光谱学与光谱分析 |
|
|
|
|
|
The Change Detection of High Spatial Resolution Remotely Sensed Imagery Based on OB-HMAD Algorithm and Spectral Features |
CHEN Qiang1, 2, CHEN Yun-hao1, 2*, JIANG Wei-guo1, 3 |
1. State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China 2. College of Resources Science and Technology, Beijing Normal University, Beijing 100875, China 3. Academy of Disaster Reduction and Emergency Management Ministry of Civil and Ministry of Education, Beijing Normal University, Beijing 100875, China |
|
|
Abstract The high spatial resolution remotely sensed imagery has abundant detailed information of earth surface, and the multi-temporal change detection for the high resolution remotely sensed imagery can realize the variations of geographical unit. In terms of the high spatial resolution remotely sensed imagery, the traditional remote sensing change detection algorithms have obvious defects. In this paper, learning from the object-based image analysis idea, we proposed a semi-automatic threshold selection algorithm named OB-HMAD (object-based-hybrid-MAD), on the basis of object-based image analysis and multivariate alternative detection algorithm (MAD). which used the spectral features of remotely sensed imagery into the field of object-based change detection. Additionally, OB-HMAD algorithm has been compared with other the threshold segmentation algorithms by the change detection experiment. Firstly, we obtained the image object by the multi-solution segmentation algorithm. Secondly, we got the object-based difference image object using MAD and minimum noise fraction rotation (MNF) for improving the SNR of the image object. Then, the change objects or area are classified using histogram curvature analysis (HCA) method for the semi-automatic threshold selection, which determined the threshold by calculated the maximum value of curvature of the histogram, so the HCA algorithm has better automation than other threshold segmentation algorithms. Finally, the change detection results are validated using confusion matrix with the field sample data. Worldview-2 imagery of 2012 and 2013 in case study of Beijing were used to validate the proposed OB-HMAD algorithm. The experiment results indicated that OB-HMAD algorithm which integrated the multi-channel spectral information could be effectively used in multi-temporal high resolution remotely sensed imagery change detection, and it has basically solved the “salt and pepper” problem which always exists in the pixel-based change detection, and has mitigated the impact of building shadows and geometric registration error, and has improved the overall accuracy and kappa coefficient than other change detection algorithm, but it has more undetected error. By compared with the SNR of image object, we know that the MNF transformation could effectively improve to concentrate the change information.
|
Received: 2014-04-14
Accepted: 2014-08-13
|
|
Corresponding Authors:
CHEN Yun-hao
E-mail: cyh@bnu.edu.cn
|
|
[1] CHEN Shu-peng, ZHAO Ying-shi(陈述彭, 赵英时). Remote Sensing Analysis on Geo-Science(遥感地学分析). Beijing: Surveying and Mapping Press(北京: 测绘出版社), 1990. [2] YIN Shou-jing, WU Chuan-qing, WANG Qiao, et al(殷守敬, 吴传庆, 王 桥, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2013, 33(12): 3339. [3] ZHANG Hui, WANG Jian-guo(张 辉, 王建国). Journal of Electronics & Information Technology(电子与信息学报), 2008, 30(7): 1727. [4] CHEN Yun-hao, LI Xiao-bing(陈云浩, 李晓兵). Journal of Remote Sensing(遥感学报), 2002, 6(1): 12. [5] WANG Wen-jie, ZHAO Zhong-ming, ZHU Hai-qing(王文杰, 赵忠明, 朱海青). Application Research of Computers(计算机应用研究), 2009, 26(8):. [6] LIAO Ming-sheng, ZHU Pan(廖明生, 朱 攀). Journal of Remote Sensing(遥感学报), 2000, 4(3):197. [7] Blaschke T. ISPRS Journal of Photogrammetry and Remote Sensing,2010, 65(1): 2. [8] CHEN Yun-hao, FENG Tong, SHI Pei-jun, et al(陈云浩, 冯 通, 史培军, 等). Geomatics and Information Science of Wuhan University(武汉大学学报·信息科学版),2006, 31(4): 316. [9] SUN Xiao-xia, ZHANG Ji-xian, LIU Zheng-jun(孙晓霞, 张继贤, 刘正军). Science of Surveying and Mapping(测绘科学),2006, 31(1): 62. [10] Hotelling H. Relations between Two Sets of Variates. Biometrika,1936, 28(3-4): 321. [11] ZHANG Lu(张 路). Change Detection in Remotely Sensed Imagery Using Multivariate Statistical Analysis(基于多元统计分析的遥感影像变化检测方法研究). Wuhan: Wuhan University(武汉: 武汉大学), 2004. [12] Canty M J, Nielsen A A. International Journal of Remote Sensing,2006, 27(18): 3961. [13] Mas J F. International Journal of Remote Sensing, 1999, 20(1): 139. [14] CHEN Jing, HE Chun-yang(陈 晋, 何春阳). Journal of Remote Sensing(遥感学报),2001, 5(4): 259. |
