三江源大型食草动物数量无人机自动监测方法
|
摘要
应用无人机进行动物调查的研究越来越多,但是缺乏有效的自动处理图像方法,使得目视解释的工作量较大。为研究快速与准确估算三江源区域大型食草动物数量的方法,本文使用两种无人机进行7个站点的遥感影像采集。首先对无人机影像进行灰度化,使矩阵维数下降但梯度信息仍然保留,使运算速度大幅度提高;其次对影像开展高斯滤波,高斯滤波将数据进行能量转化,排除掉属于低能量部分的噪声;第三开展阈值处理得到二值化图像;采用样本中动物形态学特征开展形态运算,先用开运算消除小物体尽可能排除干扰,同时不误删牲畜,再用闭运算排除小型黑洞将同一对象连通不重复计数;最后从二值图像中检索轮廓,并返回检测到的轮廓的个数;从而自动获得主要大型食草动物物种数量与空间分布。精度检验方法为手工计数与自动计数结果比较,相对误差3.1%～6.5%,大多数情况均可达到此水平。采用计算机自动处理图像后,每张图像处理和计数的平均时间小于3 s。无人机影像的自动处理方法可为今后大规模进行藏羊、牦牛、西藏野驴和藏原羚等动物调查提供一种有效、可靠的技术途径。
There is more and more research on the application of UAV in animal surveys,but there is no effective automatic image processing method,which makes the work of visual interpretation heavy.In order to quickly and accurately count the number of large herbivores in the Source Region of Three Rivers,two UAVs were used to collect images from seven sites.Initially,the UAV image is grayed to reduce the matrix dimension and retain the gradient information,which greatly improves the operation speed.Secondly,the image is filtered by Gauss filter,which transforms the data into energy and eliminates the noise belonging to the low-energy part.Thirdly,threshold processing is carried out to get the binary image.Then the morphological characteristics of animal in the sample are used to preform morphological calculations.The open operation first eliminates the interference of small objects as much as possible without deleting livestock by mistake,and then excludes small black holes by close operation to connect the same object without repeated counting.Finally,the contour is retrieved from the binary image and the number of detected contours is returned.Thus,the number and spatial distribution of the main livestock species are automatically obtained.Comparing manual counting with automatic counting,the relative error is between 3.1% and 6.5%,which can be reached in most cases.The average time of image processing and counting is less than 3 seconds after automatic image processing by computer.The automatic processing method of UAV image can provide an effective and reliable technical way for large-scale investigation of Tibetan sheep,yaks,Tibetan wild ass and Tibetan antelope in the future.
There is more and more research on the application of UAV in animal surveys,but there is no effective automatic image processing method,which makes the work of visual interpretation heavy.In order to quickly and accurately count the number of large herbivores in the Source Region of Three Rivers,two UAVs were used to collect images from seven sites.Initially,the UAV image is grayed to reduce the matrix dimension and retain the gradient information,which greatly improves the operation speed.Secondly,the image is filtered by Gauss filter,which transforms the data into energy and eliminates the noise belonging to the low-energy part.Thirdly,threshold processing is carried out to get the binary image.Then the morphological characteristics of animal in the sample are used to preform morphological calculations.The open operation first eliminates the interference of small objects as much as possible without deleting livestock by mistake,and then excludes small black holes by close operation to connect the same object without repeated counting.Finally,the contour is retrieved from the binary image and the number of detected contours is returned.Thus,the number and spatial distribution of the main livestock species are automatically obtained.Comparing manual counting with automatic counting,the relative error is between 3.1% and 6.5%,which can be reached in most cases.The average time of image processing and counting is less than 3 seconds after automatic image processing by computer.The automatic processing method of UAV image can provide an effective and reliable technical way for large-scale investigation of Tibetan sheep,yaks,Tibetan wild ass and Tibetan antelope in the future.
引文
Bradski G.2000.The openCV library.Dr.Dobb's Journal of Software Tools,25(11):120-126.
