顾及多分辨率特征的复合字典城中村识别方法

doi:10.13474/j.cnki.11-2246.2023.0102

测绘通报 ›› 2023, Vol. 0 ›› Issue (4): 41-48,48.doi: 10.13474/j.cnki.11-2246.2023.0102

顾及多分辨率特征的复合字典城中村识别方法

邢若芸¹, 冉树浩¹, 高贤君^1,2,3, 杨元维^1,2,4, 方军^2,3

1. 长江大学地球科学学院, 湖北武汉 430100;
2. 湖南科技大学测绘遥感信息工程湖南省重点实验室, 湖南湘潭 411201;
3. 湖南科技大学地理空间信息技术国家地方联合工程实验室, 湖南湘潭 411201;
4. 城市空间信息工程北京市重点实验室, 北京 100045

收稿日期:2022-04-11 发布日期:2023-04-25
通讯作者: 高贤君。E-mail:junxgao@yangtzeu.edu.cn
作者简介:邢若芸(1997—),女,硕士,研究方向为遥感影像解译。E-mail:1832836094@qq.com
基金资助:
湖南科技大学测绘遥感信息工程湖南省重点实验室开放基金(E22205);自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室开放基金(MEMI-2021-2022-08);城市轨道交通数字化建设与测评技术国家工程实验室开放课题基金(2021ZH02);城市空间信息工程北京市重点实验室经费(20210205)

Identification method of urban villages with improved composite dictionary considering multi-resolution features

XING Ruoyun¹, RAN Shuhao¹, GAO Xianjun^1,2,3, YANG Yuanwei^1,2,4, FANG Jun^2,3

1. School of Geosciences, Yangtze University, Wuhan 430100, China;
2. Hunan Provincial Key Laboratory of Geo-information Engineering in Surveying, Mapping and Remote Sensing, Hunan University of Science and Technology, Xiangtan 411201, China;
3. National-local Joint Engineering Laboratory of Geo-spatial Information Technology, Hunan University of Science and Technology, Xiangtan 411201, China;
4. Beijing Key Laboratory of Urban Spatial Information Engineering, Beijing Institute of Surveying and Mapping, Beijing 100045, China

Received:2022-04-11 Published:2023-04-25

摘要/Abstract

摘要： 城中村作为一种特殊的城市聚落类型,对其进行精确有效的监控识别有助于实现城乡协调发展、优化城乡生态环境。现有面向对象的城中村识别方法通常需要大量样本数据,导致训练成本较高,数据更新效率偏低。针对以上问题,本文提出了顾及多分辨率特征的复合字典城中村识别方法。首先通过密集格网采样提取尺度不变特征转换(SIFT)全局特征,并与多分辨率颜色矢量角直方图特征融合,形成视觉词典;然后将影像表示为视觉词频率直方图;最后使用随机森林分类器进行分类,以实现场景尺度的城中村识别。以高分二号影像为测试数据对该方法进行验证,结果表明,其总体精度达90.08%,Kappa系数达80.16%,相较于加速稳健特征(SURF)、SIFT、VGG16、ResNet50,总体精度分别高出8.99%、3.51%、4.78%、2.28%。

关键词: 城中村识别, 高分辨率遥感影像, 复合字典, 多分辨率颜色特征, 直方图特征融合

Abstract: Urban village is a special type of urban settlement, and accurate and effective monitoring and identification of urban village is conducive to achieving coordinated development of urban and rural areas and optimizing the ecological environment. Existing object-oriented urban village identification methods usually require a large amount of sample data, resulting in high training cost and low data update efficiency. In order to solve the problems, a composite dictionary urban village identification method considering multi-resolution characteristics is proposed. Firstly, we use dense grid sampling to extract SIFT global features, and fuse them with multi-resolution color vector angular histogram features to form a visual dictionary. Then we use the image representation as a visual word frequency histogram. Finally, the random forest classifier is classified to realize the identification of urban villages at scene scale. The overall accuracy of the proposed method reaches 90.08% and the Kappa coefficient reaches 80.16%. It is 8.99%, 3.51%, 4.78% and 2.28% higher than that of SURF, SIFT, VGG16 and ResNet50, respectively.

Key words: identification of urban villages, high-resolution remote sensing images, composite dictionary, multi-resolution color features, histogram feature fusion

中图分类号:

P237

邢若芸, 冉树浩, 高贤君, 杨元维, 方军. 顾及多分辨率特征的复合字典城中村识别方法[J]. 测绘通报, 2023, 0(4): 41-48,48.

XING Ruoyun, RAN Shuhao, GAO Xianjun, YANG Yuanwei, FANG Jun. Identification method of urban villages with improved composite dictionary considering multi-resolution features[J]. Bulletin of Surveying and Mapping, 2023, 0(4): 41-48,48.

参考文献

[1] 冯权泷,陈泊安,牛博文,等. 基于多尺度扩张卷积神经网络的城中村遥感识别[J]. 农业机械学报,2021,52(11):181-189.
[2] ZENG H,YU X,ZHANG J. Urban village demolition,migrant workers' rental costs and housing choices:evidence from Hangzhou,China[J]. Cities,2019,94:70-79.
[3] 田艳玲,张维桐,张锲石,等. 图像场景分类技术综述[J]. 电子学报,2019,47(4):915-926.
[4] WURM M,TAUBENBÖCK H,WEIGAND M,et al. Slum mapping in polarimetric SAR data using spatial features[J]. Remote Sensing of Environment,2017,194:190-204.
[5] VATSAVAI R R,CHERIYADAT A,GLEASON S. Unsupervised semantic labeling framework for identification of complex facilities in high-resolution remote sensing images[C]//Proceedings of 2010 IEEE International Conference on Data Mining Workshops. Sydney:IEEE,2011:273-280.
[6] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.
[7] 冯建英,吴丹丹,王博,等. 中文在线评论文本分析对生鲜农产品电商影响研究综述[J]. 农业机械学报,2021,52(S1):504-512.
[8] QUELHAS P,MONAY F,ODOBEZ J M,et al. A thousand words in a scene[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(9):1575-1589.
[9] 刘辉. 基于高分辨率遥感影像的城中村提取方法研究[D]. 武汉:武汉大学,2018.
[10] YANG Yi,NEWSAM S. Bag-of-visual-words and spatial extensions for land-use classification[C]//Proceedings of the 18th SigSpatial International Conference on Advances in Geographic Information Systems. New York:ACM,2010:270-279.
[11] ZHU Qiqi,ZHONG Yanfei,ZHAO Bei,et al. Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery[J]. IEEE Geoscience and Remote Sensing Letters,2016,13(6):747-751.
[12] FENG Jiangfan,LIU Yuanyuan,WU Lin. Bag of visual words model with deep spatial features for geographical scene classification[J]. Computational Intelligence and Neuroscience,2017(6-19):5169675.
[13] RAZAVIAN A S,AZIZPOUR H,SULLIVAN J,et al. CNN features off-the-shelf:an astounding baseline for recognition[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Columbus:IEEE,2014:512-519.
[14] HERSHEY S,CHAUDHURI S,ELLIS D P W,et al. CNN architectures for large-scale audio classification[C]//Proceedings of 2017 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). New Orleans:IEEE,2017:131-135.
[15] WURM M,STARK T,XX Z,et al. Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2019,150:59-69.
[16] TAN X,SUN C M,SIRAULT X,et al. Feature matching in stereo images encouraging uniform spatial distribution[J]. Pattern Recognition,2015,48(8):2530-2542.
[17] 朱祺琪. 面向高分辨率遥感影像场景语义理解的概率主题模型研究[D]. 武汉:武汉大学,2018.
[18] LODHI H,SAUNDERS C,SHAWE-TAYLOR J,et al. Text classification using string kernels[J]. The Journal of Machine Learning Research,2002,2:419-444.
[19] 戚超,左毅,陈哲琪,等. 基于改进VGG16的大米加工精度分级方法研究[J]. 农业机械学报,2021,52(5):301-307.
[20] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas:IEEE,2016:770-778.
[21] 杨森,冯全,张建华,等. 基于深度学习与复合字典的马铃薯病害识别方法[J]. 农业机械学报,2020,51(7):22-29.
[22] 许景辉,邵明烨,王一琛,等. 基于迁移学习的卷积神经网络玉米病害图像识别[J]. 农业机械学报,2020,51(2):230-236.
[23] 唐颖复,王忠静,张子雄. 基于改进SIFT和SURF算法的沙丘图像配准[J]. 清华大学学报(自然科学版),2021,61(2):161-169.

顾及多分辨率特征的复合字典城中村识别方法

Identification method of urban villages with improved composite dictionary considering multi-resolution features

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张悦, 张锦. 泥石流高分辨率遥感影像频域特征提取方法及应用[J]. 测绘通报, 2023, 0(3): 111-115.
[2]	潘建平, 付占宝, 程卫华, 陆世安, 李鑫, 孙博文, 黄桂萍. 基于地表类型的山地海绵城市生态建设评估[J]. 测绘通报, 2022, 0(5): 84-88.
[3]	陈智朗, 付振华, 朱紫阳, 王慧慧, 刘沁雯, 杨钰灵, 许耿然. 基于HRNet的高分辨率遥感影像建筑物变化信息提取[J]. 测绘通报, 2022, 0(5): 126-132.
[4]	杨素妨, 杜林. 多特征流形鉴别嵌入的高分辨率遥感影像分类[J]. 测绘通报, 2021, 0(9): 37-42.
[5]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[6]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021, 0(6): 44-49.
[7]	陈利燕, 林鸿, 吴健华. 融合随机森林和超像素分割的建筑物自动提取[J]. 测绘通报, 2021, 0(2): 49-53.
[8]	王媛, 杜明义, 杨柳忠, 蔡国印, 张宁. 多源遥感数据支持下的城市生态状况评价[J]. 测绘通报, 2021, 0(11): 16-20.
[9]	迪里胡玛尔·阿汗木江, 玉素甫江·如素力. 新疆焉耆盆地土壤湿度时空分布特征[J]. 测绘通报, 2021, 0(11): 36-41.
[10]	常京新, 高贤君, 杨元维, 王双喜. 融合多时相高分影像的建筑物轮廓优化方法[J]. 测绘通报, 2020, 0(7): 112-115.
[11]	谢梦, 刘伟, 李二珠, 杨梦圆, 王晓檀. 深度卷积神经网络支持下的遥感影像语义分割[J]. 测绘通报, 2020, 0(5): 36-42.
[12]	乔婷婷, 李鲁群. 结合数据增广和迁移学习的高分辨率遥感影像场景分类[J]. 测绘通报, 2020, 0(2): 37-42.
[13]	陈辉, 张卡, 宿东, 王蓬勃. 建筑物侧面轮廓线约束的高分辨率遥感影像建筑物高度估算方法[J]. 测绘通报, 2019, 0(9): 34-37,72.
[14]	孟庆祥, 吴玄. 基于深度卷积神经网络的高分辨率遥感影像场景分类[J]. 测绘通报, 2019, 0(7): 17-22.
[15]	郝怀旭, 万太礼, 罗年学. 利用OpenStreetMap数据进行高空间分辨率遥感影像分类[J]. 测绘通报, 2019, 0(7): 69-72,126.