Author(s)

Jie Gong ¹, Xuefeng Zhao ¹, Yifei Zhao ¹, Songhong Yao ¹

Affiliation(s)

¹ Shenyang University, Dadong District, Shenyang, China

Corresponding Author

Xuefeng Zhao

ABSTRACT

This study integrates Scenic Beauty Estimation (SBE) and DeepLabV3+ semantic segmentation to evaluate campus greenway visual quality at Shenyang University. Sixty node images and 130 valid student evaluations were used to link perceived beauty with measurable visual elements. Regression results show that greenway morphology and spatial extension improve SBE values, whereas excessive green visibility, vehicle presence, and spatial closure reduce perceived quality. Teaching-area greenways achieved the highest mean SBE value, while office-area greenways scored lowest. The results support targeted design strategies for strengthening visual corridors, balancing greenery and permeability, and reducing traffic-related visual interference.

KEYWORDS

Campus greenway; Landscape visual quality; Scenic Beauty Estimation (SBE); Semantic segmentation; Functional zoning

CITE THIS PAPER

Jie Gong, Xuefeng Zhao, Yifei Zhao, Songhong Yao. Quantifying Visual Quality in Campus Greenways Using Scenic Beauty Estimation and Deep Learning-Based Semantic Segmentation. Journal of Civil Engineering and Urban Planning (2026). Vol. 8, No.2, 92-99. DOI: http://dx.doi.org/10.23977/jceup.2026.080210.

REFERENCES

[1] LITTLE, C. E. 1995. Greenways for America, JHU Press.
[2] JONGMAN, R. H., KULVIK, M. & KRISTIANSEN, I. 2004. European ecological networks and greenways. Landscape and Urban Planning, 68, 305-319.
[3] ANDERSON, C. E., ZIMMERMAN, A., LEWIS, S., MARMION, J. & GUSTAT, J. 2019. Cyclist and pedestrian behavior on an urban greenway. International Journal of Environmental Research and Public Health, 16, 201.
[4] DOBER, R. P. 2000. Campus Landscape: Functions, Forms, Features, John Wiley & Sons.
[5] GABR, M., ELKADI, H. & TRILLO, C. 2019. Recognizing greenway network for quantifying student experience on campus-based universities. Proceedings of the Fabos Conference on Landscape and Greenway Planning.
[6] ZUBE, E. H., PITT, D. G. & ANDERSON, T. W. 1974. Perception and measurement of scenic resources. Landscape Research, 1, 10-11.
[7] BROWN, T. C. & DANIEL, T. C. 1986. Predicting scenic beauty of timber stands. Forest Science, 32, 471-487.
[8] XU, X., DONG, R., LI, Z., JIANG, Y. & GENOVESE, P. V. 2024. Visual experience evaluation by integrating SBE-SD and eye movement analysis. Heritage Science, 12, 281.
[9] ZHANG, X., XIONG, X., CHI, M., YANG, S. & LIU, L. 2024. Visual quality assessment and landscape elements of rural greenways. Ecological Indicators, 160, 111844.
[10] LEE, J., LEE, H.-S., JEONG, D., SHAFER, C. S. & CHON, J. 2019. User perception and preference of greenway trail characteristics. Sustainability, 11, 4438.
[11] LI, X., WANG, X., JIANG, X., HAN, J., WANG, Z., WU, D., LIN, Q., LI, L., ZHANG, S. & DONG, Y. 2022. Prediction of riverside greenway aesthetic quality using environmental modeling. Journal of Cleaner Production, 367, 133066.
[12] HAO, X. & LONG, Y. 2017. Street greenery: A new indicator for evaluating walkability. Shanghai Urban Planning Review, 1, 32-36.
[13] YU, Y., ZHANG, X. & ZENG, W. 2019. Human-scale quality on streets based on street-view images and urban analytical tools. Urban Planning International, 34, 18-27.
[14] HU, X., ZOU, X. & FAN, H. 2023. Landscape influencing factors of waterfront greenways based on scenic beauty estimation. Frontiers in Earth Science, 11, 1211775.
[15] QI, Z., DUAN, J., SU, H., FAN, Z. & LAN, W. 2023. Using crowdsourcing images to assess visual quality of urban landscapes. Ecological Indicators, 154, 110793.
[16] GARCIA-GARCIA, A., ORTS-ESCOLANO, S., OPREA, S., VILLENA-MARTINEZ, V. & GARCIA-RODRIGUEZ, J. 2017. A review on deep learning techniques applied to semantic segmentation. arXiv:1704.06857.
[17] LONG, J., SHELHAMER, E. & DARRELL, T. 2015. Fully convolutional networks for semantic segmentation. Proceedings of CVPR, 3431-3440.
[18] RONNEBERGER, O., FISCHER, P. & BROX, T. 2015. U-net: Convolutional networks for biomedical image segmentation. MICCAI, 234-241.
[19] JIANG, J. & DAI, K. 2021. Landscape image segmentation and beauty evaluation based on convolution neural network. IEEE TOCS, 1020-1023.
[20] DUPONT, L., ANTROP, M. & VAN EETVELDE, V. 2015. Landscape expertise and visual perception of landscape photographs. Landscape and Urban Planning, 141, 68-77.
[21] BUHYOFF, G. J., WELLMAN, J. D., HARVEY, H. & FRASER, R. 1978. Landscape architects' interpretations of people's landscape preferences. Journal of Environmental Management, 6(3), 255-262.
[22] EDENSOR, T. 2010. Walking in rhythms: Place, regulation, style and the flow of experience. Visual Studies, 25, 69-79.
[23] QIN, X., GAO, L. & SHEN, Y. 2016. Road landscape enclosure scale and sequence characteristics. Journal of Testing and Evaluation, 44, 734-743.
[24] LIU, M. & NIJHUIS, S. 2020. Mapping landscape spaces. Environmental Impact Assessment Review, 82, 106376.
[25] NIE, W., JIA, J., WANG, M., SUN, J. & LI, G. 2022. Panoramic green view index and pleasure level based on EEG experiment. Landscape Architecture Frontiers, 10, 36-51.
[26] GEHL, J. 2011. Life Between Buildings: Using Public Space. Washington, DC: Island Press.
[27] ULRICH, R. S. 1979. Visual landscapes and psychological well-being. Landscape Research, 4, 17-23.
[28] BAI, Y., BAI, Y., WANG, R., YANG, T., SONG, X. & BAI, B. 2023. Built environment and cycling behaviour around urban greenways. Land, 12, 619.

Sponsors, Associates, and Links

---

• Journal of Sustainable Development and Green Buildings
  
  
• Landscape and Urban Horticulture
  
  
• Bridge and Structural Engineering
  
  
• Soil Mechanics and Geotechnical Engineering
  
  
• Journal of Municipal Engineering
  
  
• Heating, Ventilation and Air Conditioning
  
  
• Indoor Air Quality and Climate
  
  
• Computer Aided Architecture Design