[1]林志玮,丁启禄,涂伟豪,等.基于多元HoG及无人机航拍图像的植被类型识别[J].森林与环境学报,2018,38(04):444-450.[doi:10.13324/j.cnki.jfcf.2018.04.010]
 LIN Zhiwei,DING Qilu,TU Weihao,et al.Vegetation type recognition based on multivariate HoG and aerial image captured by UAV[J].,2018,38(04):444-450.[doi:10.13324/j.cnki.jfcf.2018.04.010]
点击复制

基于多元HoG及无人机航拍图像的植被类型识别()
分享到:

《森林与环境学报》[ISSN:2096-0018/CN:35-1327/S]

卷:
38
期数:
2018年04期
页码:
444-450
栏目:
出版日期:
2018-10-15

文章信息/Info

Title:
Vegetation type recognition based on multivariate HoG and aerial image captured by UAV
作者:
林志玮12 丁启禄1 涂伟豪1 林金石3 刘金福14 黄炎和3
1. 福建农林大学计算机与信息学院, 福建 福州 350002;
2. 福建农林大学林学院, 福建 福州 350002;
3. 福建农林大学资源与环境学院, 福建 福州 350002;
4. 福建省高校生态与资源统计重点实验室, 福建 福州 350002
Author(s):
LIN Zhiwei12 DING Qilu1 TU Weihao1 LIN Jinshi3 LIU Jinfu14 HUANG Yanhe3
1. College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China;
2. College of Forestry, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China;
3. College of Resource and Environment, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China;
4. Key Laboratory for Ecology and Resource Statistics of Fujian Province, Fuzhou, Fujian 350002, China
关键词:
无人机航拍影像光学图像颜色信息植被类型识别
Keywords:
unmanned aerial vehicleaerial photographyoptical imagecolor informationvegetation type recognition
分类号:
S719
DOI:
10.13324/j.cnki.jfcf.2018.04.010
摘要:
使用无人机进行低空航拍,快速取得大范围的植被图像,结合多元HoG特征进行植被类型识别。首先,利用Gabor滤波器提取图像的纹理信息,HSV和Lab颜色空间转化提取图像的颜色信息。其次,将图像分割为N个单元格(cell),基于纹理与颜色信息计算每个单元格的方向梯度直方图(HoG)特征,形成多元HoG特征。最后,以单元格为分类单位,结合随机森林机器学习算法,建立植被类型识别模型。以福建省安溪县山区为研究区域,结果表明:利用无人机低空航拍的光学影像结合多元HoG特征进行植被类型识别是可行的;对于植被与非植被识别,其最高分类正确率达到96.04%;20 m航拍下,植被类型识别率最高,为82.44%,随着航拍高度的升高,模型识别效果呈现下降趋势。进一步采集福建省长汀县山区的植被航拍影像为测试数据,证明模型对于不同地区植被类型识别的稳定性,其识别精度最高可达73.31%,正确率无显著差异。本研究采用无人机载光学相机获取植被光学图像数据,数据获取方便且所需费用较低;提出的植被类型识别模型具有较高的精度;对于不同地区的植被类型识别具有较好的稳健性,可方便应用于野外森林树种监控与管理。根据不同高度模型识别结果,航拍高度不宜过高,航拍高度以20 m为宜。
Abstract:
The paper used the unmanned aerial vehicle (UAV) which can quickly obtain a wide range of vegetation images to capture the low-altitude aerial photography and associated with the multivariate HoG features to recognize vegetation types. Firstly, the texture information of the image were extracted by Gabor filter and using HSV and Lab color space transform to extract the color information. Next, the image were divided into N cells, then computing the gradient of histogram of each cell based on the texture and color information to form the multivariate HoG features. Finally, taking the cell as the classification unit, combining the random forest machine learning algorithm, vegetation types recognition model were established. Taking the Anxi County in Fujian Province as the test area, the results showed that it was feasible to identify the vegetation types by using the optical image of low-altitude aerial photography; the highest recognition accuracy in recognizing vegetation and non-vegetation was 96.04%; the recognition accuracy rate was 82.44% in recognizing vegetation types at 20 m and decreased with the height increase. Moreover, the vegetation images of aerial photography were further collected, which was captured at the Changting County of Fujian Province, as another data to prove the robustness of the model of vegetation type recognition in different areas, the highest recognition accuracy was 73.31%, the accuracy was similar compared with the result of Anxi County. In this paper, the vegetation images by using the unmanned aerial vehicle with optical camera were conveniently, econmically obtained; the proposed vegetation type recognition model can be easily applied to the field vegetation type monitoring and management as the high precision and its robustness in various regions. In addition, according to the recognition result at various aerial height, the proposed aerial height should not be too high, 20 m as the reference height of aerial photography was suitable.