Chretien L,Theau J,Menard P.2016.Visible and thermal infrared remote sensing for the detection of white-tailed deer using an unmanned aerial system.Wildlife Society Bulletin,40(1):181-191.
Chabot D,Bird DM.2015.Wildlife research and management methods in the 21 st century:Where do unmanned aircraft fit in? Journal of Unmanned Vehicle Systems,3:1 37-1 55.
Glasbey C A.1993.An analysis of histogram-based thresholding algorithms.CVGIP:Graphical Modes and Image Processing, 55:532-537.
Gonzalez L F,Montes G A,Puig E,Johnson S,Mengersen K,Gaston K J.2016.Unmanned aerial vehicles(UAVs)and artificial intelligence revolutionizing wildlife monitoring and conservation.Sensors,16(1):1-18.
Hodgson J C,Mott R,Baylis S M,Pham T T,Wotherspoon S,Kil-patrick A D,Segaran R R,Reid L,Teraids A,Koh L P.2018.Drones count wildlife more accurately and precisely than humans.Methods Ecol Evol, 9:1160-1167.DOI:10.1111/2041-210X.12974
Laliberte A S,Ripple W J.2003.Automated wildlife counts from remotely sensed imagery.Wildlife Society Bulletin,31(2):362-371.
Linchant J,Lhoest S,Quevauvillers S,Lejeune P,Vermeulen C,Seneki Ngabinzeke J,Belanganayi B L,Delvingt W,Bouche P.2018.UAS imagery reveals new survey opportunities for counting hippos.PLoS ONE,13(11):e0206413.DOI:10.1371/journal. pone.0206413
Li X H,Gao E H,Li B D,Zhan X J.2019.Estimating abundance of Tibetan wild ass,Tibetan gazelle and Tibetan antelope using species distribution models and distance sampling.Sci Sin Vitae,49:151-162.(in Chinese)
Luo W,Shao Q Q,Wang D L,Wang Y C.2017.An object-oriented classification method for detectdion of large wild herbivores:a case study in the Source Region of Three Rivers in Qinghai.Chinese Journal of Wildlife,38(4):561-564.(in Chinese)
Olivares-Mendez M A,Fu C H,Ludivig P,Bissyand6 T F,Kannan S,Zurad M,Annaiyan A,Voos H,Campoy P.2015.Towards an autonomous vision-based unmanned aerial system against wildlife Poachers.Sensors,15(12):31362-31391.
Qiao H J,Wang X Y,Wang W,Luo Z H,Tang K,Huang Y,Yang S N,Cao W W,Zhao X Q,Jiang J P,Hu J H.2018.From nature reserve to national park system pilot:changes of environmental coverage in the Three-River-Source National Park and implications for amphibian and reptile conservation.Biodiversity Science,26(2):202-209.(in Chinese)
Prewitt J M S,Mendelsohn M L.1966.The analysis of cell images.Annals of the New York Academy of Sciences,128:1035-1053.DOI:10.1111/j.1749-6632.1965.tb11715.x
Shao Q Q,Guo X J,Li Y Z,Wang Y C,Wang D L,Liu J Y,Fan J W,Yang F.2018.Using UAV remote sensing to analyze the population and distribution of large wild herbivores.Journal of Remote Sensing,22(3):497-507.(in Chinese)
Stéfan van der Walt,Johannes L Sch(o|¨)nberger,Juan Nunez-Iglesias,Boulogne F,Warner J D,Yager N,Gouillart E,Yu T,the scikit-image contributors.2014.Scikit-image:image processing in Python.Peer J,2:e453.DOI:10.7717/peerj.453.
Vermeulen C,Lejeune P,Lisein J,Sawadogo P,BouchéP.2013.Unmanned aerial survey of elephants.PLoS ONE,8(2):e54700.
