=Paper=
{{Paper
|id=Vol-3838/short6
|storemode=property
|title=Measurement of displacement of petroglyphs of Bangudae Terrace in Daegok-ri, Ulju, using edge and region extraction (short paper)
|pdfUrl=https://ceur-ws.org/Vol-3838/short6.pdf
|volume=Vol-3838
|authors=Sang-Yun Lee
|dblpUrl=https://dblp.org/rec/conf/viperc/Lee24
}}
==Measurement of displacement of petroglyphs of Bangudae Terrace in Daegok-ri, Ulju, using edge and region extraction (short paper)==
https://ceur-ws.org/Vol-3838/short6.pdf
Measurement of displacement of petroglyphs of Bangudae
Terrace in Daegok-ri, Ulju, using edge and region extraction
Sang-Yun Lee1,∗
1 Police Science & Public Safety ICT Research Center, Digital Convergence Research Institute,
Electronics and Telecommunications Research Institute, South Korea
Abstract
Petroglyphs of Bangudae Terrace in Daegok-ri, Ulju are the world's oldest whale hunting petroglyphs and are
located on a cliff in Daegokcheon. It was designated as South Korea's National Treasure No. 285, and was
listed as the 'Daegokcheon Petroglyph Group' on the 'Priority List', a list of UNESCO World Heritage
candidates.
When stone cultural assets such as the Petroglyphs of Bangudae Terrace are damaged, it is very difficult to
restore them to their original state. Therefore, it is very important to predict risk factors in advance and
regularly manage them for preservation.
In this paper, we will use two Deep Learning models such as PiDiNet, and DexiNed to extract edges and
legions. And then we will measure the contours and areas of the extracted areas. In terms of area, both ‘Cavity’
and ‘Joint separation’ showed the highest values in the first quarter. Additionally, looking at the change from
the second quarter to the fall, the numbers appear to be stable in the case of ‘Cavity’.
In the future, we will continue to conduct experiments to improve the accuracy of edge and area extraction
and to present a reference point for whether displacement has occurred through additional experiments so that
we can automatically determine that displacement has occurred-
Keywords
Petroglyphs of Bangudae Terrace, Displacement, PiDiNet, DexiNed, Deep Learning.
1. 1 Introduction
Petroglyphs of Bangudae Terrace in Daegok-ri, Ulju are the world's oldest whale hunting
petroglyphs and are located on a cliff in Daegokcheon. It was designated as South Korea's
National Treasure No. 285, and was listed as the 'Daegokcheon Petroglyph Group' on the 'Priority
List', a list of UNESCO World Heritage candidates selected by the Cultural Heritage
Administration (CHA) of the South Korea [1]. However, due to the Sayeon Dam located
downstream of Daegokcheon, the water volume decreases during the dry season when rainfall
is low, but when rainfall increases, the water level rises rapidly, causing the petroglyphs to be
submerged, gradually accelerating damage due to encroachment or erosion [2].
When stone cultural assets such as the Petroglyphs of Bangudae Terrace are damaged, it is very
difficult to restore them to their original state [3, 4]. Therefore, it is very important to predict
risk factors in advance and regularly manage them for preservation [5]. However, such regular
monitoring and management has many limitations in terms of resources, information
processing, and expertise, therefore various studies are being conducted to automatically
monitor and manage cultural assets using Deep Learning technology [6, 7].
VIPERC2024: 3rd International Conference on Visual Pattern Extraction and Recognition for Cultural Heritage
Understanding, 1 September 2024
∗ Corresponding author.
sylllee@etri.re.kr (Sang-Yun Lee)
0000-0003-2568-4616 (Sang-Yun Lee)
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
We will use two Deep Learning models, including, PiDiNet [6], and DexiNed [7], as Deep Learning
architectures to extract edges and legions [8]. And then we will extract ‘Cavity’ and ‘Joint
separation’ using them, and measure the contours and areas of the extracted areas over time to
monitor trends in displacement.
This paper is structured as follows. Chapter 2 will describe the data collection process for
Petroglyphs of Bangudae Terrace, datasets for experiments, and labeling methods. Chapter 3 will
describe the Deep Learning Neural Network used for edge extraction. Chapter 4 will present the
preprocessing process and results of displacement measurement and analyzes the experimental
results. And we will conclude in Chapter 5.
2. Dataset and preprocessing
The monitoring image is data taken from a telephoto camera located 200m across from
Petroglyphs of Bangudae Terrace, and is captured once a day at the same time. Since it is
impossible to capture the entire area at once, the horizontal area is divided into 12 areas and
then filmed by rotating the camera angle. The original data is saved as a JPEG image, the standard
is 4912 x 7360, and the data capacity is approximately 20 to 35 MB per image.