参考文献/References:

[1] 梁尧钦, 曾辉. 高光谱遥感在植被特征识别研究中的应用[J]. 世界林业研究, 2009, 22(1):41-47.
[2] WANG K, FRANKLIN S E, GUO X L, et al. Remote sensing of ecology, biodiversity and conservation: a review from the perspective of remote sensing specialists[J]. Sensors, 2010, 10(11): 9 647-9 667.
[3] SHANG X, CHISHOLM L A. Classification of Australian native forest species using hyperspectral remote sensing and machine-learning classification algorithms[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 2 481-2 489.
[4] BOSCHETTI M, BOSCHETTI L, OLIVERI S, et al. Tree species mapping with airborne hyper-spectral MIVIS data: the Ticino Park study case[J]. International Journal of Remote Sensing, 2007, 28(6): 1 251-1 261.
[5] FASSNACHT F E, NEUMANN C, FÖRSTER M, et al. Comparison of feature reduction algorithms for classifying tree species with hyperspectral data on three central European test sites[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 2 547-2 561.
[6] FASSNACHT F E, LATIFI H, STEREN'CZAK K, et al. Review of studies on tree species classification from remotely sensed data[J]. Remote Sensing of Environment, 2016, 186: 64-87.
[7] 林丽群, 汪正祥, 雷耘等. 神农架川金丝猴栖息地优势乔木树种遥感识别及其分布特征[J]. 生态学报, 2017, 37(19): 6 534-6 543.
[8] 魏晶昱, 毛学刚, 方本煜, 等. 基于Landsat 8 OLI辅助的亚米级遥感影像树种识别[J]. 北京林业大学学报, 2016, 38(11): 23-33.
[9] SASAKI T, IMANISHI J, IOKI K, et al. Object-based classification of land cover and tree species by integrating airborne LiDAR and high spatial resolution imagery data[J]. Landscape and Ecological Engineering, 2012, 8(2): 157-171.
[10] ADELABU S, MUTANGA O, ADAM E, et al. Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image[J]. Journal of Applied Remote Sensing, 2013, 7(1): 073480.
[11] ZHANG K W, HU B X. Individual urban tree species classification using very high spatial resolution airborne multi-spectral imagery using longitudinal profiles[J]. Remote Sensing, 2012, 4(6): 1 741-1 757.
[12] 刘怀鹏, 安慧君, 王冰, 等. 基于递归纹理特征消除的WorldView-2树种分类[J]. 北京林业大学学报, 2015, 37(8): 53-59.
[13] 游晓斌, 王蕾. 应用辅助信息提高森林分类和森林区划能力的研究[J]. 北京林业大学学报, 2003, 25(S1): 41-42.
[14] MAFANYA M, TSELE P, BOTAI J, et al. Evaluating pixel and object based image classification techniques for mapping plant invasions from UAV derived aerial imagery: Harrisia pomanensis as a case study[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 129: 1-11.
[15] RICHTER R, REU B, WIRTH C, et al. The use of airborne hyperspectral data for tree species classification in a species-rich Central European forest area[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 52: 464-474.
[16] FUNG T, MA H F Y, SIU W L, et al. Subtropical tree recognition with hyperspectral data analysis in Hong Kong[J]. Geocarto International, 2001, 16(3): 25-34.
[17] 刘丽娟, 庞勇, 范文义, 等. 机载LiDAR和高光谱融合实现温带天然林树种识别[J]. 遥感学报, 2013, 17(3): 679-695.
[18] 费运巧, 刘文萍, 骆有庆, 等. 森林病虫害监测中的无人机图像分割算法比较[J]. 计算机工程与应用, 2017, 53(8): 216-223.
[19] 雷添杰, 李长春, 何孝莹. 无人机航空遥感系统在灾害应急救援中的应用[J]. 自然灾害学报, 2011, 20(1): 178-183.
[20] 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.
[21] 陈明健, 陈志泊, 杨猛, 等. 叶片传统特征和距离矩阵与角点矩阵相结合的树种识别算法[J]. 北京林业大学学报, 2017, 39(2): 108-116.
[22] IWATA T, SAITOH T. Tree recognition based on leaf images[C]//Proceedings of 2013 SICE Annual Conference. Nagoya, Japan: IEEE, 2013: 2 489-2 494.
[23] KIM S J, KIM B W, KIM D P. Tree recognition for landscape using by combination of features of its leaf, flower and bark[C]//Proceedings of 2011 SICE Annual Conference. Tokyo, Japan: IEEE, 2011: 1 147-1 151.
[24] BERTRAND S, CERUTTI G, TOUGNE L. Bark recognition to improve leaf-based classification in didactic tree species identification[C]//Proceedings of the 12th International Conference on Computer Vision Theory and Applications. Porto, Portugal: VISAPP, 2017: 435-442.
[25] 孙伶君, 汪杭军, 祁亨年. 基于分块LBP的树种识别研究[J]. 北京林业大学学报, 2011, 33(4): 107-112.
[26] 何永涛, 郎海玲. 植被建设在黄土高原水土保持中的意义及其对策[J]. 水土保持研究, 2009, 16(4): 30-33, 38.
[27] 潘声旺, 袁馨, 雷志华, 等. 乡土植物生活型构成对川渝地区边坡植被水土保持效益的影响[J]. 生态学报, 2016, 36(15): 4 654-4 663.
[28] 中国植被编辑委员会. 中国植被[M]. 北京: 科学出版社, 1980.
[29] 滕升华, 沈怡平. 颜色空间在图像彩色化处理中的应用分析[J]. 计算机科学, 2009, 36(10): 277-279.
[30] 顾明, 郑林涛, 尤政. 基于颜色空间转换的交通图像增强算法[J]. 仪器仪表学报, 2015, 36(8): 1 901-1 907.
[31] 庞晓敏, 闵子建, 阚江明. 基于HSI和LAB颜色空间的彩色图像分割[J]. 广西大学学报(自然科学版), 2011, 36(6): 976-980.
[32] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE, 2005: 886-893.
[33] 张琳琳, 赵晓英, 原慧. 风对植物的作用及植物适应对策研究进展[J]. 地球科学进展, 2013, 28(12): 1 349-1 353.
[34] 刘南威. 自然地理学[M]. 北京: 科学出版社, 2000.

