Division of planar forms of traditional residences in the Hehuang region validated by CNN

ZHANG Xinhong; WEI Bin; DONG Jianhong

doi:10.16152/j.cnki.xdxbzr.2026-02-018

您当前的位置：

首页 >

文章列表页 >

Division of planar forms of traditional residences in the Hehuang region validated by CNN

Cultural heritage conservation | 更新时间：2026-05-11

- Division of planar forms of traditional residences in the Hehuang region validated by CNN
- Journal of Northwest University (Natural Science Edition) Vol. 56, Issue 2, Pages: 431-442(2026)
- 作者机构：
  
  1.兰州理工大学　建筑与艺术设计学院/东南大学城市与建筑遗产保护教育部重点实验室（西北中心），甘肃　兰州　730050
  2.烟台南山学院　艺术与设计学院，山东　烟台　265700
- 作者简介：
- 基金信息：
- DOI：10.16152/j.cnki.xdxbzr.2026-02-018
  CLC： TU241.5
- Received：27 January 2026，
  
  Revised：2026-03-14，
  
  Published：25 April 2026
- 稿件说明：
移动端阅览
ZHANG Xinhong, WEI Bin, DONG Jianhong. Division of planar forms of traditional residences in the Hehuang region validated by CNN[J]. Journal of Northwest University (Natural Science Edition), 2026, 56(2): 431-442.
DOI：

ZHANG Xinhong, WEI Bin, DONG Jianhong. Division of planar forms of traditional residences in the Hehuang region validated by CNN[J]. Journal of Northwest University (Natural Science Edition), 2026, 56(2): 431-442. DOI： 10.16152/j.cnki.xdxbzr.2026-02-018.

摘要

现有针对河湟地区传统民居平面形态的研究，存在着类型划分不一致与不完善的问题。在梳理已有研究和研判多源数据的基础上，提出一种新的类型划分体系，进而借助卷积神经网络技术对其适用性进行了对比验证。结果表明：①新建类型体系的总体识别准确率和类别簇群边界均明显优于4种已有类型体系；②二字型的加入不仅提高了L字型的识别准确率、降低了一字型的误判率，而且也显著增强了L字型、凹字型和一字型3个簇群间的语义区分度；③日字型的加入既提高了凹字型的识别准确率、降低了其被误判为回字型的概率，也强化了凹字型簇群与回字型簇群之间的语义界限，增强了各类别样本点语义特征的一致性。验证表明新建类型体系更适用于河湟地区传统民居平面形态类型的划分，这不仅为地区传统村落与传统民居的保护传承提供了理论支撑，也为其他地区开展相关研究提供了案例借鉴。

Abstract

The existing research on the planar form of traditional residences in the Hehuang region presents inconsistencies and insufficiencies in type division. Based on the review of existing research and the assessment of multi-source data

a new type division system is proposed and its applicability is validated by using convolutional neural networks (CNN) technology. The results show that: ① the overall recognition accuracy and the boundary definition of clusters in the new typological system are significantly superior to those of four existing systems; ② the inclusion of "Ⅱ-shaped" not only improves the recognition accuracy for "L-shaped" and reduces the misclassification rate for "-shaped" but also significantly enhances the semantic distinctiveness between the clusters of "L-shaped"

"凹-shaped" and "Ⅰ-shaped". ③ the inclusion of "日-shaped" not only improves the recognition accuracy for "凹-shaped" forms and reduces the probability of misclassifying "凹-shaped" as "回-shaped"

but also strengthens the semantic boundaries between the "凹-shaped" and "回-shaped" clusters

enhancing the consistency of semantic features among the samples within each category. Overall

the newly established type system is more applicable to the division of types of traditional residential planar forms in the Hehuang region

providing theoretical support for the protection and inheritance of traditional villages and residences in the region

and offering case references for similar research in other areas.

关键词

Keywords

references

刘奔腾 . 甘肃聚落 [M ] . 北京 : 中国建筑工业出版社 , 2023 : 1 - 5 .

常青 . 传统聚落古今观——纪念中国营造学社成立九十周年 [J ] . 建筑学报 , 2019 ( 12 ): 14 - 19 .