2.1. Labeling Method
Labeling data for learning has the same file name as the original data, but is saved as PNG with a
different extension. Additionally, the dimensions of 4912 x 7360 horizontal and vertical are the
same as those of the original data. This is tailored to an open source-based Deep Learning
algorithm for learning. The learning data is divided into ‘Joint separation’ areas, ‘Cavity’ areas,
and areas containing both ‘Joint separation’ and ‘Cavity’ according to the type of displacement
(See Figure 1). And depending on the labeling method, it is divided into 'Linestrip', 'Polygon', and
'Linestrip & Polygon' (See Figure 2).
Figure 1: Displacement type Figure 2: Labeling method
2.1.1. ‘Cavity’ labeling
The cavity is located at the bottom of the Petroglyphs of Bangudae Terrace, and is an empty space
naturally created by water flow and erosion over a long period of time. We used a labeling tool
called Labelme to label the ‘Cavity’ area and labeled it with ‘Linestrip’ or ‘Polygon’ type (See
Figure 3). In the case of ‘Cavity’, unlike ‘Joint separation’, they have a simple shape, so the labeling
method of ‘Linestrip & Polygon’ was not applied.
(a) Original data (b) Labeling by ‘Polygon’ (c) Labeling by ‘Linestrip’
Figure 3: Labeling of ‘Cavity’ area
2.1.2. ‘Joint separation’ labeling
The main rock surface of the Petroglyphs of Bangudae Terrace has various types of ‘Joint
separation’ developed, including vertical separation, diagonal separation, and complex
separation. We used a labeling tool called Labelme to label the ‘Joint separation’ area and labeled
it with ‘Linestrip’, ‘Polygon’, and ‘Linestrip & Polygon’ (See Figure 4).
(a) Original data (b) Labeling by (c) Labeling by (d) Labeling by
‘Polygon’ ‘Linestrip’ ‘Polygon’&Linestrip’
Figure 4: Labeling of ‘Joint separation’
2.1.3. ‘Cavity & ‘Joint separation’ labeling
We labeled the ‘Cavity’ and ‘Joint separation’ areas in the same manner as described in the
previous section to experiment with images containing both of them (See Figure 5).
(a) Original data (b) Labeling by (c) Labeling by (d) Labeling by
‘Polygon’ ‘Linestrip’ ‘Polygon’&Linestrip’
Figure 5: Labeling of ‘Cavity’ & ‘Joint separation’
2.2. Data normalization
To normalize the learning data, we converted the labeling data to a binary image with pixel
values from 0 to 255 (See Figure 6-(a)). And the sizes of both the original image and the labeled
image were normalized to 1,280 x 720. In this process, a comparative experiment was conducted
using two different methods: cropping and reducing the image size to 1/10 and resizing it to 491
x 736 (See Figure 6-(b)).
(a) ‘Crop’ (b) ‘Resize’
Figure 6: Normalization of training data
3. Deep Learning Networks for Edge Detection
In this paper, we utilize an Open Source-based pre-trained Deep Learning model based on CNN.
After labeling the original image of the Petroglyphs of Bangudae Terrace, it goes through
preprocessing processes such as black-and-white processing and normalization, and uses this as
learning data to extract edges.
Based on this result, we can determine the detection area for ‘Cavity’ and ‘Joint separation’, and
detect or predict whether displacement will occur by analyzing the change patterns of
displacement values in time series. Figure 7 shows the overall research and development flow
chart for the method proposed in this paper.
Figure 7: Research and development flow chart
We used two Artificial Intelligence Neural Networks, including PiDiNet, and DexiNed, to detect
the displacement of the Petroglyphs of Bangudae Terrace in Daegok-ri, Ulju, South Korea and
measure the amount of displacement in this research. PiDiNet is specialized in detecting details
in images [6] while DexiNed is optimized for boundary edge detection [7].
3.1. PiDiNet
The PiDiNet model uses a deep and wide separable Neural Network structure for fast inference
and easy learning [9] (see Figure 8). PiDiNet do not use any normalization layers for simplicity
since the resolutions of the training images are not uniform and replace the vanilla convolution
in the 3 × 3 depth-wise convolutional layer in the residual blocks with Pixel Difference
Convolution (PDC) [6].
It learns rich edge representations through side structures and effectively generates edge-maps
[10]. It generates a lot of multi-scale edge information through many Compact Dilation
Convolution based Module (CDCM) and removes background noise using Compact Spatial
Attention Module (CSAM). Then, it combines single edge maps with a sigmoid function to
generate the final edge map.
Figure 8: Architecture of PiDiNet
3.2. DexiNed
The DexiNed model consists of two subnetworks: Dexi and USNet (see Figure 9). The Dexi
network consists of six blocks that act as encoders, and each block consists of sub-blocks with
multiple neural network layers and skip-connections [11, 12].
