On classifier learning methodologies with application to compressed remote sensing images

Galina Proskura, Oleksii Rubel, Vladimir Lukin

Abstract


Remote sensing images have found numerous applications nowadays. A traditional outcome or intermediate result of their processing is a classification map. Such maps are usually obtained from a pre-trained classifier and it is desired to have the produced classification maps as accurately as possible. The basic subject of this article is the factors determining this accuracy. The main among them are the quality of remote sensing data and classifier type, parameters and training approach. Image quality can be degraded due to several factors. One of them is distortions introduced by lossy compression that is widely used due to a huge volume of acquired data and the necessity to sufficiently decrease their size at transmission, storage and/or dissemination stages. Because of this, the main goal of this paper is to consider classification and lossy compression jointly. In particular, this means that the classifier learning can be performed for original (uncompressed, compressed in a lossless manner) images (if they are available) as well as for compressed data at hand (offered to a user for classification and further analysis). The task of this paper is to consider and compare these two options. The first one is the classifier learning for original images and further application to compressed data, where images can be compressed with different compression ratios while producing compressed data of different quality. The second option is the use of the classifier learning for compressed images, where compression parameters for training data can be approximately the same as for the images to which the classifier is applied. The main result is that the latter methodology can provide certain benefits compared to the classifier learning for original data if one has to classify compressed remote sensing data. Simulation data are obtained for a classifier based on a convolutional neural network. As images for training and verification, four real-life three-channel (visible range) Sentinel-2 remote sensing images of Kharkiv and Kharkiv region are employed that possess different complexity of the content and have four main classes. The practical recommendations are given. In conclusion, we can state that it is worth having classifiers trained for several degrees of compression and it is reasonable to compress complex structure images with special care.

Keywords


lossy compression; three-channel images; classification; neural network classifier; training data

Full Text:

PDF

References


Mielke, C., Boshce, N. K., Rogass, C., Segl, K., Gauert, C., Kaufmann, H. Potential Applications of the Sentinel-2 Multispectral Sensor and the ENMAP hyperspectral Sensor in Mineral Exploration. EARSeL eProceedings, 2014, vol. 13, no. 2, pp. 93-102. DOI: 10.12760/01-2014-2-07.

Kussul, N., Lavreniuk, M., Shelestov, A., Skakun, S. Crop inventory at regional scale in Ukraine: Developing in season and end of season crop maps with multi-temporal optical and SAR satellite imagery. European Journal of Remote Sensing, 2018, vol. 51, iss. 1, pp. 627-636. DOI: 10.1080/22797254.2018.1454265.

Zhong, P., Wang, R. Multiple-Spectral-Band CRFs for Denoising Junk Bands of Hyperspectral Imagery. IEEE Transactions on Geoscience and Remote Sensing, 2013, vol. 51, iss. 4, pp. 2269-2275. DOI: 10.1109/TGRS.2012.2209656.

Kussul, N., Lemoine, G., Gallego, F. J., Skakun, S. V., Lavreniuk, M., Shelestov, A. Yu. Parcel-Based Crop Classification in Ukraine Using Landsat-8 Data and Sentinel-1A Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, vol. 9, iss. 6, pp. 2500-2508. DOI: 10.1109/JSTARS.2016.2560141.

Sun, J., Yang, J., Zhang, C., Yun, W., Qu, J. Automatic remotely sensed image classification in a grid environment based on the maximum likelihood method. Mathematical and Computer Modelling, 2013, vol. 58, iss. 3-4, pp. 573-581. DOI: 10.1016/j.mcm.2011.10.063.

Sisodia, P. S., Tiwari, V., Kumar, A. Analysis of Supervised Maximum Likelihood Classification for remote sensing image. International Conference on Recent Advances and Innovations in Engineering (ICRAIE-2014), 2014, pp. 1-4. DOI: 10.1109/ICRAIE.2014.6909319.

Sajjad, H., Kumar, P. Future Challenges and Perspective of Remote Sensing Technology. In Applications and Challenges of Geospatial Technology, P. Kumar, M. Rani, P. Chandra, H. Sajjad, B. Chaudhary (eds.), Springer, Cham, 2019, pp. 275-277. DOI: 10.1007/978-3-319-99882-4_16.

Bioucas-Dias, J. M., Plaza, A., Camps-Valls, G., Scheunders, P., Nasrabadi, N., Chanussot, J. Hyperspectral Remote Sensing Data Analysis and Future Challenges. IEEE Geoscience and Remote Sensing Magazine, 2013, vol. 1, iss. 2, pp. 6-36. DOI: 10.1109/MGRS.2013.2244672.