CHANG Q . A historical and contemporary perspective on traditional settlements: Commemorating the 90th anniversary of the establishment of the society for research in Chinese architecture [J ] . Architectural Journal , 2019 ( 12 ): 14 - 19 .

阿摩斯·拉普卜特 . 宅形与文化 [M ] . 北京 : 中国建筑工业出版社 , 2007 : 45 - 77 .

印朗川 , 刘沛林 . 湘江流域传统民居平面原型基因的类型表达及空间分异 [J ] . 地理研究 , 2023 , 42 ( 8 ): 2191 - 2210 .

YIN L C , LIU P L . Typological expression and spatial differentiation of planar prototype genes of traditional dwellings in the Xiangjiang River basin [J ] . Geographical Research , 2023 , 42 ( 8 ): 2191 - 2210 .

陶伟 , 何新 , 蒋伟 . 平遥古城传统民居形态特征的变迁及其类型：基于堪舆学的微观探察 [J ] . 人文地理 , 2014 , 29 ( 5 ): 40 - 48 .

TAO W , HE X , JIANG W . Evolution of morphological characteristics and type classification of traditional dwellings in the ancient city of Pingyao: A microscopic investigation based on Kan-yu geomancy [J ] . Human Geography , 2014 , 29 ( 5 ): 40 - 48 .

李婧 , 杨定海 , 肖大威 . 海南岛传统聚落文化分区及区际过渡关系研究——从海南岛传统民居平面形制及聚落形态类型谈起 [J ] . 建筑学报 , 2020 ( S2 ): 8 - 15 .

LI J , YANG D H , XIAO D W . Research on cultural zoning and inter-regional transition relationship of traditional settlements in Hainan Island: From the perspective of plan form of traditional dwellings and settlement morphology types [J ] . Architectural Journal , 2020 ( S2 ): 8 - 15 .

张献梅 , 左满常 . 河南民居院落平面布局特征 [J ] . 安徽农业科学 , 2008 , 36 ( 35 ): 15474 - 15476, 15622 .

ZHANG X M , ZUO M C . Plan layout characteristics of traditional residential courtyards in Henan [J ] . Journal of Anhui Agricultural Sciences , 2008 , 36 ( 35 ): 15474 - 15476, 15622 .

LI S T , SONG W W , FANG L Y , et al . Deep learning for hyperspectral image classification: An overview [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 9 ): 6690 - 6709 .

MA L , LI M C , MA X X , et al . A review of supervised object-based land-cover image classification [J ] . ISPRS Journal of Photogrammetry and Remote Sensing , 2017 , 130 : 277 - 293 .

杨瑞 , 祁元 , 苏阳 . 深度学习U-Net方法及其在高分辨卫星影像分类中的应用 [J ] . 遥感技术与应用 , 2020 , 35 ( 4 ): 767 - 774 .

YANG R , QI Y , SU Y . Deep learning U-Net model and its application in high-resolution satellite image classification [J ] . Remote Sensing Technology and Application , 2020 , 35 ( 4 ): 767 - 774 .

田甜 , 王迪 , 王珍 , 等 . 基于深度学习模型的种植结构复杂区农作物精细分类研究 [J ] . 中国农业资源与区划 , 2022 , 43 ( 12 ): 147 - 158 .

TIAN T , WANG D , WANG Z , et al . Fine classification of crops in complex planting structure areas based on deep learning models [J ] . Chinese Journal of Agricultural Resources and Regional Planning , 2022 , 43 ( 12 ): 147 - 158 .

赖丽娜 , 米瑜 , 周龙龙 , 等 . 生成对抗网络与文本图像生成方法综述 [J ] . 计算机工程与应用 , 2023 , 59 ( 19 ): 21 - 39 .

LAI L N , MI Y , ZHOU L L , et al . A survey of generative adversarial networks and text-to-image generation methods [J ] . Computer Engineering and Applications , 2023 , 59 ( 19 ): 21 - 39 .

刘羿漩 , 葛广英 , 齐振岭 , 等 . 基于改进深度卷积生成对抗网络的刺绣图像修复 [J ] . 激光与光电子学进展 , 2023 , 60 ( 20 ): 68 - 78 .