Yang F,Shao Q Q,Guo X J,Lisein J,Tang Y Z,Li Y Z,Wang D L,Wang Y C,Fan J W.2018.Effect of large wild herbivore populations on the forage-livestock balance in the Source Region of the Yellow River.Sustainability, 10(2):340.
Zhao X Q,Zhou H K.2005.Eco-environmental degradation,vegetationregeneration and sustainable development in the headwaters of Three River on Tibetan Plateau.China Academic Journal,20(6):471-476.(in Chinese)
乔慧捷,汪晓意,王伟,罗振华,唐科,黄燕,杨胜男,曹伟伟,赵新全,江建平,胡军华.2018.从自然保护区到国家公园体制试点:三江源国家公园环境覆盖的变化及其对两栖爬行类保护的启示.生物多样性,26(2):202-209.
李欣海,郜二虎,李百度,詹祥江.2019.用物种分布模型和距离抽样估计三江源藏野驴、藏原羚和藏羚羊的数量.中国科学:生命科学,(2).
宋清洁.2018.基于无人机的大型食草动物调查研究——以中国青海省隆宝湿地国家自然保护区为例.兰州:兰州大学硕士学位论文.
陈桂琛,卢学峰,彭敏,赵以莲.2003.青海省三江源区生态系统基本特征及其保护.青海科技,(4):14-17.
邵全琴,郭兴健,李愈哲,汪阳春,王东亮,刘纪远,樊江文,杨帆.2018.无人机遥感的大型野生食草动物种群数量及分布规律研究.遥感学报,22(3):129-139.
罗巍,邵全琴,王东亮,汪阳春.2017.基于面向对象分类的大型野生食草动物识别方法——以青海三江源地区为例.野生动物学报,(4):23-26.
赵新全,周华坤.2005.三江源区生态环境退化、恢复治理及其可持续发展.中国科学院院刊,20(6):471-476.
魏军,任晓乾,栾兰.2014.最佳阈值选择的方法及在图像处理中的应用.数字技术与应用,(1):53-53.
Chretien L,Theau J,Menard P.2016.Visible and thermal infrared remote sensing for the detection of white-tailed deer using an unmanned aerial system.Wildlife Society Bulletin,40(1):181-191.
Chabot D,Bird DM.2015.Wildlife research and management methods in the 21 st century:Where do unmanned aircraft fit in? Journal of Unmanned Vehicle Systems,3:1 37-1 55.
Glasbey C A.1993.An analysis of histogram-based thresholding algorithms.CVGIP:Graphical Modes and Image Processing, 55:532-537.
Gonzalez L F,Montes G A,Puig E,Johnson S,Mengersen K,Gaston K J.2016.Unmanned aerial vehicles(UAVs)and artificial intelligence revolutionizing wildlife monitoring and conservation.Sensors,16(1):1-18.
Hodgson J C,Mott R,Baylis S M,Pham T T,Wotherspoon S,Kil-patrick A D,Segaran R R,Reid L,Teraids A,Koh L P.2018.Drones count wildlife more accurately and precisely than humans.Methods Ecol Evol, 9:1160-1167.DOI:10.1111/2041-210X.12974
Laliberte A S,Ripple W J.2003.Automated wildlife counts from remotely sensed imagery.Wildlife Society Bulletin,31(2):362-371.
Linchant J,Lhoest S,Quevauvillers S,Lejeune P,Vermeulen C,Seneki Ngabinzeke J,Belanganayi B L,Delvingt W,Bouche P.2018.UAS imagery reveals new survey opportunities for counting hippos.PLoS ONE,13(11):e0206413.DOI:10.1371/journal. pone.0206413
Li X H,Gao E H,Li B D,Zhan X J.2019.Estimating abundance of Tibetan wild ass,Tibetan gazelle and Tibetan antelope using species distribution models and distance sampling.Sci Sin Vitae,49:151-162.(in Chinese)
Luo W,Shao Q Q,Wang D L,Wang Y C.2017.An object-oriented classification method for detectdion of large wild herbivores:a case study in the Source Region of Three Rivers in Qinghai.Chinese Journal of Wildlife,38(4):561-564.(in Chinese)
Olivares-Mendez M A,Fu C H,Ludivig P,Bissyand6 T F,Kannan S,Zurad M,Annaiyan A,Voos H,Campoy P.2015.Towards an autonomous vision-based unmanned aerial system against wildlife Poachers.Sensors,15(12):31362-31391.
