Decoding spatial genes of living heritage in traditional villages: TV-RSI-413 and MCPNet
Source abstract
Abstract
Traditional villages encode settlement-scale “spatial genes”. We present TV-RSI-413, a dataset of 2478 on-site images from 413 Jiangxi villages (ground DSLR, low-altitude oblique UAV, and open street-view), each pixel-labelled into 22 classes. A three-stage audit yields high inter-rater agreement (Cohen’s κ = 0.92). Building on this resource, we propose MCPNet, a multiscale context-perceptual segmentation network designed to preserve cadastral edges and network continuity. Under the official in-domain protocol (20 spatial-gene classes), MCPNet achieves 34.7% mean accuracy and 24.3% mean IoU, outperforming DeepLabV3+ by 5.1 points in mean accuracy and 2.6 points in mean IoU, with higher boundary and connectivity scores. In a practice-facing setting that includes background and occluders, overall accuracy reaches 85.3% and mean IoU 70.7%. We release fixed splits, evaluation scripts, and code for FAIR reuse. The 22 classes further aggregate into functional archetypes linked to heritage values, enabling auditable priorities for conservation, ecological zoning, micro-restoration, parcelisation, and risk-aware governance.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Archaeological Research and Protection · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (55)
Show source-provided references
1. UNESCO. Recommendation on the historic urban landscape (hul) (2011). https://whc.unesco.org/document/160163. Accessed 28 Sep 2025.
2. Nations, U. Sustainable development goal 11.4: Strengthen efforts to protect and safeguard the world’s cultural and natural heritage (2015). https://sdgs.un.org/goals/goal11. Accessed 28 Sep 2025.
3. for Disaster Risk Reduction (UNDRR), U. N. O. Sendai framework for disaster risk reduction 2015–2030 https://www.undrr.org/publication/sendai-framework-disaster-risk-reduction-2015-2030 (2015). Accessed 2025-09-28.
4. Olah, B. et al. From historical maps to lidar data: How not to lose field boundaries and hedgerows—lessons from Slovakia. Land 14, 1370 (2025).10.3390/land14071370 ↗
5. Dong, Y. et al. Landscape gene characteristics of traditional villages along the Jinzhong section of the Wanli tea road from the perspective of the village–temple system. Land 13, 1602 (2024).10.3390/land13101602 ↗
6. Long, H., Qu, Y. & Liu, Y. Spatial restructuring in rural China: policy intervention and development. J. Rural Stud. 47, 387–396 (2016).10.1016/j.jrurstud.2016.07.028 ↗
7. Zhu, X. et al. Cultural routes as heritage corridors: Spatial identification and classification along the ancient tea–horse road. Buildings 13, 2451 (2023).10.3390/buildings13102451 ↗
8. Zhang, J. et al. Traditional village spatial gene identification and schema language: a case of shaoxing tsukashi village. Geogr. Res. 44, 988–1008 (2025).
9. Cao, K., Liu, Y., Cao, Y., Wang, J. & Tian, Y. Construction and characteristic analysis of landscape gene maps of traditional villages along ancient Qin–Shu roads, western china. Herit. Sci. 12, 37 (2024).10.1186/s40494-024-01155-y ↗
10. Liu, Y., Li, Y., Chen, Y., Li, Y. & Shi, L. Process and pattern of hollowing of traditional villages in China from 2000 to 2020. Land 10, 1156 (2021).10.3390/land10111156 ↗
11. Zacharová, M. et al. Historical agricultural landforms—Central European bio-cultural heritage. Land 11, 963 (2022).10.3390/land11070963 ↗
12. Wang, Y., Zhou, P., Geng, G., An, L. & Zhou, M. Enhancing point cloud registration with transformer: cultural heritage protection of the terracotta warriors. Herit. Sci. 12, 314 (2024).10.1186/s40494-024-01425-9 ↗
13. Wang, Z., Liu, Y. & Chen, H. How deep learning impacts the evaluation of traditional village landscapes: a review. Buildings 13, 525 (2023).10.3390/buildings13020525 ↗
14. Wu, S., Zhang, Q. et al. Effect of traditional village landscape genes on tourists’ image construction: a case of Zhangguying village. J. Resour. Ecol. 15, 587–600 (2024).
