TY - JOUR
T1 - Effective compression of hyperspectral imagery using an improved 3D DCT approach for land cover analysis in remote sensing applications
AU - Qiao, Tong
AU - Ren, Jinchang
AU - Sun, Meijun
AU - Zheng, Jiangbin
AU - Marshall, Stephen
PY - 2014
Y1 - 2014
N2 - Although hyperspectral imagery (HSI), which has been applied in a wide range of applications, suffers from very large volumes of data, its uncompressed representation is still preferred to avoid compression loss for accurate data analysis. In this paper, we focus on quality-assured lossy compression of HSI, where the accuracy of analysis from decoded data is taken as a key criterion to assess the efficacy of coding. An improved 3D Discrete Cosine Transform (DCT) based approach is proposed, where a Support Vector Machine (SVM) is applied to optimally determine the weighting of inter-band correlation within the quantisation matrix. In addition to the conventional quantitative metrics Signal-to-Noise Ratio (SNR) and Structural Similarity (SSIM) for performance assessment, the classification accuracy on decoded data from the SVM is adopted for quality-assured evaluation, where the Set Partitioning in Hierarchical Trees (SPIHT) method with 3D Discrete Wavelet Transform (DWT) is used for benchmarking. Results on four publically available HSI datasets have indicated that our approach outperforms SPIHT in both subjective (qualitative) and objective (quantitative) assessments for land cover analysis in remote sensing applications. Moreover, our approach is more efficient and generates much reduced degradation for subsequent data classification hence provides a more efficient and quality-assured solution in effective compression of HSI.
AB - Although hyperspectral imagery (HSI), which has been applied in a wide range of applications, suffers from very large volumes of data, its uncompressed representation is still preferred to avoid compression loss for accurate data analysis. In this paper, we focus on quality-assured lossy compression of HSI, where the accuracy of analysis from decoded data is taken as a key criterion to assess the efficacy of coding. An improved 3D Discrete Cosine Transform (DCT) based approach is proposed, where a Support Vector Machine (SVM) is applied to optimally determine the weighting of inter-band correlation within the quantisation matrix. In addition to the conventional quantitative metrics Signal-to-Noise Ratio (SNR) and Structural Similarity (SSIM) for performance assessment, the classification accuracy on decoded data from the SVM is adopted for quality-assured evaluation, where the Set Partitioning in Hierarchical Trees (SPIHT) method with 3D Discrete Wavelet Transform (DWT) is used for benchmarking. Results on four publically available HSI datasets have indicated that our approach outperforms SPIHT in both subjective (qualitative) and objective (quantitative) assessments for land cover analysis in remote sensing applications. Moreover, our approach is more efficient and generates much reduced degradation for subsequent data classification hence provides a more efficient and quality-assured solution in effective compression of HSI.
KW - hyperspectral imaging
KW - coding and compression
KW - 3D DCT
KW - support vector machine (SVM)
KW - remote sensing
UR - http://www.tandfonline.com/doi/full/10.1080/01431161.2014.968682
U2 - 10.1080/01431161.2014.968682
DO - 10.1080/01431161.2014.968682
M3 - Article
VL - 35
SP - 7316
EP - 7337
JO - International Journal of Remote Sensing
JF - International Journal of Remote Sensing
SN - 0143-1161
IS - 20
ER -