{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:10:19Z","timestamp":1775913019709,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2019,3,28]],"date-time":"2019-03-28T00:00:00Z","timestamp":1553731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61875180"],"award-info":[{"award-number":["61875180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>A multispectral image is a three-order tensor since it is a three-dimensional matrix, i.e., one spectral dimension and two spatial position dimensions. Multispectral image compression can be achieved by means of the advantages of tensor decomposition (TD), such as Nonnegative Tucker Decomposition (NTD). Unfortunately, the TD suffers from high calculation complexity and cannot be used in the on-board low-complexity case (e.g., multispectral cameras) that the hardware resources and power are limited. Here, we propose a low-complexity compression approach for multispectral images based on convolution neural networks (CNNs) with NTD. We construct a new spectral transform using CNNs, where the CNNs are able to transform the three-dimension spectral tensor from large-scale to a small-scale version. The NTD resources only allocate the small-scale three-dimension tensor to improve calculation efficiency. We obtain the optimized small-scale spectral tensor by the minimization of original and reconstructed three-dimension spectral tensor in self-learning CNNs. Then, the NTD is applied to the optimized three-dimension spectral tensor in the DCT domain to obtain the high compression performance. We experimentally confirmed the proposed method on multispectral images. Compared to the case that the new spectral tensor transform with CNNs is not applied to the original three-dimension spectral tensor at the same compression bit-rates, the reconstructed image quality could be improved. Compared with the full NTD-based method, the computation efficiency was obviously improved with only a small sacrifices of PSNR without affecting the quality of images.<\/jats:p>","DOI":"10.3390\/rs11070759","type":"journal-article","created":{"date-parts":[[2019,3,29]],"date-time":"2019-03-29T03:50:21Z","timestamp":1553831421000},"page":"759","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Multispectral Transforms Using Convolution Neural Networks for Remote Sensing Multispectral Image Compression"],"prefix":"10.3390","volume":"11","author":[{"given":"Jin","family":"Li","sequence":"first","affiliation":[{"name":"Department of Engineering, University of Cambridge, 9 JJ Thomson Avenue, Cambridge CB3 0FA, UK"}]},{"given":"Zilong","family":"Liu","sequence":"additional","affiliation":[{"name":"Optic Division, National Institute of Metrology, Beijing 100029, China"}]}],"member":"1968","published-online":{"date-parts":[[2019,3,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0034-4257(90)90074-V","article-title":"Vegetation in deserts. I. A regional measure of abundance from multispectral images","volume":"31","author":"Smith","year":"1990","journal-title":"Remote Sens. Environ."},{"key":"ref_2","first-page":"1285","article-title":"Radiometric calibration of Landsat Thematic Mapper multispectral images","volume":"55","author":"Chavez","year":"1989","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Huang, W., Liu, M., Zhang, H., and Zou, B. (2010, January 18\u201320). Fusion of satellite images in urban area: Assessing the quality of resulting images. Proceedings of the Geoinformatics of 2010 18th IEEE International Conference, Beijing, China.","DOI":"10.1109\/GEOINFORMATICS.2010.5568105"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1080\/014311600210993","article-title":"Incorporating texture into classification of forest species composition from airborne multispectral images","volume":"21","author":"Franklin","year":"2000","journal-title":"Int. J. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1190\/1.1440723","article-title":"Discrimination of hydrothermally altered and unaltered rocks in visible and near infrared multispectral images","volume":"42","author":"Rowan","year":"1977","journal-title":"Geophysics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.dsp.2013.12.001","article-title":"Compressive sensing and adaptive direct sampling in hyperspectral imaging","volume":"26","author":"Hahn","year":"2014","journal-title":"Digit. Signal Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1991","DOI":"10.1109\/LGRS.2014.2316141","article-title":"Semisupervised classification for hyperspectral imagery with transductive multiple-kernel learning","volume":"11","author":"Sun","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1016\/j.ijleo.2015.09.007","article-title":"A highly reliable and super-speed optical fiber transmission for hyper-spectral SCMOS camera","volume":"127","author":"Li","year":"2016","journal-title":"Opt. Int. J. Light Electron Opt."},{"key":"ref_9","unstructured":"Imai, F.H., and Berns, R.S. (1998, January 17\u201320). High-resolution multi-spectral image archives: A hybrid approach. Proceedings of the Color and Imaging Conference, Scottsdale, AZ, USA."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"7008","DOI":"10.1109\/TGRS.2014.2306687","article-title":"A novel spatial\u2013spectral similarity measure for dimensionality reduction and classification of hyperspectral imagery","volume":"52","author":"Pu","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"6341","DOI":"10.1109\/TGRS.2013.2296329","article-title":"A novel rate control algorithm for onboard predictive coding of multispectral and hyperspectral images","volume":"52","author":"Valsesia","year":"2014","journal-title":"Ieee Trans. Geosci. Remote Sens."