摘要
针对无人机(UAV)影像农田场景地块边界提取过程中由于大幅面、高分辨率和地块尺寸大小不一致等带来的过分割问题,提出了一种基于多尺度分割的地块边界自动化提取流程。该流程采用分块分割策略,在多尺度组合聚合(MCG)分割方法框架下,通过对比实验研究并选取最佳地面采样距离和分析边界提取准确率关于尺度变化曲线选择最优分割尺度,进而实现了地块边界自动提取。以湖北省仙桃市为数据源进行的实验结果表明:面向地块边界提取的最佳地面采样距离为30 cm,最优分割尺度为[0. 2,0. 4],整场景总体地块边界提取准确率可达90%以上。该方法不仅能准确提取大幅面的农业地块边界,也可为后期农业无人机航拍规划提供参考依据。
Aiming at the over-segmentation problem caused by inconsistency of large-format, high-resolution and inconsistency of parcel size in extraction of Unmanned Aerial Vehicle( UAV) remote sensing image of farmland scene, an automatic extraction process for land boundary based on multi-scale segmentation was proposed. In this process, the block segmentation strategy was adopted under the framework of Multi-scale Combinatorial Grouping( MCG) segmentation method.The optimal ground sampling distance was selected by comparing experimental research and optimal segmentation scale was selected by analyzing the variation curve of boundary extraction accuracy with scale, therefore automatic extraction process of parcel boundaries was achieved. Experiments were conducted on the data collected from Xiantao City, Hubei Province. The experimental results show that the most suitable ground sampling distance for extracting land parcel boundary is about 30 cm and the optimal segmentation scale is [0. 2,0. 4]. The accuracy of land parcel boundary extraction can be more than 90%. In addition, the proposed method can accurately extract large-scale agricultural parcel boundary and also can provide a reference for later aerial program of agriculture UAV.
引文
[1]李平,徐新,董浩,等.利用可分性指数的极化SAR图像特征选择与多层SVM分类[J].计算机应用,2018,38(1):132-136.(LI P, XU X, DONG H, et al. Polarimetric SAR image feature selection and multi-layer SVM classification using divisibility index[J].Journal of Computer Applications, 2018, 38(1):132-136.)
[2]刘栋,童敏明,路红蕊.无人机多机协作探索煤矿灾变环境算法[J].计算机应用,2017,37(8):2401-2404.(LIU D, TONG M M, LU H R. Algorithm for exploring coal mine disaster environment by multi-UAV cooperation[J]. Journal of Computer Applications,2017, 37(8):2401-2404.)
[3]李宁,李刚,邓中亮.改进灰狼算法在土壤墒情监测预测系统中的应用[J].计算机应用,2017,37(4):1202-1206.(LI N, LI G,DENG Z L. Application of improved grey wolf optimizer algorithm in soil moisture monitoring and forecasting system[J]. Journal of Computer Applications, 2017, 37(4):1202-1206.)
[4]王利民,刘佳,杨玲波,等.基于无人机影像的农情遥感监测应用[J].农业工程学报,2013,29(18):136-145.(WANG L M, LIU J, YANG L B, et al. Applications of unmanned aerial vehicle images on agricultural remote sensing monitoring[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(18):136-145.)
[5]张正健,李爱农,边金虎,等.基于无人机影像可见光植被指数的若尔盖草地地上生物量估算研究[J].遥感技术与应用,2016,31(1):51-62.(ZHANG Z J, LI A N, BIAN J H, et al. Estimating aboveground biomass of grassland in Zoige by visible vegetation index derived from unmanned aerial vehicle image[J]. Remote Sensing Technology and Application, 2016, 31(1):51-62.)
[6]BARNES G, VOLKMANN W. High-resolution mapping with unmanned aerial systems[J]. Surveying and Land Information Science, 2015, 74(1):5-13.
[7]YANG M D, HUANG K S, KUO Y H, et al. Spatial and spectral hybrid image classification for rice lodging assessment through UAV imagery[J]. Remote Sensing, 2017, 9(6):583.
[8]LIU W, DONG J, XIANG K, et al. A sub-pixel method for estimating planting fraction of paddy rice in Northeast China[J]. Remote Sensing of Environment, 2018, 205:305-314.
[9]CROMMELINCK S, BENNETT R, GERKE M, et al. Review of automatic feature extraction from high-resolution optical sensor data for UAV-based cadastral mapping[J]. Remote Sensing, 2016, 8(8):689.
[10]LUO X, BENNETT R M, KOEVA M, et al. Investigating semiautomated cadastral boundaries extraction from airborne laser scanned data[J]. Land, 2017, 6(3):60.
[11]张超,乔敏,刘哲,等.基于无人机和卫星遥感影像的制种玉米田识别纹理特征尺度优选[J].农业工程学报,2017,33(17):98-104.(ZHANG C, QIAO M, LIU Z, et. al. Texture scale analysis and identification of seed maize fields based on UAV and satellite remote sensing images[J]. Transactions of the Chinese Societyof Agricultural Engineering, 2017, 33(17):98-104.)
[12]BRUZZONE L, CARLIN L. A multilevel context-based system for classification of very high spatial resolution images[J]. IEEE Transactions on Geoscience&Remote Sensing, 2006, 44(9):2587-2600.
