Landscape Aesthetics of Check Dams Based on Scenic Beauty Estimation Method and Artificial Intelligence Technology †
Abstract
:1. Introduction
2. Materials and Methods
2.1. Questionnaire Survey
- Elements: The elements of the landscape were classified as natural and artificial elements. Natural elements such as vegetation, sky, and water enhance the ecological health and beauty of the landscape. Conversely, artificial elements such as concrete structures, soil and water conservation facilities, and other functional structures detract from its aesthetics.
- Characteristics: The respondent’s intuitive visual impression of the facility for colors, shapes, lines, and arrangements was classified by colors and tones. Cool-toned colors (e.g., blue, and green) are associated with natural landscapes, such as the sky, rivers, and vegetation, and offer a calm and cool perception. Warm-toned colors (e.g., red, orange, and yellow) are common in soil and building materials and convey warmth and vitality. These visual differences impact the aesthetic judgment of the respondent.
- Emotional responses: The emotional reactions or feelings of the respondents were assessed after looking at the photos. The emotional reactions were positive (e.g., cleanliness, pleasure, or comfort) or negative (e.g., disorder, boredom, or depression) and were evaluated for visual experience.
2.2. SBE
2.3. Semantic Segmentation
3. Results and Discussion
3.1. Questionnaire Survey
3.2. SBE
3.3. Semantic Segmentation
4. Conclusions and Suggestions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Liew, S. Types and Impacts of Debris Flow Failure in Tropical Hilly Terrain and Development Areas and its Practical Rehabilitation Solutions. In Proceedings of the 2nd Geotechnical Society of Singapore (GeoSS) and Malaysian Geotechnical Society (MGS) Conference 2023, Singapore, 30 November–2 December 2023. [Google Scholar]
- Wu, H.-L.; Feng, Z.-y. Ecological engineering methods for soil and water conservation in Taiwan. Ecol. Eng. 2006, 28, 333–344. [Google Scholar] [CrossRef]
- Pearlmutter, D.; Theochari, D.; Nehls, T.; Pinho, P.; Piro, P.; Korolova, A.; Papaefthimiou, S.; Mateo, M.C.G.; Calheiros, C.; Zluwa, I. Enhancing the circular economy with nature-based solutions in the built urban environment: Green building materials, systems and sites. Blue-Green Syst. 2020, 2, 46–72. [Google Scholar] [CrossRef]
- Zube, E.H.; Sell, J.L.; Taylor, J.G. Landscape perception: Research, application and theory. Landsc. Plan. 1982, 9, 1–33. [Google Scholar] [CrossRef]
- Kaplan, R.; Kaplan, S.; Brown, T. Environmental preference: A comparison of four domains of predictors. Environ. Behav. 1989, 21, 509–530. [Google Scholar] [CrossRef]
- Chen, J.-C.; Jiang, J.-G.; Wang, J.-S. The visual preference for riverbed vegetation: A case study in central Taiwan. Ecol. Saf. 2018, 12, 246–254. [Google Scholar]
- Chen, J.-C.; Huang, C.-L.; Chen, S.-C.; Tfwala, S.S. Visual harmony of engineering structures in a mountain stream. Water 2021, 13, 3324. [Google Scholar] [CrossRef]
- Peng, S.-H.; Han, K.-T. Assessment of aesthetic quality on soil and water conservation engineering using the scenic beauty estimation method. Water 2018, 10, 407. [Google Scholar] [CrossRef]
- Peng, S.-H.; Huang, C.-Y.; Chen, S.-C. Visual Language Translation Analysis and Scenic Beauty Estimation of Mountain Stream Facilities. Water 2022, 14, 3605. [Google Scholar] [CrossRef]