[1] |
SONG Ruo-xi1, 3, FENG Yi-ning3, CHENG Wei2, WANG Xiang-hai2, 3*. Advance in Hyperspectral Images Change Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2354-2362. |
[2] |
GAO Feng1, 2, 3, JIANG Qun-ou1, 2, 3*, XIN Zhi-ming4, XIAO Hui-jie1, 2, LÜ Ke-xin1, QIAO Zhi1. Extraction Method of Oasis Shelterbelt Systems Based on Remote-Sensing Images ——A Case Study of Dengkou County[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(12): 3896-3905. |
[3] |
HUANG Shao-dong1, XU Wei-heng1, 2, 3*, XIONG Yuan1, WU Chao1, DAI Fei1, 2, 3, XU Hai-feng1, WANG Lei-guang2, 3, KOU Wei-li1. Combining Textures and Spatial Features to Extract Tea Plantations Based on Object-Oriented Method by Using Multispectral Image[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(08): 2565-2571. |
[4] |
GONG Yi-long, YAN Li* . Building Change Detection Based on Multi-Level Rules Classification with Airborne LiDAR Data and Aerial Images [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(05): 1325-1330. |
[5] |
YAN Li, GONG Yi-long*, ZHANG Yi, DUAN Wei . Application of Optical Flow Dynamic Texture in Land Use/Cover Change Detection [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(11): 3056-3061. |
[6] |
YIN Shou-jing, WU Chuan-qing, WANG Qiao*, MA Wan-dong, ZHU Li, YAO Yan-juan, WANG Xue-lei, WU Di . Review of Change Detection Methods Using Multi-Temporal Remotely Sensed Images [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(12): 3339-3342. |
[7] |
ZHANG Fang-li, DU Shi-hong*, GUO Zhou . Extracting Municipal Solid Waste Dumps Based on High Resolution Images[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(08): 2024-2030. |
[8] |
LIU Kai1, ZHANG Li-fu1*, YANG Hang1, ZHU Hai-tao1, JIANG Hai-ling2, LI Yao1 . Hyperspectral Unstructured Background Target Detection Approach Based on Object-Oriented Analysis [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(06): 1653-1657. |
[9] |
CHEN Chao1, QIN Qi-ming1*, CHEN Li1, WANG Jin-liang1, LIU Ming-chao1, WEN Qi2 . Extraction of Bridge over Water from High-Resolution Remote Sensing Images Based on Spectral Characteristics of Ground Objects [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(03): 718-722. |
[10] |
WEI Li-fei1, WANG Hai-bo2 . Change Detection from High-Resolution Remote Sensing Image Based on MSE Model [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(03): 728-732. |
[11] |
LIU Jun1, 2, TIAN Qing-jiu1*, HUANG Yan1, DU Ling-tong1 . Dynamic Monitoring of Summer Maize Planting Information for Spatial and Temporal Variations in Huanghuaihai Plain During 2000—2010 [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2012, 32(09): 2534-2539. |
[12] |
WU Jian, PENG Dao-li* . Tree-Crown Information Extraction of Farmland Returned to Forests Using QuickBird Image Based on Object-Oriented Approach [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(09): 2533-2536. |
[13] |
TAN Yu-min1,HUAI Jian-zhu1,TANG Zhong-shi2 . An Object-Oriented Remote Sensing Image Segmentation Approach Based on Edge Detection [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(06): 1624-1627. |
[14] |
DENG Jin-song1, 2, SHI Yuan-yuan1, 2, CHEN Li-su1, 2, WANG Ke1, 2*, ZHU Jin-xia1, 2. Cotton Identification and Extraction Using Near Infrared Sensor and Object-Oriented Spectral Segmentation Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(07): 1754-1758. |
[15] |
DENG Jin-song1, LI Jun2, WANG Ke1 . Detecting Land Use Change Using PCA-Enhancement and Multi-Source Classifier from SPOT Images [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(06): 1627-1631. |
|
|
|
|