Oh, H., Bilgin, A., Marcellin, M. Visually lossless JPEG 2000 for remote image browsing. Information, 2016, vol. 7, iss. 3, article no. 45. DOI: 10.3390/info7030045.

Aiazzi, B., Alparone, L., Baronti, S., Lastri, C., Santurri, L., Selva, M. Spectral distortion in lossy compression of hyperspectral imagery. IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2003). Proceedings (IEEE Cat. No. 03CH37477), 2003, pp. 1817-1819. DOI: 10.1109/IGARSS.2003.1294260.

Zabala, A., Pons, X., Díaz-Delgado, Garcia, R., Auli-Llinas, F. F., Serra-Sagrista, J. Effects of JPEG and JPEG2000 lossy compression on remote sensing image classification for mapping crops and forest areas. IEEE International Symposium on Geoscience and Remote Sensing, 2006, pp. 790-793. DOI: 10.1109/IGARSS.2006.203.

Sayood, K. Introduction to data compression. Fifth Edition. San Francisco, Morgan Kaufmann Publ., 2018. DOI: 10.1016/C2015-0-06248-7.

Hussain, A. J., Al-Fayadh, A., Radi, N. Image compression techniques: A survey in lossless and lossy algorithms. Neurocomputing, 2018, vol. 300, pp. 44-69. DOI: 10.1016/j.neucom.2018.02.094.

Liu, H., Zhang, Y., Zhang, H. et al. Deep learning-based picture-wise just noticeable distortion prediction model for image compression. IEEE Transactions on Image Processing, 2019, vol. 29, pp. 641-656. DOI: 10.1109/TIP.2019.2933743.

Li, F., Krivenko, S., Lukin, V. Two-step providing of desired quality in lossy image compression by SPIHT. Radioelectronic and computer systems, 2020, no. 2(94), pp. 22-32. DOI: 10.32620/reks.2020.2.02.

Ozah, N., Kolokolova, A. Compression improves image classification accuracy. Advances in Artificial Intelligence. Canadian AI 2019. Lecture Notes in Computer Science. Springer, Cham, 2019, vol. 11489, pp. 525-530. DOI: 10.1007/978-3-030-18305-9_55.

Doss, S., Pal, S., Akila, D. et al. Satellite image remote sensing for identifying aircraft using SPIHT and NSCT. IEEE Signal processing magazine, 2020, vol. 7, no. 5, pp. 631-634. DOI: 10.31838/jcr.07.05.130.

Li, F., Lukin, V., Proskura, G., Vasilyeva, I., Chernova, G. Image Classification Accuracy Analysis for Three-channel Remote Sensing Data. Proceedings of the conference “Intelligent Information technologies and systems of information security” IntelITSIS-2022, March 23–25, 2022, Ukraine. 15 p. Available at: http://ceur-ws.org/Vol-3156/paper39.pdf. (аccessed 10.04.2022).

Ustuner, M., Sanli, F. B. Comparison of Neural Network and ISODATA classifiers for Land Cover Assessment Using Optical Data. FIG Commission 3 Workshop 2012 Spatial Information, Informal Development, Property and Housing, 2012, pp. 1-7.

Proskura, G., Makarichev, V., Rubel, O., Lukin, V. Analysis of Classification Quality of DAT-Based Compression Images. IEEE 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), 2022, pp. 233-238. DOI: 10.1109/TCSET55632.2022.9766942.

Lukin, V., Vasilyeva, I., Krivenko, S., Li, F., Abramov, S., Rubel, O., Vozel, B., Chehdi, K., Egiazarian, K. Lossy Compression of Multichannel Remote Sensing Images with Quality Control. Remote Sensing, 2020, vol. 12, iss. 22, article no. 3840. DOI: 10.3390/rs12223840.

Vasil'eva, I. K., Lukin, V. V. Analiz metodov postklassifikatsionnoi obrabotki mnogokanal'nykh izobrazhenii [Multichannel images post-classification processing techniques analysis]. Radioelectronic and computer systems, 2019, no. 1(89), pp. 17-28. DOI: 10.32620/reks.2019.1.02.

Proskura, G., Vasilyeva, I., Li, F., Lukin, V. Classification of Compressed Multichannel Images and Its Improvement. 30th International Conference Radioelektronika 2020, April 2020, Bratislava, Slovakia, 2020, pp. 1-6. DOI: 10.1109/RADIOELEKTRONIKA49387.2020.9092371.




DOI: https://doi.org/10.32620/reks.2022.3.13

Refbacks

  • There are currently no refbacks.