相似文献/References:

[1]樊仲谋,周成军,周新年,等.无人机航测技术在森林资源调查中的应用[J].森林与环境学报,2018,38(03):297.[doi:10.13324/j.cnki.jfcf.2018.03.007]
 FAN Zhongmou,ZHOU Chengjun,ZHOU Xinnian,et al.Application of unmanned aerial vehicle aerial survey technology in forest inventory[J].,2018,38(04):297.[doi:10.13324/j.cnki.jfcf.2018.03.007]
[2]闻馨,贾明明,李晓燕,等.基于无人机可见光影像的红树林冠层群落识别[J].森林与环境学报,2020,40(05):486.[doi:10.13324/j.cnki.jfcf.2020.05.005]
 WEN Xin,JIA Mingming,LI Xiaoyan,et al.Identification of mangrove canopy species based on visible unmanned aerial vehicle images[J].,2020,40(04):486.[doi:10.13324/j.cnki.jfcf.2020.05.005]

备注/Memo

备注/Memo:
收稿日期:2018-02-25;改回日期:2018-04-27。
基金项目:中国博士后科学基金项目(2018M632565);福建省自然科学基金项目(2016J01718);海峡博士后交流项目。
作者简介:林志玮(1981-),男,讲师,博士,从事图像处理、图形识别、机器学习等研究。Email:cwlin@fafu.edu.cn。
更新日期/Last Update: 1900-01-01