基于混合像元分解与EM算法的中低分辨率遥感影像变化检测
|
摘要
中低分辨率遥感影像中广泛存在的混合像元极大地限制了变化检测结果的精度。基于混合像元分解技术,能够深入到像元内部,比较不同端元的组成分差异影像,然后获取亚像元级别的变化信息。如何从差异影像中确定合适的变化阈值,从而准确地判断变化是否发生,是一个难点问题。在高斯模型分布假设的情况下,采用最大期望法(expectation maximization,EM)自动提取最佳阈值,完成自适应的变化检测过程。选择了两种典型的阈值选择方法与该方法进行比较,结果证明基于EM的自适应变化检测方法可以更准确地提取变化信息,具有较好的稳健性。
The low spatial resolution images often have high temporal repetition rates, but they contain a large number of mixed pixels, which may seriously limit their capability in change detection. Pixel unmixing can produce the proportional fractions of land-covers, on which sub-pixel information can be extracted to reduce the low-spatial-resolution-problem to some extent. Therefore, the sub-pixel change detection can be proposed to overcome this issue in this paper. Firstly, the endmembers of different temporal remote sensing images are extracted; after that, the pixel unmixing process is implemented and the abundance difference image is produced through comparison with the fractional abundances. The endmember variability per pixel is considered during the process to ensure the high accuracy of derived proportional fractional difference image; in the end, an exact threshold should be determined according to the difference image. In order to avoid some false change and noises of the initial fractional difference image, a suitable threshold should be set. In the light of the intensity change values in the image are consistent with the distribution of Gauss mixture, the expectation maximization(EM) algorithm and Bayes discriminant criterion are both used to find out the best threshold of each land cover change. Once the threshold value is set, fraction changes larger than the value will be considered to be correct; other changes will be regarded as zero. The proposed method is compared with two traditional methods in both of the simulated and real experiments. The result demonstrates that our method can extract more precise changed information with high stability.
The low spatial resolution images often have high temporal repetition rates, but they contain a large number of mixed pixels, which may seriously limit their capability in change detection. Pixel unmixing can produce the proportional fractions of land-covers, on which sub-pixel information can be extracted to reduce the low-spatial-resolution-problem to some extent. Therefore, the sub-pixel change detection can be proposed to overcome this issue in this paper. Firstly, the endmembers of different temporal remote sensing images are extracted; after that, the pixel unmixing process is implemented and the abundance difference image is produced through comparison with the fractional abundances. The endmember variability per pixel is considered during the process to ensure the high accuracy of derived proportional fractional difference image; in the end, an exact threshold should be determined according to the difference image. In order to avoid some false change and noises of the initial fractional difference image, a suitable threshold should be set. In the light of the intensity change values in the image are consistent with the distribution of Gauss mixture, the expectation maximization(EM) algorithm and Bayes discriminant criterion are both used to find out the best threshold of each land cover change. Once the threshold value is set, fraction changes larger than the value will be considered to be correct; other changes will be regarded as zero. The proposed method is compared with two traditional methods in both of the simulated and real experiments. The result demonstrates that our method can extract more precise changed information with high stability.
引文
[1] Du Peijun, Liu Sicong. Change Detection from Multi-temporal Remote Sensing Images by Integrating Multiple Features [J]. Journal of Remote Sensing, 2012, 16(4): 663-677(杜培军, 柳思聪. 融合多特征的遥感影像变化检测 [J]. 遥感学报, 2012, 16 (4): 663-677)
