have
Red square highlights false trace (it is a slope with bare calcareous soil).
Blue squares indicate the largest of the side traces along the tour route.
observation statistics. Based on the obtained series of images
it will be possible to try to identify large coalitions of
vegetation using vegetation indices, which are widely used in
analysis of remote sensing images [16, 17].
VI International Conference on "Information Technology and Nanotechnology" (ITNT-2020) 48
Image Processing and Earth Remote Sensing
ACKNOWLEDGMENT [9] E. Ostrom and H. Nagendra, “Insights on linking forests, trees, and
people from the air, on the ground, and in the laboratory,” Proc.
The research was supported by RFBR projects № 18-07- Natural. Acad. Sci. USA, vol.103, pp. 19224-19231, 2006.
00748 a, № 17-29-03190 ofi_m. Data preparation through [10] H. Nagendra and D.Rocchini, “High resolution satellite imagery for
UAV shooting was supported by RFBR project № 19-29- tropical biodiversity studies: the devil is in the detail,” Biodivers.
09045. Conserv., vol. 17, pp. 3431-3442, 2008.
[11] M. Germen, “Alternative cityscape visualisation: drone shooting as a
REFERENCES new dimension in urban photography,” Electronic Visualisation and
the Arts (EVA), pp. 150-157, 2016.
[1] P.Wight, “Planning for resource protection and tourism management
in protected areas: A practical perspective,” Tourism: People, Places, [12] G.P. Jones, L.G. Pearlstine and H.F. Percival, “An assessment of
Products, pp.130-141, 2002. small unmanned aerial vehicles for wildlife research,” Wild. Soc.
Bull., vol. 34, pp. 750-758, 2006.
[2] State report on the state of the environment and natural resources of
the Samara region for 2014, vol. 25, 2015. [13] J.Y.L.Tay, A. Erfmeier and J.M. Kalwij, “Reaching new heights: can
drones replace current methods to study plant population dynamics?”
[3] Red Book of the Russian Federation (plants and mushrooms), Plant Ecol., vol. 219, pp. 1139-1150, 2018.
Moscow, Partnership of scientific publications of KMK, 2008.
[14] A.V. Nikonorov, M.V. Petrov, S.A. Bibikov, V.V. Kutikova, A.A.
[4] The Red Book of the Samara Region. Rare species of plants, lichens Morozov and N.L. Kazanskiy, “Image restoration in diffractive
and fungi, Tolyatti: IEVB RAS, 2007. optical systems using deep learning and deconvolution,” Computer
[5] On Specially Protected Natural Areas: Feder. Law of March 14, 1995 Optics, vol. 41, no. 6, pp. 875-887, 2017. DOI: 10.18287/2412-6179-
No. 33-FZ: Ed. from Nov 24 2014. Meeting of the legislation of the 2017-41-6-875-887.
Russian Federation, 1995. [15] S.A. Bibikov, N.L. Kazanskiy and V.A. Fursov, “Vegetation type
[6] C.S. Shuman and R.F. Ambrose, “A comparison of remote sensing recognition in hyperspectral images using a conjugacy indicator,”
and ground-based methods for monitoring wetland restoration Computer Optics, vol. 42, no. 5, pp. 846-854, 2018. DOI:
success,” Restor. Ecol., vol.11, pp. 325-333, 2003. 10.18287/2412-6179-2018-42-5-846-854.
[7] T.W. Gillespie, G.M. Foody, D. Rocchini, A.P. Giorgi, and S. [16] V.V. Efremenko and T.N. Chimitdoriev, “On the use of various
Saatchi, “Measuring and modelling biodiversity from space,” Prog vegetation indices in remote sensing of ecosystems,” Research of the
Phys Geogr., vol. 32, pp. 203-221, 2008. Earth from space, pp. 49-56, 1988.
[8] K. Wang, S.E. Franklin, X. Guo and M. Cattet, “Remote sensing of [17] N.S. Vorobiova, V.V. Sergeyev and A.V. Chernov, “Information
ecology, biodiversity and conservation: a review from the perspective technology of early crop identification by using satellite images,”
of remote sensing specialists,” Sensors, vol.10, pp. 9647-9667, 2010. Computer Optics, vol. 40, no., 6, pp. 929-938, 2016. DOI:
10.18287/2412-6179-2016-40-6-929-938.
VI International Conference on "Information Technology and Nanotechnology" (ITNT-2020) 49