Share Email Print
cover

Proceedings Paper

Predicting apple tree leaf nitrogen content based on hyperspectral applying wavelet and wavelet packet analysis
Author(s): Yao Zhang; Lihua Zheng; Minzan Li; Xiaolei Deng; Hong Sun
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The visible and NIR spectral reflectance were measured for apple leaves by using a spectrophotometer in fruit-bearing, fruit-falling and fruit-maturing period respectively, and the nitrogen content of each sample was measured in the lab. The analysis of correlation between nitrogen content of apple tree leaves and their hyperspectral data was conducted. Then the low frequency signal and high frequency noise reduction signal were extracted by using wavelet packet decomposition algorithm. At the same time, the original spectral reflectance was denoised taking advantage of the wavelet filtering technology. And then the principal components spectra were collected after PCA (Principal Component Analysis). It was known that the model built based on noise reduction principal components spectra reached higher accuracy than the other three ones in fruit-bearing period and physiological fruit-maturing period. Their calibration R2 reached 0.9529 and 0.9501, and validation R2 reached 0.7285 and 0.7303 respectively. While in the fruit-falling period the model based on low frequency principal components spectra reached the highest accuracy, and its calibration R2 reached 0.9921 and validation R2 reached 0.6234. The results showed that it was an effective way to improve ability of predicting apple tree nitrogen content based on hyperspectral analysis by using wavelet packet algorithm.

Paper Details

Date Published: 9 November 2012
PDF: 10 pages
Proc. SPIE 8527, Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications IV, 85271A (9 November 2012); doi: 10.1117/12.977397
Show Author Affiliations
Yao Zhang, China Agricultural Univ. (China)
Lihua Zheng, China Agricultural Univ. (China)
Minzan Li, China Agricultural Univ. (China)
Xiaolei Deng, China Agricultural Univ. (China)
Hong Sun, China Agricultural Univ. (China)


Published in SPIE Proceedings Vol. 8527:
Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications IV
Allen M. Larar; Hyo-Sang Chung; Makoto Suzuki; Jian-yu Wang, Editor(s)

© SPIE. Terms of Use
Back to Top