[2] Howarth P J, Wickware G M. Procedures for Change Detection Using Landsat Digital Data [J]. International Journal of Remote Sensing, 1981, 2(3): 191-277
[3] Mas J F. Monitoring Land-Cover Changes: A Comparison of Change Detection Techniques [J]. International Journal of Remote Sensing, 1999, 20(1):139-152
[4] Chen Xue, Ma Jianwen, Dai Qin. Remote Sensing Change Detection Based on Bayesian Networks Classifications [J]. Journal of Remote Sensing, 2005, 9(6): 667-672(陈雪, 马建文, 戴芹. 基于贝叶斯网络分类的遥感影像变化检测 [J]. 遥感学报, 2005, 9(6): 667-672)
[5] Wu Chen, Du Bo, Zhang Liangpei. Hyperspectral Change Detection Based on Independent Component Analysis [J]. Journal of Remote Sensing, 2012, 16(3): 545-561(武辰, 杜博, 张良培. 基于独立成分分析的高光谱变化检测 [J]. 遥感学报, 2012, 16(3): 545-561)
[6] Li Song, An Yulun, Hua Houqiang. Automated Method Based on Change Detection for Extracting Karst Rock Desertification Information Using Remote Sensing [J]. Remote Sensing Technology and Application, 2012,27(1): 149-153(李松, 安裕伦, 华厚强. 基于遥感变化检测的石漠化信息自动提取 [J]. 遥感技术与应用, 2012,27(1): 149-153)
[7] Wei Lifei, Zhong Yanfei, Zhang Liangpei, et al. Remote Sensing Image Change Detection Based on Multi-band Information Fusion [J]. Geomatics and Information Science of Wuhan University, 2014, 39(1): 8-11(魏立飞, 钟燕飞, 张良培, 等. 多波段信息融合的遥感影像变化检测[J]. 武汉大学学报\5信息科学版,2014, 39(1): 8-11)
[8] Tong S S, Pham T L, Pham V C. Land Cover Change Analysis Using Change Vector Analysis Method in Duy Tien District, Ha Nam Province in Vietnam[C]. 7th FIG Regional Conference TS 1G-Remote Sensing for Sustainable Development, Hanoi, Vietnam, 2009
[9] Turner B L, Meyer W B, Skole D L. Global Land-Use/Land-Cover Change: Towards an Integrated Study [J]. Ambio, 1994, 23(1): 91-95
[10] Haertel V, Shimabukuro Y E, Almeida-Filho R. Fraction Images in Multitemporal Change Detection [J]. International Journal of Remote Sensing, 2004, 25(23):5 473-5 489
[11] Anderson L O, Shimabukuro Y E, Arai E. Cover: Multitemporal Fraction Images Derived from Terra MODIS Data for Analysing Land Cover Change over the Amazon Region [J]. International Journal of Remote Sensing, 2005, 26(11):2 251-2 257
[12] Lu D, Batistella M, Moran E. Multitemporal Spectral Mixture Analysis for Amazonian Land-Cover Change Detection [J]. Canadian Journal of Remote Sensing, 2004, 30(1):87-100
[13] Zhao Chunhui, Qi Bin, Wang Yulei. An Improved N-FINDR Hyperspectral Endmember Extraction Algorithm [J]. Journal of Electronics and Information Technology, 2012,34(2):500-503 (赵春晖,齐滨,王玉磊.一种改进的 N-FINDR 高光谱端元提取算法[J]. 电子与信息学报,2012,34(2):500-503)
[14] Heinz D C, Chang C. Fully Constrained Least Squares Linear Spectral Mixture Analysis Method for Material Quantification in Hyperspectral Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 39(3):529-545
[15] Yang H L, Peng J H, Xia B R,et al. An Improved EM Algorithm for Remote Sensing Classification[J]. Chinese Science Bulletin, 2013, 58(9): 1 060-1 071
[16] Wu Ke, Niu Ruiqing, Wang Yi. Change Detection of Multi-spectral Remote Sensed Images Based on PCA and EM Algorithm[J].Computer Science, 2010, 37(3): 275-282(吴柯, 牛瑞卿, 王毅. 基于PCA与EM算法的多光谱遥感影像变化检测研究 [J]. 计算机科学, 2010, 37(3): 275-282)
[17] Dian Yuanyong. Analysis of Change Detection Based on Remote Sensed Images [D]. Wuhan: Wuhan University, 2005 (佃袁勇. 基于遥感影像的变化检测研究 [D]. 武汉:武汉大学, 2005)
[18] Li Xue, Shu Ning, Wang Yan, et al. Change Detection Based on Land-Use Status Transition Analysis[J]. Geomatics and Information Science of Wuhan University, 2011, 36(8): 951-952(李雪, 舒宁, 王琰, 等. 利用土地利用状态转移分析的变化检测[J]. 武汉大学学报·信息科学版, 2011, 36(8): 951-952)
[19] Wu Wei, Shen Zhanfeng, Wu Tianjun, et al. Joint Probability Space Based Self-Adaptive Remote Sen- sing Change Detection Method [J]. Acta Geodaetica et Cartographica Sinica, 2016,45(1):74-79(吴炜,沈占锋,吴田军,等. 联合概率密度空间的遥感自适应变化检测方法[J]. 测绘学报,2016,45(1):74-79)
[2] Howarth P J, Wickware G M. Procedures for Change Detection Using Landsat Digital Data [J]. International Journal of Remote Sensing, 1981, 2(3): 191-277
[3] Mas J F. Monitoring Land-Cover Changes: A Comparison of Change Detection Techniques [J]. International Journal of Remote Sensing, 1999, 20(1):139-152
[4] Chen Xue, Ma Jianwen, Dai Qin. Remote Sensing Change Detection Based on Bayesian Networks Classifications [J]. Journal of Remote Sensing, 2005, 9(6): 667-672(陈雪, 马建文, 戴芹. 基于贝叶斯网络分类的遥感影像变化检测 [J]. 遥感学报, 2005, 9(6): 667-672)
[5] Wu Chen, Du Bo, Zhang Liangpei. Hyperspectral Change Detection Based on Independent Component Analysis [J]. Journal of Remote Sensing, 2012, 16(3): 545-561(武辰, 杜博, 张良培. 基于独立成分分析的高光谱变化检测 [J]. 遥感学报, 2012, 16(3): 545-561)
[6] Li Song, An Yulun, Hua Houqiang. Automated Method Based on Change Detection for Extracting Karst Rock Desertification Information Using Remote Sensing [J]. Remote Sensing Technology and Application, 2012,27(1): 149-153(李松, 安裕伦, 华厚强. 基于遥感变化检测的石漠化信息自动提取 [J]. 遥感技术与应用, 2012,27(1): 149-153)
[7] Wei Lifei, Zhong Yanfei, Zhang Liangpei, et al. Remote Sensing Image Change Detection Based on Multi-band Information Fusion [J]. Geomatics and Information Science of Wuhan University, 2014, 39(1): 8-11(魏立飞, 钟燕飞, 张良培, 等. 多波段信息融合的遥感影像变化检测[J]. 武汉大学学报\5信息科学版,2014, 39(1): 8-11)
[8] Tong S S, Pham T L, Pham V C. Land Cover Change Analysis Using Change Vector Analysis Method in Duy Tien District, Ha Nam Province in Vietnam[C]. 7th FIG Regional Conference TS 1G-Remote Sensing for Sustainable Development, Hanoi, Vietnam, 2009
[9] Turner B L, Meyer W B, Skole D L. Global Land-Use/Land-Cover Change: Towards an Integrated Study [J]. Ambio, 1994, 23(1): 91-95
[10] Haertel V, Shimabukuro Y E, Almeida-Filho R. Fraction Images in Multitemporal Change Detection [J]. International Journal of Remote Sensing, 2004, 25(23):5 473-5 489
[11] Anderson L O, Shimabukuro Y E, Arai E. Cover: Multitemporal Fraction Images Derived from Terra MODIS Data for Analysing Land Cover Change over the Amazon Region [J]. International Journal of Remote Sensing, 2005, 26(11):2 251-2 257
[12] Lu D, Batistella M, Moran E. Multitemporal Spectral Mixture Analysis for Amazonian Land-Cover Change Detection [J]. Canadian Journal of Remote Sensing, 2004, 30(1):87-100
[13] Zhao Chunhui, Qi Bin, Wang Yulei. An Improved N-FINDR Hyperspectral Endmember Extraction Algorithm [J]. Journal of Electronics and Information Technology, 2012,34(2):500-503 (赵春晖,齐滨,王玉磊.一种改进的 N-FINDR 高光谱端元提取算法[J]. 电子与信息学报,2012,34(2):500-503)
[14] Heinz D C, Chang C. Fully Constrained Least Squares Linear Spectral Mixture Analysis Method for Material Quantification in Hyperspectral Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 39(3):529-545
[15] Yang H L, Peng J H, Xia B R,et al. An Improved EM Algorithm for Remote Sensing Classification[J]. Chinese Science Bulletin, 2013, 58(9): 1 060-1 071
[16] Wu Ke, Niu Ruiqing, Wang Yi. Change Detection of Multi-spectral Remote Sensed Images Based on PCA and EM Algorithm[J].Computer Science, 2010, 37(3): 275-282(吴柯, 牛瑞卿, 王毅. 基于PCA与EM算法的多光谱遥感影像变化检测研究 [J]. 计算机科学, 2010, 37(3): 275-282)
[17] Dian Yuanyong. Analysis of Change Detection Based on Remote Sensed Images [D]. Wuhan: Wuhan University, 2005 (佃袁勇. 基于遥感影像的变化检测研究 [D]. 武汉:武汉大学, 2005)
[18] Li Xue, Shu Ning, Wang Yan, et al. Change Detection Based on Land-Use Status Transition Analysis[J]. Geomatics and Information Science of Wuhan University, 2011, 36(8): 951-952(李雪, 舒宁, 王琰, 等. 利用土地利用状态转移分析的变化检测[J]. 武汉大学学报·信息科学版, 2011, 36(8): 951-952)
[19] Wu Wei, Shen Zhanfeng, Wu Tianjun, et al. Joint Probability Space Based Self-Adaptive Remote Sen- sing Change Detection Method [J]. Acta Geodaetica et Cartographica Sinica, 2016,45(1):74-79(吴炜,沈占锋,吴田军,等. 联合概率密度空间的遥感自适应变化检测方法[J]. 测绘学报,2016,45(1):74-79)