[13]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.(PANG X H, ZHU W Q, PAN Y Z, et al. Research on cultivated land parcel extraction based on high-resolution remote sensing image[J].Science of Surveying and Mapping, 2009, 34(1):48-49.)
[14]陈伊哲,汤修映,彭彦昆,等.农田地块图像分割技术研究[J].农业机械学报,2010,41(s1):253-256.(CHEN Y Z, TANG X Y, PENG Y K, et al. Image segmentation technology for field parcel[J]. Transactions of the Chinese Society for Agricultural Machinery, 2010, 41(s1):253-256.)
[15]陈杰,陈铁桥,梅小明,等.基于最优尺度选择的高分辨率遥感影像丘陵农田提取[J].农业工程学报,2014,30(5):99-107.(CHEN J, CHEN T Q, MEI X M, et al. Hilly farmland extraction from high resolution remote sensing imagery based on optimal scale selection[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(5):99-107.)
[16]张萍,王琳,游星.基于SVM分类的边缘提取算法[J].成都理工大学学报(自然科学版),2017,44(2):247-252.(ZHANG P,WANG L, YOU X. Edge extraction algorithm based on SVM classification[J]. Journal of Chengdu University of Technology(Science&Technology Edition), 2017, 44(2):247-252.)
[17]王小娟,李云伍,刘得雄,等.基于机器视觉的丘陵山区田间道路虚拟中线提取方法[J].西南大学学报(自然科学版),2018,40(4):162-169.(WANG X J, LI Y W, LIU D X, et al. A machine vision-based method for detecting virtual midline of field roads in the hilly areas[J]. Journal of Southwest University(Natural Science Edition), 2018, 40(4):162-169.)
[18]GARCIA-PEDRERO A, GONEZALO-MARTIN C, LILLOSAAVEDRA M. A machine learning approach for agricultural parcel delineation through agglomerative segmentation[J]. International Journal of Remote Sensing, 2017, 38(7):1809-1819.
[19]WASSIE Y A, KEOVE M N, BENNETT R M, et al. A procedure for semi-automated cadastral boundary feature extraction from highresolution satellite imagery[J]. Journal of Spatial Science, 2018,63(1):75-92.
[20]VETRIVEL A, GERKE M, KERLE N, et al. Segmentation of UAV-based images incorporating 3D point cloud information[J].The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015, 40(3):261.
[21]ARBELAEZ P, PONT-TUSET J, BARRON J T, et al. Multiscale combinatorial grouping[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington,DC:IEEE Computer Society, 2014:328-335.
[22]黄慧萍,吴炳方.地物大小、对象尺度、影像分辨率的关系分析[J].遥感技术与应用,2006,21(3):243-248.(HUANG H P,WU B F. Analysis to the relationship of feature size, objectsscales, image resolution[J]. Remote Sensing Technology and Application, 2006, 21(3):243-248.)
[23]LOPEZ G F, TORRES S J, SERRAN P A, et al. Early season weed mapping in sunflower using UAV technology:variability of herbicide treatment maps against weed thresholds[J]. Precision Agriculture, 2016, 17(2):183-199.
[24]王志华,孟樊,杨晓梅,等.高空间分辨率遥感影像分割尺度参数自动选择研究[J].地球信息科学学报,2016,18(5):639-648.(WANG Z H, MENG F, YANG X M, et al. Study on the automatic selection of segmentation scale parameters for high spatial resolution remote sensing images[J]. Journal of Geo-Information Science, 2016,18(5):639-648.)
[25]张吉星,程效军,郭王.一种高分辨率遥感影像最优分割尺度确定的方法[J].地矿测绘,2016,32(2):12-14.(ZHANG J X,CHENG X J, GUO W. A method of determining optimal segmentation scale of high resolution remote sensing image[J]. Surveying and Mapping of Geology and Mineral Resources, 2016, 32(2):12-14.)
[26]王宏胜,李永树,吴玺,等.结合空间分析的面向对象无人机影像土地利用分类[J].测绘工程,2018,27(2):57-61.(WANG H S, LI Y S, WU X, et al. Object-oriented land use classification from UAV imagery with spatial analysis[J]. Engineering of Surveying and Mapping, 2018,27(2):57-61.)
[27]DOLLAR P, ZITNICK C L. Fast edge detection using structured forests[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(8):1558-1570.
[28]张祖潜,廖蕾艳,叶燕平.仙桃气象条件对中稻产量的影响分析[J].农业与技术,2017,37(22):216-217.(ZHANG Z Q, LIAO L Y, YE Y P. Analysis of the influence of the weather conditions of Xiantao on the yield of middle rice[J]. Agriculture&Technology, 2017,37(22):216-217.)
[29]CROMMELINCK S, BENNETT R, GERKE M, et al. Contour detection for UAV-based cadastral mapping[J]. Remote Sensing,2017, 9(2):171.
[30]CHENG J, LI L, LUO B, et al. High-resolution remote sensing image segmentation based on improved RIU-LBP and SRM[J].EURASIP Journal on Wireless Communications&Networking,2013, 2013(1):263.