- Anderson, L.; Schroeder, H.W. Application of wildland scenic assessment methods to the urban landscape. Landsc. Plan. 1983, 10, 219–237. [Google Scholar] [CrossRef]
- Arthur, L.M.; Daniel, T.C.; Boster, R.S. Scenic assessment: An overview. Landsc. Plan. 1977, 4, 109–129. [Google Scholar] [CrossRef]
- Schroeder, H.W. Environmental perception rating scales: A case for simple methods of analysis. Environ. Behav. 1984, 16, 573–598. [Google Scholar] [CrossRef]
- Liu, X.; Deng, Z.; Yang, Y. Recent progress in semantic image segmentation. Artif. Intell. Rev. 2019, 52, 1089–1106. [Google Scholar] [CrossRef]
- Thoma, M. A survey of semantic segmentation. arXiv 2016, arXiv:1602.06541. [Google Scholar]
- Guo, J.; He, H.; He, T.; Lausen, L.; Li, M.; Lin, H.; Shi, X.; Wang, C.; Xie, J.; Zha, S. GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing. J. Mach. Learn. Res. 2020, 21, 845–851. [Google Scholar]
- Zhao, J.; Guo, Q. Intelligent assessment for visual quality of streets: Exploration based on machine learning and large-scale street view data. Sustainability 2022, 14, 8166. [Google Scholar] [CrossRef]
- Liu, Z.; Lin, Y.; Cao, Y.; Hu, H.; Wei, Y.; Zhang, Z.; Lin, S.; Guo, B. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada, 10–17 October 2021; pp. 10012–10022. [Google Scholar]
- Hassani, A.; Shi, H. Dilated neighborhood attention transformer. arXiv 2022, arXiv:2209.15001. [Google Scholar]
- Zhou, B.; Zhao, H.; Puig, X.; Xiao, T.; Fidler, S.; Barriuso, A.; Torralba, A. Semantic Understanding of Scenes Through the ADE20K Dataset. Int. J. Comput. Vis. 2019, 127, 302–321. [Google Scholar] [CrossRef]
- Zhou, B.; Zhao, H.; Puig, X.; Fidler, S.; Barriuso, A.; Torralba, A. Scene Parsing through ADE20K Dataset. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 5122–5130. [Google Scholar]
- Brown, T.C. Scaling of Ratings: Concepts and Methods; U.S. Department of Agriculture, Forest Service, Rocky Mountain Forest and Range Experiment Station: Fort Collins, CO, USA, 1990. [Google Scholar]
- Daniel, T.C. Measuring the quality of the natural environment: A psychophysical approach. Am. Psychol. 1990, 45, 633. [Google Scholar] [CrossRef]
No. | Photo | Average Preferences * | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
Elements | Characteristics | Responses | ||||||||
Natural | Artificial | Cool Tone | Neutral Tone | Warm Tone | Orderly Arrangement | Disorderly Arrangement | Positive | Negative | ||
1 | 3.55 | 3.59 | 3.5 | 3.53 | 3.38 | 3.65 | 3.81 | 3.84 | 2.84 | |
2 | 3.33 | 3.39 | 3.21 | 3.47 | 3.55 | 3.45 | 2.76 | 3.79 | 2.53 | |
3 | 2.72 | 2.85 | 2.73 | 2.93 | 3.29 | 3.00 | 2.33 | 3.50 | 2.20 | |
4 | 3.66 | 3.81 | 3.80 | 3.89 | 4.18 | 3.80 | 3.50 | 4.14 | 3.11 | |
5 | 4.53 | 4.51 | 4.55 | 4.36 | 4.46 | 4.53 | 4.40 | 4.61 | 3.67 | |
6 | 3.24 | 3.20 | 3.57 | 3.06 | 2.87 | 3.38 | 2.56 | 3.74 | 2.46 | |
7 | 2.78 | 2.89 | 2.84 | 2.67 | 3.05 | 2.80 | 2.51 | 3.44 | 2.31 | |
8 | 4.53 | 4.51 | 4.67 | 4.44 | 4.24 | 4.60 | 4.67 | 4.69 | 2.94 | |
9 | 4.08 | 3.97 | 3.50 | 3.82 | 3.63 | 4.10 | 4.00 | 4.30 | 2.69 | |
10 | 4.43 | 4.50 | 4.42 | 4.54 | 4.56 | 4.47 | 4.00 | 4.61 | 3.29 |
Photo No. | Original Score | SBE 1 | ||
---|---|---|---|---|
Mean | Median | Standard Deviation | ||
1 | 3.47 | 4 | 0.93 | −9.48 |
2 | 3.19 | 3 | 1.03 | −51.53 |
3 | 2.58 | 2 | 1.08 | −131.62 |
