Object-oriented aquatic vegetation extracting approach based on visible vegetation indices.

doi:10.13287/j.1001-9332.201605.002

Abstract

Abstract: Using the estimation of scale parameters (ESP) image segmentation tool to determine the ideal image segmentation scale, the optimal segmented image was created by the multi-scale segmentation method. Based on the visible vegetation indices derived from mini-UAV imaging data, we chose a set of optimal vegetation indices from a series of visible vegetation indices, and built up a decision tree rule. A membership function was used to automatically classify the study area and an aquatic vegetation map was generated. The results showed the overall accuracy of image classification using the supervised classification was 53.7%, and the overall accuracy of object-oriented image analysis (OBIA) was 91.7%. Compared with pixel-based supervised classification method, the OBIA method improved significantly the image classification result and further increased the accuracy of extracting the aquatic vegetation. The Kappa value of supervised classification was 0.4, and the Kappa value based OBIA was 0.9. The experimental results demonstrated that using visible vegetation indices derived from the mini-UAV data and OBIA method extracting the aquatic vegetation developed in this study was feasible and could be applied in other physically similar areas.

JING Ran, DENG Lei, ZHAO Wen-ji, GONG Zhao-ning. Object-oriented aquatic vegetation extracting approach based on visible vegetation indices.[J]. Chinese Journal of Applied Ecology, 2016, 27(5): 1427-1436.