15. Tian, Y., Wang, J. et al. Parcel-level land-use mapping with very high-resolution imagery and landscape metrics in rural regions. Remote Sens. 13, 2146 (2021).10.3390/rs13112146 ↗
16. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA 770–778 (IEEE, 2016). https://doi.org/10.1109/CVPR.2016.90.10.1109/CVPR.2016.90 ↗
17. Hümmer, C. et al. Strong but simple: A baseline for domain generalized dense perception by clip-based transfer learning. In Proceedings of the Asian Conference on Computer Vision (ACCV) 4223–4244 (2024).10.1007/978-981-96-0972-7_27 ↗
18. Jain, A. et al. ODIN: a single model for 2D and 3D segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 3564–3574 https://doi.org/10.1109/CVPR52733.2024.00342 (IEEE, 2024).10.1109/CVPR52733.2024.00342 ↗
19. Kirillov, A. et al. Segment anything. Preprint at https://arxiv.org/abs/2304.02643 (2023).
20. Cheng, B., Schwing, A. & Kirillov, A. Masked-attention mask transformer for universal image segmentation (Mask2Former). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 1290–1299. https://doi.org/10.1109/CVPR52688.2022.00135 (IEEE, 2022).10.1109/CVPR52688.2022.00135 ↗
21. Sodano, M., Magistri, F., Nunes, L., Behley, J. & Stachniss, C. Open-world semantic segmentation including class similarity. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 3184–3194. https://doi.org/10.1109/CVPR52733.2024.00307 (IEEE, 2024).10.1109/CVPR52733.2024.00307 ↗
22. Li, F. et al. Semantic-sam: Segment and recognize anything at any granularity. Preprint at https://arxiv.org/abs/2307.04767 (2023).
23. Chen, J., Lu, J., Zhu, X. & Zhang, L. Generative semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 7111–7120. https://doi.org/10.1109/CVPR52729.2023.00687 (IEEE, 2023).10.1109/CVPR52729.2023.00687 ↗
24. Strudel, R., Garcia, R., Laptev, I. & Schmid, C. Segmenter: transformer for semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 7262–7272. https://doi.org/10.1109/ICCV48922.2021.00717 (2021).10.1109/ICCV48922.2021.00717 ↗
25. Zheng, P. et al. Bilateral reference for high-resolution dichotomous image segmentation. Preprint at https://arxiv.org/abs/2401.03407 (2024).10.26599/AIR.2024.9150038 ↗
26. Zhang, L. et al. Atrous convolution and multi-scale context for very high resolution remote sensing semantic segmentation: a review. Remote Sens. 14, 543 (2022).10.3390/rs14030543 ↗
27. Zhang, H. et al. Saanet: Scale-aware attention network for semantic segmentation of very high resolution aerial images. Remote Sens. 15, 5729 (2023).10.3390/rs15245729 ↗
28. Landauer, J. et al. Beyond the greater Angkor region: automatic large-scale mapping of Angkorian period reservoirs in satellite imagery using deep learning. PLoS ONE 20, e0320452 (2025).10.1371/journal.pone.0320452 ↗
29. Pistola, A., Orrù, V., Marchetti, N. & Roccetti, M. Ai-ming backwards: Vanishing archaeological landscapes in Mesopotamia and automatic detection of sites on corona imagery. PLoS ONE 20, e0330419 (2025).10.1371/journal.pone.0330419 ↗
30. Mo, S., Shi, Y., Yuan, Q. & Li, M. A survey of deep learning road extraction algorithms using high-resolution remote sensing images. Sensors 24, 1708 (2024).10.3390/s24051708 ↗
31. Wang, Z., Zhu, J. & Wu, Z. Study on the spatial distribution characteristics of traditional villages and their response to the water network system in the lower Yangtze River basin. Sci. Rep. 14, 22586 (2024).10.1038/s41598-024-74363-y ↗
32. Réby, K., Guilhelm, A. & De Luca, L. Semantic segmentation using foundation models for cultural heritage: an experimental study on Notre-Dame de Paris. In ICCV Workshops (e-Heritage) 1689–1697 (2023).10.1109/ICCVW60793.2023.00184 ↗
33. Yang, X., Jiang, X., Sun, Y., Liu, L. & Han, M. Uhr-effnet: A lightweight network for ultra-high-resolution remote sensing image semantic segmentation. Remote Sens. 16, 2192 (2024).10.3390/rs16122192 ↗
34. Wang, Z. et al. Accurate semantic segmentation of very high-resolution remote sensing images considering feature state sequences: From benchmark datasets to urban applications. ISPRS J. Photogramm. Remote Sens. 206, 92–105 (2024).