},{"key":"ref_12","first-page":"1090","article-title":"Reliability of space image recorder based on NAND flash memory","volume":"20","author":"Li","year":"2012","journal-title":"Guangxue Jingmi Gongcheng (Opt. Precis. Eng.)"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2806","DOI":"10.1109\/TIP.2018.2794179","article-title":"Camera-Aware Multi-Resolution Analysis for Raw Image Sensor Data Compression","volume":"27","author":"Lee","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/JSTARS.2017.2781906","article-title":"Prediction of Compression Ratio for DCT-Based Coders With Application to Remote Sensing Images","volume":"11","author":"Zemliachenko","year":"2018","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"6539","DOI":"10.1038\/s41598-017-06834-4","article-title":"Compressive sampling based on frequency saliency for remote sensing imaging","volume":"7","author":"Li","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_16","first-page":"1700","article-title":"Application of ADV212 to the large field of view multi-spectral TDICCD space camera","volume":"32","author":"Li","year":"2012","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_17","unstructured":"Wei, Y., Zhao, Z., and Song, J. (2004, January 20\u201324). Urban building extraction from high-resolution satellite panchromatic image using clustering and edge detection. Proceedings of the 2004 IEEE International Geoscience and Remote Sensing Symposium, Anchorage, AK, USA."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1779","DOI":"10.1080\/01431160802639525","article-title":"Merging hyperspectral and panchromatic image data: Qualitative and quantitative analysis","volume":"30","author":"Cetin","year":"2009","journal-title":"Int. J. Remote Sens."},{"key":"ref_19","first-page":"459","article-title":"The use of intensity-hue-saturation transformations for merging SPOT panchromatic and multispectral image data","volume":"56","author":"Carper","year":"1990","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.neucom.2015.01.050","article-title":"High quality multi-spectral and panchromatic image fusion technologies based on Curvelet transform","volume":"159","author":"Dong","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/79.363507","article-title":"System considerations for multispectral image compression designs","volume":"12","author":"Vaughn","year":"1995","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1109\/36.841986","article-title":"Compression of multispectral remote sensing images using clustering and spectral reduction","volume":"38","author":"Kaarna","year":"2000","journal-title":"Ieee Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"022801","DOI":"10.3788\/COL201715.022801","article-title":"Efficient multi-bands image compression method for remote cameras","volume":"15","author":"Li","year":"2017","journal-title":"Chin. Opt. Lett."},{"key":"ref_24","first-page":"738735","article-title":"Multispectral image compression based on DSC combined with CCSDS-IDC","volume":"2014","author":"Li","year":"2014","journal-title":"Sci. World J."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"064203","DOI":"10.1088\/1674-1056\/22\/6\/064203","article-title":"An image compression method for space multispectral time delay and integration charge coupled device camera","volume":"22","author":"Li","year":"2013","journal-title":"Chin. Phys. B"},{"key":"ref_26","unstructured":"Markas, T., and Reif, J. (April, January 30). Multispectral image compression algorithms. Proceedings of the Data Compression of IEEE Conference, Snowbird, UT, USA."},{"key":"ref_27","first-page":"1325","article-title":"Reconstruction of multispatial, multispectral image data using spatial frequency content","volume":"46","author":"Schowengerdt","year":"1980","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_28","unstructured":"Epstein, B.R., Hingorani, R., Shapiro, J.M., and Czigler, M. (1992, January 24\u201327). Multispectral KLT-wavelet data compression for Landsat thematic mapper images. Proceedings of the 1992 Data Compression IEEE Conference, Snowbird, UT, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1016\/j.patcog.2003.10.018","article-title":"Multispectral image compression using eigenregion-based segmentation","volume":"37","author":"Chang","year":"2004","journal-title":"Pattern Recognit."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"074591","DOI":"10.1117\/1.JRS.7.074591","article-title":"Predictor analysis for onboard lossy predictive compression of multispectral and hyperspectral images","volume":"7","author":"Ricci","year":"2013","journal-title":"J. Appl. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4808","DOI":"10.1109\/TGRS.2013.2285049","article-title":"Spatial\u2013spectral classification of hyperspectral images using discriminative dictionary designed by learning vector quantization","volume":"52","author":"Wang","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Cheng, K.J., and Dill, J. (2013). Lossless to lossy compression for hyperspectral imagery based on wavelet and integer KLT transforms with 3D binary EZW. Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery of International Society for Optics and Photonics, Proceedings of the SPIE Defense, Security, and Sensing, Baltimore, MD, USA, 29 April\u20133 May 2013, SPIE.","DOI":"10.1117\/12.2016200"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.ins.2013.03.027","article-title":"Lossy-to-lossless 3D image coding through prior coefficient lookup tables","volume":"239","author":"Marcellin","year":"2013","journal-title":"Inf. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"074594","DOI":"10.1117\/1.JRS.7.074594","article-title":"Performance impact of parameter tuning on the CCSDS-123 lossless multi-and hyperspectral image compression standard","volume":"7","author":"Kiely","year":"2013","journal-title":"J. Appl. Remote Sens."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Karami, A., Yazdi, M., and Asli, A.Z. (2010, January 7\u201310). Hyperspectral image compression based on tucker decomposition and discrete cosine transform. Proceedings of the 2nd International Conference on Image Processing Theory, Tools and Applications, Paris, France.","DOI":"10.1109\/IPTA.2010.5586739"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1109\/JSTARS.2012.2189200","article-title":"Compression of hyperspectral images using discerete wavelet transform and tucker decomposition","volume":"5","author":"Karami","year":"2012","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1109\/LSP.2012.2210872","article-title":"Multi-way compressed sensing for sparse low-rank tensors","volume":"19","author":"Sidiropoulos","year":"2012","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Li, N., and Li, B. (2010, January 26\u201329). Tensor completion for on-board compression of hyperspectral images. Proceedings of the IEEE International Conference on Image Processing, Hong Kong, China.","DOI":"10.1109\/ICIP.2010.5651225"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/j.neucom.2014.06.052","article-title":"Compression of hyperspectral remote sensing images by tensor approach","volume":"147","author":"Zhang","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1515\/phys-2017-0123","article-title":"Compression of hyper-spectral images using an accelerated nonnegative tensor decomposition","volume":"15","author":"Li","year":"2017","journal-title":"Open Phys."},{"key":"ref_41","first-page":"296474","article-title":"Compression of multispectral images with comparatively few bands using posttransform Tucker decomposition","volume":"2014","author":"Li","year":"2014","journal-title":"Math. Probl. Eng."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF02289464","article-title":"Some mathematical notes on three-mode factor analysis","volume":"31","author":"Tucker","year":"1966","journal-title":"Psychometrika"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1016\/j.neucom.2010.06.031","article-title":"Extended HALS algorithm for nonnegative Tucker decomposition and its applications for multiway analysis and classification","volume":"74","author":"Phan","year":"2011","journal-title":"Neurocomputing"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Cichocki, A., Zdunek, R., Phan, A.H., and Amari, S.I. (2009). Nonnegative Matrix and Tensor Factorizations, Wiley.","DOI":"10.1002\/9780470747278"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1109\/TMM.2008.917357","article-title":"Joined spectral trees for scalable SPIHT-based multispectral image compression","volume":"10","author":"Khelifi","year":"2008","journal-title":"IEEE Trans. Multimed."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1109\/LGRS.2009.2032370","article-title":"JPEG2000 encoding of remote sensing multispectral images with no-data regions","volume":"7","year":"2010","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1109\/TGRS.2010.2071880","article-title":"Pairwise orthogonal transform for spectral image coding","volume":"49","author":"Blanes","year":"2011","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1016\/j.actaastro.2008.12.006","article-title":"Image compression systems on board satellites","volume":"64","author":"Yu","year":"2009","journal-title":"Acta Astronaut."},{"key":"ref_49","first-page":"1193","article-title":"A light-weight multispectral sensor for micro UAV\u2014Opportunities for very high resolution airborne remote sensing","volume":"37","author":"Nebiker","year":"2008","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.eja.2015.07.004","article-title":"Low-altitude, high-resolution aerial imaging systems for row and field crop phenotyping: A review","volume":"70","author":"Sankaran","year":"2015","journal-title":"Eur. J. Agron."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.sigpro.2019.01.024","article-title":"Panchromatic image compression based on improved post-transform for space optical remote sensors","volume":"159","author":"Li","year":"2019","journal-title":"Signal Process."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Xue, J., Zhao, Y., Liao, W., and Chan, J.C.W. (2019). Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction. Remote Sens., 11.","DOI":"10.3390\/rs11020193"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/7\/759\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:41:22Z","timestamp":1760186482000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/7\/759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,28]]},"references-count":52,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2019,4]]}},"alternative-id":["rs11070759"],"URL":"https:\/\/doi.org\/10.3390\/rs11070759","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,28]]}}}