Qiao H J,Wang X Y,Wang W,Luo Z H,Tang K,Huang Y,Yang S N,Cao W W,Zhao X Q,Jiang J P,Hu J H.2018.From nature reserve to national park system pilot:changes of environmental coverage in the Three-River-Source National Park and implications for amphibian and reptile conservation.Biodiversity Science,26(2):202-209.(in Chinese)
Prewitt J M S,Mendelsohn M L.1966.The analysis of cell images.Annals of the New York Academy of Sciences,128:1035-1053.DOI:10.1111/j.1749-6632.1965.tb11715.x
Shao Q Q,Guo X J,Li Y Z,Wang Y C,Wang D L,Liu J Y,Fan J W,Yang F.2018.Using UAV remote sensing to analyze the population and distribution of large wild herbivores.Journal of Remote Sensing,22(3):497-507.(in Chinese)
Stéfan van der Walt,Johannes L Sch(o|¨)nberger,Juan Nunez-Iglesias,Boulogne F,Warner J D,Yager N,Gouillart E,Yu T,the scikit-image contributors.2014.Scikit-image:image processing in Python.Peer J,2:e453.DOI:10.7717/peerj.453.
Vermeulen C,Lejeune P,Lisein J,Sawadogo P,BouchéP.2013.Unmanned aerial survey of elephants.PLoS ONE,8(2):e54700.
Yang F,Shao Q Q,Guo X J,Lisein J,Tang Y Z,Li Y Z,Wang D L,Wang Y C,Fan J W.2018.Effect of large wild herbivore populations on the forage-livestock balance in the Source Region of the Yellow River.Sustainability, 10(2):340.
Zhao X Q,Zhou H K.2005.Eco-environmental degradation,vegetationregeneration and sustainable development in the headwaters of Three River on Tibetan Plateau.China Academic Journal,20(6):471-476.(in Chinese)
乔慧捷,汪晓意,王伟,罗振华,唐科,黄燕,杨胜男,曹伟伟,赵新全,江建平,胡军华.2018.从自然保护区到国家公园体制试点:三江源国家公园环境覆盖的变化及其对两栖爬行类保护的启示.生物多样性,26(2):202-209.
李欣海,郜二虎,李百度,詹祥江.2019.用物种分布模型和距离抽样估计三江源藏野驴、藏原羚和藏羚羊的数量.中国科学:生命科学,(2).
宋清洁.2018.基于无人机的大型食草动物调查研究——以中国青海省隆宝湿地国家自然保护区为例.兰州:兰州大学硕士学位论文.
陈桂琛,卢学峰,彭敏,赵以莲.2003.青海省三江源区生态系统基本特征及其保护.青海科技,(4):14-17.
邵全琴,郭兴健,李愈哲,汪阳春,王东亮,刘纪远,樊江文,杨帆.2018.无人机遥感的大型野生食草动物种群数量及分布规律研究.遥感学报,22(3):129-139.
罗巍,邵全琴,王东亮,汪阳春.2017.基于面向对象分类的大型野生食草动物识别方法——以青海三江源地区为例.野生动物学报,(4):23-26.
赵新全,周华坤.2005.三江源区生态环境退化、恢复治理及其可持续发展.中国科学院院刊,20(6):471-476.
魏军,任晓乾,栾兰.2014.最佳阈值选择的方法及在图像处理中的应用.数字技术与应用,(1):53-53.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |