BUSINESS Flower Species Identification And Coverage Estimation Based On Hyperspectral Remote Sensing Data Gai Yingying 1, Fan Wenjie 1, Xu Xiru 1, Zhang.

Presentation on theme: "BUSINESS Flower Species Identification And Coverage Estimation Based On Hyperspectral Remote Sensing Data Gai Yingying 1, Fan Wenjie 1, Xu Xiru 1, Zhang."— Presentation transcript:

1 BUSINESS Flower Species Identification And Coverage Estimation Based On Hyperspectral Remote Sensing Data Gai Yingying 1, Fan Wenjie 1, Xu Xiru 1, Zhang Yuanzhen 2 1. Institute of RS and GIS, Peking University, Beijing, China 2. China Meteorological Administration Training Centre, Beijing, China Email Address: fanwj@pku.edu.cn (Fan Wenjie)

2 Outline 1. Preface 2. Data 2.1 Data acquirement 2.2 Data preprocessing 3. Methodology 3.1 Flower spectral feature extraction 3.2 Mixed spectra unmixing 4. Results 5. Discussion

3 Preface Causes of grassland degradation: overgrazing excess reclamation …… Monitoring grass species and coverage accurately using hyperspectral remote sensing data makes a significant contribution to species diversity research and sustainable development of grassland ecosystem. Hyperspectral remote sensing becomes an important way of monitoring terrestrial ecosystem. Superiorities of hyperspectral remote sensing: provide information at different temporal and spatial scales high spectral resolution ……

4 Data Data acquirement Study area: Hulunbeier meadow grassland, Hulunbeier City, Inner Mongolia, China. Time: from July 1st to July 3rd, 2010 Flower species: Serratula centauroides Linn., Clematis hexapetala Pall., Artemisia frigida Willd. Sp. Pl., Galium verum Linn., Hemerocallis citrina Baroni, Lilium concolor var. pulchellum and Lilium pumilum

5 Data Data acquirement Device: ASD FieldSpec-3, with the spectral range of 350–2500 nm and the spectral resolution of 1 nm Data type: spectra of same kind flower canopies, spectra of quadrates contained flowers of single and multiple species

6 Data Data prepocessing Wavelet filtering

7 Data prepocessing Comparison of Wavelet filtering and Savitzky-Golay filtering Data Signals of high frequency were more stable dealing with wavelet filter than Savitzky-Golay filter.

8 Flower spectral feature extraction Spectral Differential --- identify Serratula centauroides Linn. and divide other flowers into three sets Methodology 1)The spectral derivatives of Serratula centauroides Linn. between purple and blue bands are below zeros; 2)The maximum derivatives of both Clematis hexapetala Pall. and Artemisia frigida Willd. Sp. Pl. in the range from 500 nm to 600 nm are much smaller than others; 3)The derivatives of Galium verum Linn. and Hemerocallis citrina Baroni reach peaks in 500-550 nm, while Lilium concolor var. pulchellum and Lilium pumilum in 550-600 nm.

9 Flower spectral feature extraction Spectral Differential --- identify Serratula centauroides Linn. and divide other flowers into three sets Methodology (1) (2) (3) (4)

10 Flower spectral feature extraction Spectral Reordering --- identify Clematis hexapetala Pall. and Artemisia frigida Willd. Sp. Pl. Methodology When spectra were reordered based on Clematis hexapetala Pall., curves of Artemisia frigida Willd. Sp. Pl. shows different fluctuation. It is the same the other way round.

11 Flower spectral feature extraction Vegetation Index --- identify the other two sets: Galium verum Linn., Hemerocallis citrina Baroni Lilium concolor var. pulchellum, Lilium pumilum. Methodology Flower speciesγ Lilium pumilum2.9407-3.7834 Lilium concolor var. pulchellum4.1446-9.0796 Flower speciesNDVIs Galium verum Linn.0.5119-0.5985 Hemerocallis citrina Baroni0.2145-0.3224

12 Mixed spectra unmixing linear spectral mixture analysis Methodology P --- measured spectra vector N --- number of end-numbers C i --- proportion of e i in pixels n --- error quadrate spectra --- mixed spectra flower spectra --- end-member spectra range of wave bands--- 400-750 nm C --- proportional vector of end-numbers E --- matrix of end-number vector Definition: mixed pixel end-member

13 Accuracy analysis of flowers identification Results Verification results showed that when the coverage of flowers was more than 10%, the accuracy of identification methods would be higher than 90%. Flower species Not-identify error /% Incorrect-identify error /% Total error/% Serratula centauroides Linn.8.330 Clematis hexapetala Pall.06.67 Artemisia frigida Willd. Sp. Pl.6.670 Galium verum Linn.5.883.038.91 Hemerocallis citrina Baroni05.88 Lilium concolor var. pulchellum000 Lilium pumilum000

14 Accuracy analysis of pixel unmixing method Results Results also showed that the linear unmixing model was an effective method for estimating the coverage of flowers in grassland with the mean error of about 4%. Flower speciesMean errorStandard deviation Serratula centauroides Linn.0.0400.065 Clematis hexapetala Pall.0.0420.034 Artemisia frigida Willd. Sp. Pl.0.0620.032 Galium verum Linn.0.0290.073 Hemerocallis citrina Baroni0.0520.037 Lilium concolor var. pulchellum0.0210.028 Lilium pumilum0.018Null Note: There are not enough data for validation of Lilium pumilum.

15 Discussion The methods studied in the paper demonstrate promising application in monitoring some herb plants during florescence. More flowers will also be distinguished with high accuracy if multi-temporal data are available. In our study, application of field measured hyperspectral data in vegetation monitoring has been broaden, but species identification using remote sensing is to some extent limited by field observation. Admittedly, what we have observed in this study is far from complete and it requires further research.

16 Discussion Grasslands need protection!

17 Email Address: fanwj@pku.edu.cn (Fan Wenjie) Institute of RS and GIS, Peking University, China