35. Zhou, M., Sui, H., Chen, S., Wang, J. & Chen, X. Bt-roadnet: a boundary- and topology-aware neural network for road extraction from high-resolution remote sensing imagery. ISPRS J. Photogramm. Remote Sens. 168, 288–306 (2020).10.1016/j.isprsjprs.2020.08.019 ↗
36. Sun, Z., Zhou, W., Ding, C. & Xia, M. Multi-resolution transformer network for building and road segmentation of remote sensing images. ISPRS Int. J. Geo-Inf. 11, 165 (2022).10.3390/ijgi11030165 ↗
37. Yuan, Y., Chen, X. & Wang, J. Object-contextual representations for semantic segmentation. In Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science Vol. 12351 (eds Vedaldi, A., Bischof, H., Brox, T. & Frahm, J. M.) 173-190 (Springer, Cham, 2020). https://doi.org/10.1007/978-3-030-58539-6_11.10.1007/978-3-030-58539-6_11 ↗
38. Tang, Y. et al. Using very high resolution remote sensing to assess cultural landscape change in mountain areas. Sustainability 14, 1319 (2022).10.3390/su14031319 ↗
39. Gou, J. et al. Knowledge distillation in deep learning: a survey. Int. J. Comput. Vis. 129, 1789–1819 (2021).10.1007/s11263-021-01453-z ↗
40. Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science Vol. 9351 (eds Navab, N., Hornegger, J., Wells, W. & Frangi, A.) 234-241 (Springer, Cham, 2015). https://doi.org/10.1007/978-3-319-24574-4_28.10.1007/978-3-319-24574-4_28 ↗
41. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F. & Adam, H. Encoder–decoder with atrous separable convolution for semantic image segmentation. In Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science Vol. 11211 (eds Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y.) 833-851 (Springer, Cham, 2018). https://doi.org/10.1007/978-3-030-01234-2_49.10.1007/978-3-030-01234-2_49 ↗
42. Zhao, H., Shi, J., Qi, X., Wang, X. & Jia, J. Pyramid scene parsing network. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA 6230-6239 (IEEE, 2017). https://doi.org/10.1109/CVPR.2017.660.10.1109/CVPR.2017.660 ↗
43. Berman, M., Rannen Triki, A. & Blaschko, M. B. The lovász-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA 4413-4421 (IEEE, 2018). https://doi.org/10.1109/CVPR.2018.00464.10.1109/CVPR.2018.00464 ↗
44. Liu, Z. et al. Semantic segmentation and photogrammetry of crowdsourced images to monitor historic facades. Herit. Sci. 10, 27 (2022).10.1186/s40494-022-00664-y ↗
45. Liao, H., Zhou, S., Zhang, K., Zhang, Y. & Liu, D. Automatic classification method for traditional village heritage value elements (TVHVE) using deep learning: a pilot study in Luxi County, Hunan, China. Herit. Sci. 12, 289 (2024).10.1186/s40494-024-01505-w ↗
46. Liu, H., Zhong, Y. & Gao, M. Study on spatial form evolution of traditional villages in Anhui province under the background of Gan–Po culture corridor. Herit. Sci. 12, 26 (2024).
47. Cordts, M. et al. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 3213–3223 (2016).10.1109/CVPR.2016.350 ↗
48. Neuhold, G., Ollmann, T., Rota Buló, S. & Kontschieder, P. The mapillary vistas dataset for semantic understanding of street scenes. In 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy 5000-5009 (IEEE, 2017). https://doi.org/10.1109/ICCV.2017.534.10.1109/ICCV.2017.534 ↗
49. Wang, J. et al. Loveda: A remote sensing land-cover dataset for domain adaptive semantic segmentation. In NeurIPS Datasets and Benchmarks (2021).
50. Xie, E. et al. Segformer: Simple and efficient design for semantic segmentation with transformers. In NeurIPS (2021).
51. Cui, Y., Jia, M., Lin, T.-Y., Song, Y. & Belongie, S. Class-balanced loss based on effective number of samples. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA 9260-9269 (IEEE, 2019). https://doi.org/10.1109/CVPR.2019.00949.10.1109/CVPR.2019.00949 ↗
52. Kervadec, H. et al. Boundary loss for highly unbalanced segmentation. In MIDL (2019).
53. Shit, S. et al. cldice: A novel topology-preserving loss function for tubular structure segmentation. In CVPR 16560–16569 (2021).10.1109/CVPR46437.2021.01629 ↗
54. Wilkinson, M. D. et al. The fair guiding principles for scientific data management and stewardship. Sci. Data 3, 160018 (2016).10.1038/sdata.2016.18 ↗
55. Remondino, F., Barazzetti, L., Nex, F., Scaioni, M. & Sarazzi, D. Uav photogrammetry for mapping and 3d modeling: Current status and future perspectives. In International Archives of the Photogrammetry, Remote Sensing And Spatial Information Sciences 25–31 (2011).10.5194/isprsarchives-XXXVIII-1-C22-25-2011 ↗