Classification of Forest Land Information Using Environment Satellite (HJ-1) Data

Full Text (PDF, 695KB), PP.33-40

Views: 0 Downloads: 0

Author(s)

Yanxia Wang 1,* Wanli Huang 1 Yufeng Liu 1 Hu Li 1

1. College of Geographical Sciences Fujian Normal University´╝îFuzhou, China

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2011.04.05

Received: 5 Jun. 2010 / Revised: 3 Oct. 2010 / Accepted: 20 Jan. 2011 / Published: 8 Jun. 2011

Index Terms

HJ-1A CCD1 data, image classification, different scale, land use features extraction

Abstract

For researching properties of HJ-1A CCD camera multi-spectral data in performance on extraction of land features information, this paper selected the east area of NiLeke forest farm in the western Tianshan mountain as the study area, and analyzed different accuracies for HJ-1A CCD data in identifying forest land categories using various classification methods. Firstly, maximum-likelihood classifier, Mahalanobis distance classifier, minimum distance classifier and K-means classifier were used to category land use types with two different scales on HJ-1A CCD1 and Landsat5 TM images, and analyzed separately with confusion matrix. Secondly, forest land types were distinguished by texture information and the smallest polygon size using K-NN method based on clustering algorithm. The comparing results show: at first, different classification system have different accuracy. In the first land use classification system, the accuracy of HJ-1A CCD1 images are lower than TM images, but higher in the second land use classification system. Secondly, accuracy result of maximum-likelihood classification is the best method to classify land use types. In the first land use classification system, TM total accuracy is up to 85.1% and Kappa coefficient is 0.8. In the second land use classification system, the result is up to 85.4% and kappa coefficient is 0.74.Thirdly, judgment both from the view of visual interpretation and quantitative accuracy testes, non-supervised method with K-means classifier has low qualities where many land features have characters of scattered distribution and small different spectrum information. Finally, the experiment proved that there were good vector results on HJ-1A remote sensing image in the view of visual judgment, and extracted deferent forest land by the overall accuracy 87% with the supports by those variables’ distribution knowledge, such as conifer, mixed forest, broadleaf, shrubby.

Cite This Paper

Yanxia Wang, Wanli Huang, Yufeng Liu, Hu Li, "Classification of Forest Land Information Using Environment Satellite (HJ-1) Data", International Journal of Intelligent Systems and Applications(IJISA), vol.3, no.4, pp.33-40, 2011. DOI:10.5815/ijisa.2011.04.05

Reference

[1]Wang Qiao, The development and challenge of remote sensing technology in environmental protection area [J]. Environmental Monitoring in China, 2009, 25(4): 53-54.

[2]Twenty First Century Aerospace Technology Co. Ltd, CBERS-02B image data applied evaluation [EB/OL]. http://www.cresda.com/n16/n1115/n1522/n2149/n9949.files/n11050.pdf 1-2.

[3]Yi Ling, Wang Xiao, Liu Bin. Researches on HJ-1 satellite image quality and land use classification precision. Remote sensing for land & resources, 2009, (3):74-77.

[4]Lu Yan, Lu Lixia. Application of HJ-1 multi-spectrum datum in environmental remote sensing evaluation of Liao Dong Island. Liaoning Urban and Rural Environmental Science & Technology. 2009, 29(10):45-47 (in Chinese).

[5]Zhu Haiyong. Application and evaluation of Moonlet Datum on Environment and Calamity Monitoring Forecast [J]. Arid environmental monitoring, 2010, 24(1): 39-42.

[6]Yu Xian-chuan, Cao Ting-ting, Yang Chun-ping, et al. Remote sensing image classification based on sparse component analysis [J]. Progress in Geophysics, 2009, 24(6): 2274-2279.

[7]Fu Qiang, TM image in Forest Resource Inventory Application Research [D]. Nanjing: Nanjing Forest College, 2008.

[8]Hou Zheng-yang, Study Based on TM Images on Constructive Status Quo of Coastal Shelter System along Sandy Seacoast in Shandong[D].Beijing: Beijing Forest College, 2008.

[9]Wang Liang, Study on forest landscape assessment and eco-tourism development Guichi of Anhui Province [D]. Hefei: Anhui Agricultural University, 2008.

[10]Jiang Jin, City environment geology of remote sensing information research of Lijiang city [D], Kunming: Kunming University of Science and Technology, 2008.

[11]Creation Department, HJ-1-A/B satellite introduction [EB/OL].http://www.cresda.com/n16/n1130/n1582/8384.html, 2009.

[12]Computer network information center Chinese Academy of sciences. Landsat 4-5 TM bands design [EB/OL]. http://landsat.datamirror.csdb.cn/files/l45tm.jsp.

[13]RICHARDS J A, JIA X. Remote sensing Digital Image Analysis: An Introduction [M]. Berlin: Springer, 1999.

[14]STEIN A, MEER F, GORTE B. Spatial Statistics for Remote Sensing [M].New York: Kluwer Academic Publishers, 1999.

[15]TOTH D, AACH T. Imp roved minimum distance classification with Gaussian outlier detection for industrial inspection [A ]. Italy, 11 th International Conference on Image Analysis and Processing Palermo [C], 2001:584 – 588.

[16]Zhao Yingshi. The principle and method of analysis of remote sensing application, Beijing: Scientific press, 2008.

[17]Zhou Zhiyong, Yuan Fang, Liu Haibo. Clustering Based on Clustering-Classification Model [J]. Journal of Guangxi Normal University (Natural science Edition), 2007, 25(2):127-130.

[18]Ding Kun, Long Xiaomin, Wang Yanxia. Highly accurate geometric correction of satellite images of mountain areas [J].Journal of Remote Sensing, 2010, 14(2):278-282.

[19]Wu Ruidong. Correcting Satellite Imagery for Topographic Effects [J]. Remote Sensing Information, 2005, (4):31-34.

[20]Lv Yihe, Fu Bojie. Ecological scale and scaling [J]. Acta Ecological Sinica, 2001, 21(12): 2096-2105.