LIU Y X , GE G Y , QI Z L , et al . Embroidery image restoration based on improved deep convolutional generative adversarial network [J ] . Laser & Optoelectronics Progress , 2023 , 60 ( 20 ): 68 - 78 .

程擎 , 范满 , 李彦冬 , 等 . 无人机航拍图像语义分割研究综述 [J ] . 计算机工程与应用 , 2021 , 57 ( 19 ): 57 - 69 .

CHENG Q , FAN M , LI Y D , et al . A survey of semantic segmentation for UAV aerial images [J ] . Computer Engineering and Applications , 2021 , 57 ( 19 ): 57 - 69 .

刘艳飞 , 丁乐乐 , 孟凡效 . 目标上下文卷积神经网络高分遥感影像语义分割 [J ] . 遥感信息 , 2021 , 36 ( 6 ): 66 - 74 .

LIU Y F , DING L L , MENG F X . Semantic segmentation of high-resolution remote sensing images using object context convolutional neural network [J ] . Remote Sensing Information , 2021 , 36 ( 6 ): 66 - 74 .

杨军 , 李博赞 . 基于自注意力特征融合组卷积神经网络的三维点云语义分割 [J ] . 光学精密工程 , 2022 , 30 ( 7 ): 840 - 853 .

YANG J , LI B Z . 3D point cloud semantic segmentation based on self-attention feature fusion group convolutional neural network [J ] . Optics and Precision Engineering , 2022 , 30 ( 7 ): 840 - 853 .

邵延华 , 张铎 , 楚红雨 , 等 . 基于深度学习的YOLO目标检测综述 [J ] . 电子与信息学报 , 2022 , 44 ( 10 ): 3697 - 3708 .

SHAO Y H , ZHANG D , CHU H Y , et al . A survey of YOLO object detection based on deep learning [J ] . Journal of Electronics & Information Technology , 2022 , 44 ( 10 ): 3697 - 3708 .

董志鹏 . 基于卷积神经网络的高分辨率遥感影像目标检测方法研究 [J ] . 测绘学报 , 2023 , 52 ( 9 ): 1613 .

DONG Z P . Research on convolutional neural network-based object detection method for high-resolution remote sensing images [J ] . Acta Geodaetica et Cartographica Sinica , 2023 , 52 ( 9 ): 1613 .

覃巧华 , 肖大威 , 骆明楠 , 等 . 基于卷积神经网络的传统村落图景分类研究 [J ] . 城市规划 , 2020 , 44 ( 7 ): 52 - 58 .

QIN Q H , XIAO D W , LUO M N , et al . Research on scene classification of traditional villages based on convolutional neural networks [J ] . City Planning Review , 2020 , 44 ( 7 ): 52 - 58 .

TAO J , LI G , SUN Q , et al . An approach for identifying historic village using deep learning [J ] . SN Applied Sciences , 2023 , 5 ( 1 ): 13 .

蔡军 , 温日强 , 江伟 , 等 . 传统村落航拍图像中民族建筑识别的DeepLabV 3 +改进算法 [J ] . 测绘通报 , 2023 ( 4 ): 49 - 53 .

CAI J , WEN R Q , JIANG W , et al . Improved Deep-LabV 3 + algorithm for ethnic architecture recognition in aerial images of traditional villages [J ] . Bulletin of Surveying and Mapping , 2023 ( 4 ): 49 - 53 .

丁柏峰 . 河湟文化圈的形成历史与特征 [J ] . 青海师范大学学报：哲学社会科学版 , 2007 ( 6 ): 68 - 71 .

DING B F . The formation history and characteristics of the Hehuang cultural circle [J ] . Journal of Qinghai Normal University (Philosophy and Social Sciences E-dition) , 2007 ( 6 ): 68 - 71 .

武沐 , 王希隆 . 试论明清时期河湟文化的特质与功能 [J ] . 兰州大学学报 , 2001 , 29 ( 6 ): 45 - 52 .

WU M , WANG X L . On the intrinsic features and functions of Hehuang culture in the Ming and Qing Dynasties [J ] . Journal of Lanzhou University , 2001 , 29 ( 6 ): 45 - 52 .

高小强 . 甘青传统民居地理研究 [D ] . 西安 : 陕西师范大学 , 2017 .

王东东 , 韩卫成 . 基于建筑类型学的晋东南传统民居院落形态特征研究 [J ] . 中外建筑 , 2022 ( 5 ): 126 - 130 .

WANG D D , HAN W C . Research on morphological characteristics of traditional residential courtyards in Southeast Shanxi based on architectural typology [J ] . Chinese & Overseas Architecture , 2022 ( 5 ): 126 - 130 .

冀晶娟 , 傅潇琳 . 广西单幢传统民居住居空间类型分布及其文化地理逻辑 [J ] . 南方建筑 , 2025 ( 9 ): 58 - 68 .

JI J J , FU X L . Typological distribution of residential space of single-block traditional dwellings in Guangxi and its underlying cultural-geographical logic [J ] . South Architecture , 2025 ( 9 ): 58 - 68 .

曹琦 . 河南传统民居空间形态探析 [J ] . 郑州轻工业学院学报(社会科学版) , 2011 , 12 ( 6 ): 48 - 52 .

CAO Q . Analysis of spatial morphology of traditional dwellings in Henan [J ] . Journal of Zhengzhou University of Light Industry (Social Science Edition) , 2011 , 12 ( 6 ): 48 - 52 .

毛志远 , 徐雷 . 杭州传统民居类历史建筑的总平面格局分类研究 [J ] . 建筑与文化 , 2016 ( 8 ): 234 - 235 .

MAO Z Y , XU L . Classification research on the master plan pattern of historical buildings of traditional dwelling type in Hangzhou [J ] . Architecture & Culture , 2016 ( 8 ): 234 - 235 .

宋祥 . 青海河湟地区山地庄廓聚落景观形态研究 [D ] . 西安 : 西安建筑科技大学 , 2016 .

李旻泽 . 青海河湟谷地传统民居地域性研究 [D ] . 西安 : 长安大学 , 2016 : 34 - 51 .

张萍 . 河湟地区民族建筑地域适应性研究 [D ] . 兰州 : 兰州大学 , 2017 : 71 - 92 .

黄志林 . 青海河湟地区庄廓民居节能优化研究 [D ] . 西安 : 长安大学 , 2021 : 4 - 6 .

靳亦冰 , 王军 . 青海聚落 [M ] . 北京 : 中国建筑工业出版社 , 2022 : 139 - 142 .

吴晶晶 , 王军 , 白涛 . 青海省东部河湟地区少数民族传统聚落和民居生存智慧研究 [J ] . 四川建筑科学研究 , 2013 , 39 ( 1 ): 304 - 306 .

WU J J , WANG J , BAI T . Research on the living wisdom embodied in traditional settlements and dwellings of ethnic minorities in the eastern Hehuang region of Qinghai Province [J ] . Sichuan Building Science , 2013 , 39 ( 1 ): 304 - 306 .

KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J ] . Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .

LECUN Y , BENGIO Y , HINTONG G E . Deep learning [J ] . Nature , 2015 , 521 ( 7553 ): 436 - 444 .

崔艳荣 , 邹斌 , 韩震 , 等 . 卷积神经网络在卫星遥感海冰图像分类中的应用探究——以渤海海冰为例 [J ] . 海洋学报(中文版) , 2020 , 42 ( 9 ): 100 - 109 .

CUI Y R , ZOU B , HAN Z , et al . Application of convolutional neural networks in sea ice image classification with satellite remote sensing: A case study of sea ice in the Bohai Sea [J ] . Acta Oceanologica Sinica (Chinese Edition) , 2020 , 42 ( 9 ): 100 - 109 .

李亚飞 , 董红斌 . 基于卷积神经网络的遥感图像分类研究 [J ] . 智能系统学报 , 2018 , 13 ( 4 ): 550 - 556 .

LI Y F , DONG H B . Research on remote sensing image classification based on convolutional neural networks [J ] . CAAI Transactions on Intelligent Systems , 2018 , 13 ( 4 ): 550 - 556 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