It generates edge maps combined with the learned filter for each block, and finally creates one
edge map by combining the features generated from each edge map. USNet passes the feature
maps from the Dexi network through two blocks. In the first block, a kernel of size 1 x 1 is used
to process it through the ReLU activation function, and then a kernel of size
s × s, where s is the input feature map size, is used to create a feature map of the same size as the
predicted answer value [7].
Figure 9: Architecture of DexiNed
4. Experiment results and analysis
4.1. Preprocessing and evaluation measurement
When the ‘Joint separation’ or ‘Cavity’ areas of the edge-extracted image were not clear, we went
through the process of increasing the contrast to make the areas clearer. Figure 10-(a) shows the
result of adjusting the brightness intensity to increase the contrast of the image contrast, making
the ‘Joint separation’ area clearer. Figure 10-(b) shows the results of finding the contour line for
each joint area detected after preprocessing and calculating the area and length for the
corresponding contour area.
(a) Contrast enhancement (b) Displacement measurement
Figure 10: Contrast enhancement and displacement measurement results
The red dots in Figure 11-(a) are the horizontal and vertical endpoints of each ‘Joint separation’
area detected in the resulting image. Using these points, we can find the maximum distance
between the horizontal end points and the maximum distance between the vertical end points
of the ‘Joint separation’
Performance evaluation of the Deep Learning architecture used in the experiment can be done
through accuracy and structural similarity index.
Accuracy is obtained as a ratio of how well the ‘Joint separation’ area of the ground truth image
binarized into black and white matches the ‘Joint separation’ area extracted from the image to
be evaluated (see Figure 11-(b)). The structural similarity index (SSI) is obtained using the
structural similarity, such as luminance, contrast, and pixel value, of the two images being
compared.
(a) Maximum horizontal and vertical (b) Accuracy and Similarity
distance measurement
Figure 11: Maximum distance and measurement accuracy
4.2. Measurement of displacement of ‘Joint separation’
When looking at the displacement of ‘Joint separation’ by season using the PiDiNet model, which
shows the best general performance, the contour area showed values of 1,312, 1,606, 1,660, and
1,014 in spring, summer, fall, and winter, respectively. and the contour lengths showed values of
365, 381, 383, and 342, respectively (see Table 1).
If we only look at the amount of change in the area value, we can assume that there has been a
somewhat significant change, but if we look at the change in the length value, we may conclude
that there is no significant change. Therefore, it is necessary to comprehensively review the
amount of change in area and length to determine whether there has been a significant change.
Table 1
Seasonal ‘Joint separation’ displacement measurement results
Result
Date April 1, 2022 June 26, 2022 Sep. 22, 2022 Dec. 15, 2022
Season spring summer fall winter
Area 1,312 1,606 1,660 1,014
Contour 365 381 383 342
4.3. Measurement of displacement of ‘Cavity’ and analysis
In the case of the ‘Cavity’, the contour area showed values of 13,827, 13,263, 14,392, and 8,468
in spring, summer, fall, and winter, respectively, and the contour length showed values of 2,361,
2,273, 2,886, and 2,255, respectively (see Table 2). This also showed similar aspects to the ‘Joint
separation’ analysis results.
Table 2
Seasonal ‘Cavity’ displacement measurement results
Result
Date April 1, 2022 June 26, 2022 Sep. 22, 2022 Dec. 15, 2022
Season spring summer fall winter
Area 13,827 13,263 14,392 8,468
Contour 2,361 2,273 2,886 2,255
4.4. Integrated analysis of joint and cavity displacement measurements
Figure 12: Area changes in ‘Cavity’ and ‘Joint separation’ according to temperature
In terms of area, both ‘Cavity’ and ‘Joint separation’ showed the highest values in the first quarter
(See Figure 12). Additionally, looking at the change from the second quarter to the fall, the
numbers appear to be stable in the case of ‘Cavity’. In the case of ‘Joint separation’, there is some
change, but the value appears to be stably maintained between 1,312 and 1,660.
Changes in the contour path showed slightly different characteristics in cavities and joints, as
shown in Figure 13. In the case of cavities, the contour length had the greatest value in fall, and
in the case of joints, the difference was large between the first quarter and spring, and then
showed stable values from the second quarter to fall. Comparatively, the deviation between area
and contour length was larger in the cavity, and the contour length of all joint joints was more
stable than the area.
Figure 13: Contour changes in ‘Cavity’ and ‘Joint separation’ according to temperature
According to the comprehensive survey research report on the Daegokcheon petroglyph group
[2], the ‘Cavity’ and ‘Joint separation’ of the Petroglyphs of Bangudae Terrace undergo rapid
displacement during the spring thaw, but after April, the measured values showed a stable value
and showed a slight divergence in the negative direction. It is assumed that the gap narrowed
due to thermal expansion of the rock, and this trend is consistent with the results of this research.