References

[1] Costanza R, d’Arge R, de Groot R, et al. The value of the world’s ecosystem services and natural capital. Nature, 1997, 387: 253-260
[2] Ji G-D (籍国东), Sun T-H (孙铁珩), Li S (李顺). Constructed wetland and its application for industrial wastewater treatment. Chinese Journal of Applied Ecology (应用生态学报), 2002, 13(2): 224-228 (in Chinese)
[3] Guo N (郭铌). Vegetation index and its advances. Journal of Arid Meteorology (干旱气象), 2003, 21(4): 71-75 (in Chinese)
[4] Tian Q-J (田庆久), Min X-J (闵祥军). Advances in study on vegetation indices. Advance in Earth Science (地球科学进展), 1998, 13(4): 327-333 (in Chinese)
[5] Torres-Snchez J, Lopez-Granados F, de Castro AI, et al. Configuration and specifications of an unmanned aerial vehicle (UAV) for early site specific weed Management. PLoS One, 2013, 8: e58210
[6] Rasmussen J, Nielsen J, Garcia-Ruiz F, et al. Potential uses of small unmanned aircraft systems (UAS) in weed research. Weed Research, 2013, 53: 242-248
[7] Zarco-Tejada PJ, Diaz-Varela R, Angileri V, et al. Tree height quantification using very high resolution imagery acquired from an unmanned aerial vehicle (UAV) and automatic 3D photo-reconstruction methods. European Journal of Agronomy, 2014, 55: 89-99
[8] Gatziolis D, Lienard JF, Vogs A, et al. 3D tree dimensionality assessment using photogrammetry and small unmanned aerial vehicles. PLoS One, 2015, 10: e0137765
[9] Suzuki T, Amano Y, Takiguchi J, et al. Development of low-cost and flexible vegetation monitoring system using small unmanned aerial vehicle. ICROS-SICE Internatio-nal Joint Conference 2009, Fukuoka, 2009: 4808-4812
[10] Li N (李娜), Zhou D-M (周德民), Zhao K-Y (赵魁义). Marsh classification mapping at a community scale using high-resolution imagery. Acta Ecologica Sinica (生态学报), 2011, 31(22): 6717-6726 (in Chinese)
[11] Benz UC, Hofmann P, Willhauck G, et al. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58: 239-258
[12] Gao Y, Mas JF, Maathuis BHP, et al. Comparison of pixel-based and object-oriented image classification approaches: A case study in a coal fire area, Wuda, Inner Monolia, China. International Journal of Remote Sensing, 2006, 27: 4039-4055
[13] Wu T-W (吴统文), Song L-C (宋连春), Li W-P (李伟平), et al. An overview on progress in Beijing climate center climate system model: Its development and application to climate change studies. Acta Meteorologica Sinica (气象学报), 2014, 72(1): 12-29 (in Chinese)
[14] Hartley R. Estimation of relative camera position for unca-librated cameras. Lecture Notes in Computer Science, 1992, 588: 579-587
[15] Zhang Z. A new multistage approach to motion and structure estimation: From essential parameters to Euclidean motion via fundamental matrix. Asian Conference on Computer Vision, Hong Kong, 1998: 2938-2950
[16] Zhu F (朱锋), Xiao H (肖晖), Wei Y-N (魏亚男). Summary of UAV remote sensing image mosaicking technology. Computer Engineering and Applications (计算机工程与应用), 2014, 50(15): 38-41 (in Chinese)
[17] Wang X-P (王学平). Geometric rectification and effect analysis of remote sensing image. Computer Applications and Software (计算机应用与软件), 2008, 25(9): 102-105 (in Chinese)
[18] Giltelson AA, Kaufman YJ, Stark R. Novel algorithms for remote estimation of vegetation fraction. Remote Sen-sing of Environment, 2002, 80: 76-87
[19] Wang X-Q (汪小钦), Wang M-M (王苗苗), Wang S-Q (王绍强), et al. Extraction of vegetation information from visible unmanned aerial vehicle images. Transactions of the Chinese Society of Agricultural Engineering (农业工程学报), 2015, 31(5): 152-159 (in Chinese)
[20] Wu Y-L (伍艳莲), Zhao L (赵力), Jiang H-Y (姜海燕), et al. Image segmentation method for green crops using improved mean shift. Transactions of the Chinese Society of Agricultural Engineering (农业工程学报), 2014, 30(24): 161-167 (in Chinese)
[21] Hague T, Tillett ND, Wheeler H. Automated crop and weed monitoring in widely spaced cereals. Precision Agriculture, 2006, 7: 21-32
[22] Sun G-X (孙国祥), Wang X-H (汪小旵), Yan T-T (闫婷婷), et al. Inversion method flora growth parameters based on machine vision. Transactions of the Chinese Society of Agricultural Engineering (农业工程学报), 2014, 30(20): 187-195 (in Chinese)
[23] Woebbecke DM, Meyer GE, Vonbargen K. Color indexes for weed identification under various soil, residue, and lighting conditions. Transactions of the American Society of Agricultural Engineers, 1995, 38: 259-269
[24] Guijarro M, Pajares G, Riomoros I. Automatic segmentation of relevant textures in agricultural images. Computers and Electronics in Agriculture, 2011, 75: 75-83
[25] Guerrero JM, Pajares G, Montalvo M. Support vector machines for crop/weeds identification in maize fields. Expert Systems with Applications, 2012, 39: 11149-11155
[26] Liu H-Q (刘慧琴), Wu P-H (吴鹏海), Shen H-F (沈焕锋), et al. A spatio-temporal information fusion method based on non-local means filter. Geography and Geo-Information-Science (地理与地理信息科学), 2015, 31(4): 27-32 (in Chinese)
[27] Jia K (贾坤), Li Q-Z (李强子), Tian Y-C (田亦陈), et al. A review of classification methods of remote sensing imagery. Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2011, 31(10): 2618-2623 (in Chinese)
[28] Cao Y (曹宇), Mo L-J (莫利江), Li Y (李艳), et al. Wetland landscape ecological classification: Research progress. Chinese Journal of Applied Ecology (应用生态学报), 2009, 20(12): 3084-3092 (in Chinese)
[29] Qi L (齐腊), Zhao C-J (赵春江), Li C-J (李存军), et al. Accuracy of winter wheat identification based on multi-temporal CBERS-02 images. Chinese Journal of Applied Ecology (应用生态学报), 2008, 19(10): 2201-2208 (in Chinese)
[30] You X-Q (游晓黔), Nie A-H (聂爱华), Zhong B (仲波). A multi-layers urban extraction method combining object-oriented classification for the arid and semi-arid region. Remote Sensing Technology and Application (遥感技术与应用), 2015, 30(1): 123-128 (in Chinese)
[31] Cui Y-J (崔一娇), Zhu L (朱琳), Zhao L-J (赵丽娟). Abstraction and analysis of vegetation information based on object-oriented and spectra features. Acta Ecologica Sinica (生态学报), 2013, 33(3): 867-875 (in Chinese)
[32] Dragut L, Csillik O, Eisank C, et al. Automated para-meterization for multi-scale image segmentation on multiple layers. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 88: 119-127
[33] Li Q (李秦), Gao X-Z (高锡章), Zhang T (张涛), et al. Optimal segmentation scale selection and evaluation for multi-layer image recognition and classification. Journal of Geo-information Science (地球信息科学学报), 2011, 13(3): 409-417 (in Chinese)
[34] Zhang Z-J (张正健), Li A-N (李爱农), Lei G-B (雷光斌), et al. Change detection of remote sensing images based on multiscale segmentation and decision tree algorithm over mountainous area: A case study in Panxi region, Sichuan Province. Acta Ecologica Sinica (生态学报), 2014, 34(24): 7222-7232 (in Chinese)
[35] Peng H-T (彭海涛), Ke C-Q (柯长青). Study on object-oriented remote sensing image classification based on multi-levels segmentation. Remote Sensing Technology and Application (遥感技术与应用), 2010, 25(1): 149-154 (in Chinese)
[36] Cao B (曹宝), Qin Q-M (秦其明), Ma H-J (马海建), et al. Application of object-oriented approach to SPOT5 image classification: A case study in Haidian District, Beijing City. Geography and Geo-information Science (地理与地理信息科学), 2006, 22(2): 46-54 (in Chinese)