基于遥感影像的农田边界提取方法研究进展

doi:10.13733/j.jcam.issn.20955553.2024.12.025

摘要/Abstract

摘要：

农田边界的自动提取对高效量化农田土地资源和制定相关调控政策十分重要，是农业现代化和智慧化发展的必要条件。统计多种农田边界提取尺度下常用的遥感数据，简述农田边界提取技术经历了从无监督到监督提取的发展，总结并对比农田边界提取的4种主要方法，包括基于边缘检测的方法、基于区域的方法、混合方法和深度学习方法，深度学习方法属于监督提取技术，与遥感技术的发展息息相关。简述农田边界提取精度评定中的参考图像获取与精度评估方法。提出目前存在农田边界特征利用和挖掘不足、缺乏公开实时的数据集、缺乏针对小农地区的研究、提取方法普适性不足的问题。在综合应用农田边界特征、共享农田边界大数据和应用云计算平台、开发小农地区农田边界提取方法、融合时空协同的多源数据方面作出展望。

关键词: 农田边界, 地块分割, 边缘检测, 图像处理

Abstract:

The automated and accurate extraction of farmland boundaries plays a crucial role in effectively quantifying agricultural land resources and setting relevant regulatory policies. It is essential to the development of modern agriculture and smart agriculture. This paper compiles commonly used remote sensing data across various extraction scales and outlining the development of boundary extraction techniques from unsupervised to supervised methods. The edge-based, region-based, hybrid and deep learning methods were comprehensively summarized and compared. Deep learning, a supervised extraction technique, is closely linked to advancements in remote sensing technology. Accuracy assessment involves reference image acquisition and evaluation methods. Current challenges include the underutilization and limited exploration of farmland boundary features, the lack of publicly available and real-time datasets, the scarcity of research focused on smallholder areas, and the limited applicability of existing extraction methods. In order to overcome these challenges, the future directions of research were proposed, such as the integrated utilization of different farmland boundary features, the establishment of data-sharing platforms for comprehensive farmland boundary data, the application of cloud computing in farmland boundary analysis, the development of specialized extraction methods for smallholder areas, and the integration of spatiotemporal data from multiple sources.

Key words: farmland boundary, land segmentation, edge detection, image processing

中图分类号:

S127

孔鸣凤, 郑海峰, . 基于遥感影像的农田边界提取方法研究进展[J]. 中国农机化学报, 2024, 45(12): 168-174.

Kong Mingfeng, , Zheng Haifeng, . Research progress in farmland boundary extraction methods based on remote sensing image[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(12): 168-174.

参考文献

［1］　Garcia P A, Gonzalo-Martin C, Lillo S M. A machine learning approach for agricultural parcel delineation through agglomerative segmentation ［J］. International Journal of Remote Sensing, 2017, 38(7): 1809-1819.
［2］　Zhang H, Liu M, Wang Y, et al. Automated delineation of agricultural field boundaries from Sentinel-2 images using recurrent residual U-Net ［J］. International Journal of Applied Earth Observation and Geoinformation, 2021, 105: 102557.
［3］　石淑芹, 曹玉青, 吴文斌, 等. 耕地集约化评价指标体系与评价方法研究进展［J］. 中国农业科学, 2017, 50(7): 1210-1222.
Shi Shuqin, Cao Yuqing, Wu Wenbin, et al. Progresses in research of evaluation index system and its method on arable land intensification: A review ［J］. Scientia Agricultural Sinica, 2017, 50(7): 1210-1222.
［4］　张春华, 李修楠, 吴孟泉, 等. 基于Landsat 8 OLI数据与面向对象分类的昆嵛山地区土地覆盖信息提取［J］. 地理科学, 2018, 38(11): 1904-1913.
Zhang Chunhua, Li Xiunan, Wu Mengquan, et al. Objectoriented classification of land cover based on Landsat 8 OLI image data in the Kunyu Mountain ［J］. Scientia Geographica Sinica, 2018, 38(11): 1904-1913.
［5］　Martin D R, Fowlkes C C, Malik J. Learning to detect natural image boundaries using local brightness color and texture cues ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(5): 530-549.
［6］　Rydberg A, Borgefors G. Integrated method for boundary delineation of agricultural fields in multispectralsatellite images ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(11): 2514-2520.
［7］　Watkins B, Niekerk A V. A comparison of objectbased image analysis approaches for field boundary delineation using multitemporal Sentinel-2 imagery ［J］. Computers and Electronics in Agriculture, 2019, 158: 294-302.
［8］　Schultz B, Immitzer M, Formaggio A R, et al. Selfguided segmentation and classification of multitemporal Landsat 8 images for crop type mapping in southeastern Brazil ［J］. Remote Sensing, 2015, 7(11): 14482-14508.
［9］　周文, 明冬萍, 闫鹏飞. 结合影像分区与尺度估计的耕地提取方法研究［J］. 地球信息科学学报, 2018, 20(7): 1014-1025.
Zhou Wen, Ming Dongping, Yan Pengfei. Cultivated land extraction based on image region division and scale estimation ［J］. Journal of Geoinformation Science, 2018, 20(7): 1014-1025.
［10］　Gopidas D K, Priya D R. Hybrid segmentation method for boundary delineation of agricultural fields in multitemporal satellite image using HS-PSO-FCNN ［J］. Materials Today: Proceedings, 2022, 51: 2272-2276.
［11］　Kumar M S, Jayagopal P. Delineation of field boundary from multispectral satellite images through U-Net segmentation and template matching ［J］. Ecological Informatics, 2021, 64: 101370.
［12］　Yan L, Roy D P. Conterminous United States crop field size quantification from multitemporal Landsat data ［J］. Remote Sensing of Environment, 2016, 172: 67-86.
［13］　Crommelinck S, Bennett R, Gerke M, et al. Contour detection for UAVbased cadastral mapping ［J］. Remote Sensing, 2017, 9(2): 171-183.
［14］　Wagner M P, Oppelt N. Extracting agricultural fields from remote sensing imagery using graphbased growing contours ［J］. Remote Sensing, 2020, 12(7): 1205-1224.
［15］　Graesser J, Ramankutty N. Detection of cropland field parcels from Landsat imagery ［J］. Remote Sensing of Environment, 2017, 201: 165-180.
［16］　Babawuro U, Bei J Z. Satellite imagery cadastral features extractions using image processing algorithms: A viable option for cadastral science ［J］. International Journal of Computer Science Issues, 2012, 9(4): 30-38.
［17］　Cai Z, Hu Q, Zhang, X, et al. An adaptive image segmentation method with automatic selection of optimal scale for extracting cropland parcels in small holder farming systems ［J］. Remote Sensing, 2022, 14(13): 3037-3057.
［18］　Masoud K M, Persello C, Tolpekin V A. Delineation of agricultural field boundaries from Sentinel-2 images using a novel superresolution contour detector based on fully convolutional networks ［J］. Remote Sensing, 2019, 12(1): 59-74.
［19］　Sobel I. Neighborhood coding of binary images for fast contour following and general binary array processing ［J］. Computer Graphics and Image Processing, 1978, 8(1): 127-135.
［20］　Canny J. A computational approach to edgedetection ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
［21］　Chen B, Qiu F, Wu B, et al. Image segmentation based on constrained spectral variance difference and edge penalty ［J］. Remote Sensing, 2015, 7(5): 5980-6004.
［22］　Cheng Taoji, Yang Xusheng, Zheng Gaoxiang, et al. DESTIN: A new method for delineating the boundaries of crop fields by fusing spatial and temporal information from WorldView and Planet satellite imagery ［J］. Computers and Electronics in Agriculture, 2020, 178: 105787.
［23］　Hong R, Park J, Jang S, et al. Development of a parcellevel land boundary extraction algorithm for aerial imagery of regularly arranged agricultural areas ［J］. Remote Sensing, 2021, 13(6): 1167-1186.
［24］　庞新华, 朱文泉, 潘耀忠, 等. 基于高分辨率遥感影像的耕地地块提取方法研究［J］. 测绘科学, 2009, 34(1): 48-49, 161.
Pang Xinhua, Zhu Wenquan, Pan Yaozhong, et al. Research on the extraction method of cultivated land based on high resolution remote sensing image ［J］. Science of Surveying and Mapping, 2009, 34(1): 48-49, 161.
［25］　Pal S K, Mitra P. Multispectral image segmentation using the roughsetinitialized EM algorithm ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(11): 2495-2501.
［26］　沈占锋, 骆剑承, 吴炜, 等. 采用并行均值漂移算法实现农林地块边界的精确提取［J］. 中国图象图形学报, 2011, 16(9): 1689-1695.
Shen Zhanfeng, Luo Jianchen, Wu Wei, et al. Agricultural and forestry land boundary precise segmentation from remote sensing images by parallel mean shift algorithm ［J］. Journal of Image and Graphics, 2011, 16(9): 1689-1695.
［27］　吴晗, 林晓龙, 李曦嵘, 等. 面向农业应用的无人机遥感影像地块边界提取［J］. 计算机应用, 2019, 39(1): 298-304.
Wu Han, Li Xiaolong，Li Xirong, et al.Land parcel boundary extraction of UAV remote sensing image in agricultural application ［J］. Journal of Computer Applications, 2019, 39(1): 298-304.
［28］　苏腾飞, 张圣微, 李洪玉. 基于可变尺度Mean-Shift的农田高分遥感影像分割算法［J］. 国土资源遥感, 2017, 29(3): 41-50.
Su Tengfei, Zhang Shengwei, Li Hongyu. Variable scale Mean-Shift based method for cropland segmentation from high spatial resolution remote sensing images ［J］. Remote Sensing for Land and Resources, 2017, 29(3): 41-50.

［29］　Peng D, Zhang Y. Objectbased change detection from satellite imagery by segmentation optimization and multifeatures fusion ［J］. International Journal of Remote Sensing, 2017, 38(13): 3886-3905.

［30］　杨颖频, 吴志峰, 骆剑承, 等. 时空协同的地块尺度作物分布遥感提取［J］. 农业工程学报, 2021, 37(7):166-174.
Yang Yingpin, Wu Zhifeng, Luo Jianchen, et al. Parcelbased crop distribution extraction using the spatiotemporal collaboration of remote sensing data ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(7): 166-174.
［31］　Bergado J R, Persello C, Gevaert C. A deep learning approach to the classification of subdecimetre resolution aerial images ［J］. 2016 IEEE International Geoscience and Remote Sensing Symposium, 2016.
［32］　Marmanis D, Datcu M, Esch T, et al. Deep learning earth observation classification using ImageNet Pretrained Networks ［J］. IEEE Geoscience and Remote Sensing Letters, 2016, 13(1): 105-109.
［33］　周楠, 杨鹏, 魏春山, 等. 地块尺度的山区耕地精准提取方法［J］. 农业工程学报, 2021, 37(19): 260-266.
Zhou Nan, Yang Peng, Wei Chunshan, et al. Accurate extraction method for cropland in mountainous areas based on field parcel ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(19): 260-266.
［34］　Zhou Y, Luo J, Feng L, et al. Longshorttermmemorybased crop classification using highresolution optical images and multitemporal SAR data ［J］. Giscience & Remote Sensing, 2019, 56(8): 1170-1191.
［35］　周飞燕, 金林鹏, 董军. 卷积神经网络研究综述［J］. 计算机学报, 2017, 40(6): 1229-1251.
Zhou Feiyan, Jin Linpeng, Dong Jun. Review of convolutional neural network ［J］. Chinese Journal of Computers, 2017, 40(6): 1229-1251.
［36］　Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3431-3440.
［37］　Wang S, Chen W, Xie S M, et al. Weakly supervised deep learning for segmentation of remote sensing imagery ［J］. Remote Sensing, 2020, 12(2): 207-231.
［38］　GarciaPedrero A, LilloSaavedra M, RodriguezEsparragon D, et al. Deep learning for automatic outlining agricultural parcels: Exploiting the land parcel identification system ［J］. IEEE Access, 2019, 7: 158223-158236.
［39］　Ma L, Liu Y, Zhang X, et al. Deep learning in remote sensing applications: A metaanalysis and review ［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 152: 166-177.

[1]	杨浩勇 , 王超柱 , 刘浩义 , 关心桐 , 刘璎瑛 , 丁永前 . 种子破损率快速检测方法研究[J]. 中国农机化学报, 2024, 45(9): 104-110.
[2]	张延军, 赵建鑫, . 基于多路神经网络的黄花菜关节点检测算法研究[J]. 中国农机化学报, 2024, 45(7): 228-234.
[3]	郎秀丹, 史宇亮, 李天华, 陈明东. 基于阈值识别的温室黄瓜整体自动落蔓装置研究[J]. 中国农机化学报, 2024, 45(6): 106-112.
[4]	杨昊霖, 王其欢, 李华彪, 耿端阳, 武继达, 姚艳春. 基于改进YOLOv5的田间复杂环境障碍物检测[J]. 中国农机化学报, 2024, 45(6): 216-222.
[5]	缪亚伦, 石美琦, 孟海涛, 梁旭升, 黄才贵, 李岩舟. 基于Stereo CameraYOLOv5自然环境下百香果检测与定位模型[J]. 中国农机化学报, 2024, 45(3): 233-241.
[6]	张伟进, 王福顺, , 孙小华, 王军皓, 刘宏权, 王鑫鑫, . 传统图像分割算法在农作物籽粒考种应用中的研究进展[J]. 中国农机化学报, 2024, 45(2): 280-287.
[7]	郑红娜, , 周理想, 王强. 基于YOLO-PS的马铃薯幼苗检测方法研究[J]. 中国农机化学报, 2024, 45(12): 245-250.
[8]	姜华骏, 陆静平, 林运东. 基于二维激光雷达的甘蔗垄高检测研究[J]. 中国农机化学报, 2024, 45(11): 145-149.
[9]	崔高建, 李晓娟. 长绒棉棉铃成熟度仿生类脑分类方法研究[J]. 中国农机化学报, 2024, 45(10): 177-183.
[10]	李家超, 罗斌, 周亚男, 黄硕, 侯佩臣, . 基于图像处理的水稻剑叶夹角测量[J]. 中国农机化学报, 2024, 45(10): 228-232.
[11]	何朝霞, 朱嵘涛, 徐俊英. 基于生成对抗网络的田间杂草图像超分辨率重建[J]. 中国农机化学报, 2023, 44(9): 154-160.
[12]	黄家才, 汪涛, 张铎, 唐安, 高芳征. 基于改进YOLOv4的草莓果柄叶识别与定位[J]. 中国农机化学报, 2023, 44(9): 205-213.
[13]	李航, 廖映华, 黄波. 基于改进DQN算法的茶叶采摘机械手路径规划[J]. 中国农机化学报, 2023, 44(8): 198-205.
[14]	周显沁, 韩震宇, 刘成源. 基于改进卷积神经网络与图像处理的蚕茧识别方法[J]. 中国农机化学报, 2023, 44(5): 100-106.
[15]	周鹏飞, 蒙贺伟, , , 梁荣庆, 张炳成, 坎杂, , . 基于OpenCV-Python的土壤颗粒动态休止角试验[J]. 中国农机化学报, 2023, 44(5): 214-222.