In addition, it was reported that the correlation between temperature and displacement is
inversely proportional, which is also found to show a similar pattern to the results of this
research. However, in winter, area and contour length were directly proportional to
temperature. We analyzed that in the case of year of 2022, unlike 2019 when the comprehensive
research report was written, there were many abnormal climates, and the light and dark in the
photo may have had an effect.
5. Conclusion
Petroglyphs of Bangudae Terrace in Daegok-ri, Ulju are designated as National Treasure No. 285
of the Republic of Korea, and are listed as the 'Daegokcheon Petroglyph Group' in the 'Priority
List', a UNESCO World Heritage candidate list selected by the Cultural Heritage Administration
(CHA). However, they are submerged in water due to the Sayeon Dam located downstream of
Daegokcheon Stream, and damage from erosion is gradually accelerating.
In this paper, we presented a method to measure and automatically monitor the amount of
displacement of Petroglyphs of Bangudae Terrace using Deep Learning technology. Using
PiDiNet and DexiNed Deep Learning models, we were able to automatically extract edges and
areas and detect whether displacement occurred by measuring changes in the outline length and
area of the extracted area.
In terms of area, both ‘Cavity’ and ‘Joint separation’ showed the highest values in the first quarter.
Additionally, looking at the change from the second quarter to the fall, the numbers appear to be
stable in the case of ‘Cavity’. In the case of ‘Joint separation’, there is some change, but the value
appears to be stably maintained. In terms of contour length, the contour length of ‘Cavity’ had
the greatest value in fall, and in the case of ‘Joint separation’, the difference was large between
the first quarter and spring, and then showed stable values from the second quarter to fall.
In the future, we will continue to conduct experiments to improve the accuracy of edge and area
extraction and to present a reference point for whether displacement has occurred through
additional experiments so that we can automatically determine that displacement has occurred.
Acknowledgements
This paper was funded by the government (Korea Heritage Service) in 2024 with the support of
the National Research Institute of Cultural Heritage (No.2021A01D06-001, Development of
damage detection and alarm technology based on intelligent image analysis for safety diagnosis
of Immovable cultural heritage)
References
[1] Wikipedia Homepage, https://ko.wikipedia.org (2024).
[2] National Research Institute of Cultural Heritage, Daegokcheon Petroglyph Group
Comprehensive Survey Research Report, 11-1550011-000930-01 (2019).
[3] Kumar, Pakhee and Ofli, Ferda and Imran, Muhammad and Castillo, Carlos. Detection of
disaster-affected cultural heritage sites from social media images using deep learning
techniques, Journal on Computing and Cultural Heritage (JOCCH), 13(3), pp.1-31(2020).
[4] Hatır, M. Ergün, İsmail İnce, and Mustafa Korkanç. Intelligent detection of deterioration in
cultural stone heritage, Journal of Building Engineering , 44 ,pp.102690(2021).
[5] Hatır, Ergün, Korkanç, Mustafa, Schachner, Andreas, Ince, Ismail. The deep learning method
applied to the detection and mapping of stone deterioration in open-air sanctuaries of the
Hittite period in Anatolia, Journal of Cultural Heritage, 51, pp. 37-49(2021).
[6] Zhuo Su, Wenzhe Liu, Zitong Yu, Dewen Hu, Qing Liao, Qi Tian, Matti Pietikäinen, Li Liu,
Pixel Difference Networks for Efficient Edge Detection, In Proceedings of the International
Conference on Computer Vision (ICCV) on Computer Vison and Pattern Recognition pp.
5117–5127 (2021).
[7] Xavier Soria, Angel Sappa, Patricio Humanante, Arash Akbarinia, Dense extreme inception
network for edge detection, Pattern Recognition (139):109461 (2023).
[8] K. Simonyan, A. Zisserman. Very deep convolutional networks for largescale image
recognition, International Conference on Learning Representations(ICLR) (2015).
[9] Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias
Weyand, Marco Andreetto, and Hartwig Adam. Mobilenets: Efficient convolutional neural
networks for mobile vision applications. arXiv preprint arXiv:1704.04861(2017).
[10] Saining Xie and Zhuowen Tu. Holistically-nested edge detection. International Journal of
Computer Vision, 125(1- 3), pp. 3–18 (2017).
[11] K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition, in: Conference
on Computer Vision and Pattern Recognition (2016).
[12] Y. Zhang, Y. Tian, Y. Kong, B. Zhong, Y. Fu. Residual dense network for image super-
resolution, in: Conference on Computer Vision and Pattern Recognition (2018).