4 | 3.63 | 4 | 1.05 | 13.53 |
5 | 4.45 | 5 | 0.74 | 144.94 |
6 | 3.04 | 3 | 1.09 | −74.49 |
7 | 2.61 | 3 | 1.02 | −135.66 |
8 | 4.24 | 5 | 1.07 | 73.44 |
9 | 3.86 | 4 | 1.05 | 36.46 |
10 | 4.43 | 5 | 0.77 | 134.41 |
Photo No. | Vegetation | Structure | Sky | Land | Water | SBE | Rank of SBE | |
---|---|---|---|---|---|---|---|---|
1 | Manual classification | 44.04% | 32.27% | 10.45% | 13.25% | 0.00% | −9.48 | 6 |
Swin-L | 35.34% | 37.80% | 11.92% | 14.94% | 0.00% | |||
DiNAT-L | 35.68% | 38.99% | 11.25% | 14.08% | 0.00% | |||
2 | Manual classification | 81.41% | 12.47% | 0.00% | 1.52% | 4.59% | −51.53 | 7 |
Swin-L | 58.67% | 13.42% | 0.00% | 22.82% | 5.10% | |||
DiNAT-L | 56.87% | 12.61% | 0.00% | 25.49% | 5.04% | |||
3 | Manual classification | 83.21% | 5.75% | 0.00% | 11.04% | 0.00% | −131.62 | 9 |
Swin-L | 61.92% | 7.74% | 0.00% | 28.68% | 1.67% | |||
DiNAT-L | 72.78% | 7.62% | 0.00% | 14.77% | 4.83% | |||
4 | Manual classification | 26.59% | 2.97% | 0.00% | 26.67% | 43.77% | 13.53 | 5 |
Swin-L | 16.21% | 8.23% | 0.00% | 28.86% | 46.69% | |||
DiNAT-L | 15.73% | 2.52% | 0.00% | 35.43% | 46.31% | |||
5 | Manual classification | 53.50% | 17.33% | 0.00% | 5.73% | 23.44% | 144.94 | 1 |
Swin-L | 41.40% | 19.82% | 0.00% | 5.52% | 33.26% | |||
DiNAT-L | 41.60% | 17.85% | 0.00% | 6.97% | 33.57% | |||
6 | Manual classification | 41.10% | 11.69% | 0.10% | 35.77% | 11.34% | −74.49 | 8 |
Swin-L | 39.15% | 0.29% | 0.09% | 48.67% | 11.79% | |||
DiNAT-L | 38.26% | 12.91% | 0.10% | 46.75% | 1.98% | |||
7 | Manual classification | 26.44% | 4.21% | 26.67% | 42.68% | 0.00% | −135.66 | 10 |
Swin-L | 21.39% | 6.44% | 27.23% | 44.93% | 0.00% | |||
DiNAT-L | 21.38% | 7.01% | 27.45% | 44.17% | 0.00% | |||
8 | Manual classification | 34.36% | 21.36% | 8.77% | 14.84% | 20.68% | 73.44 | 3 |
Swin-L | 33.42% | 18.57% | 8.23% | 11.19% | 28.58% | |||
DiNAT-L | 34.26% | 19.11% | 8.09% | 20.59% | 17.96% | |||
9 | Manual classification | 48.19% | 26.43% | 0.00% | 18.44% | 6.94% | 36.46 | 4 |
Swin-L | 37.22% | 33.19% | 0.00% | 16.95% | 12.64% | |||
DiNAT-L | 37.00% | 32.52% | 0.00% | 17.35% | 13.13% | |||
10 | Manual classification | 50.10% | 11.22% | 4.67% | 0.22% | 33.80% | 134.41 | 2 |
Swin-L | 38.59% | 12.84% | 5.15% | 4.19% | 39.23% | |||
DiNAT-L | 37.35% | 18.17% | 5.19% | 4.91% | 34.38% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Weng, H.-M.; Peng, S.-H.; Wu, C.-Y.; Liang, M.-C. Landscape Aesthetics of Check Dams Based on Scenic Beauty Estimation Method and Artificial Intelligence Technology. Eng. Proc. 2025, 91, 3. https://doi.org/10.3390/engproc2025091003
Weng H-M, Peng S-H, Wu C-Y, Liang M-C. Landscape Aesthetics of Check Dams Based on Scenic Beauty Estimation Method and Artificial Intelligence Technology. Engineering Proceedings. 2025; 91(1):3. https://doi.org/10.3390/engproc2025091003
Chicago/Turabian StyleWeng, Hong-Ming, Szu-Hsien Peng, Chun-Yi Wu, and Min-Chih Liang. 2025. "Landscape Aesthetics of Check Dams Based on Scenic Beauty Estimation Method and Artificial Intelligence Technology" Engineering Proceedings 91, no. 1: 3. https://doi.org/10.3390/engproc2025091003
APA StyleWeng, H.-M., Peng, S.-H., Wu, C.-Y., & Liang, M.-C. (2025). Landscape Aesthetics of Check Dams Based on Scenic Beauty Estimation Method and Artificial Intelligence Technology. Engineering Proceedings, 91(1), 3. https://doi.org/10.3390/engproc2025091003