Lossy compression is widely used to decrease the size of multichannel remote sensing data. Alongside this positive effect, lossy compression may lead to a negative outcome as making worse image classification. Thus, if possible, lossy compression should be carried out carefully, controlling the quality of compressed images. In this paper, a dependence between classification accuracy of maximum likelihood and neural network classifiers applied to three-channel test and real-life images and quality of compressed images characterized by standard and visual quality metrics is studied. The following is demonstrated. First, a classification accuracy starts to decrease faster when image quality due to compression ratio increasing reaches a distortion visibility threshold. Second, the classes with a wider distribution of features start to “take pixels” from classes with narrower distributions of features. Third, a classification accuracy might depend essentially on the training methodology, i.e., whether features are determined from original data or compressed images. Finally, the drawbacks of pixel-wise classification are shown and some recommendations on how to improve classification accuracy are given.

This paper deals with providing the desired quality in the Better Portable Graphics (BPG)-based lossy compression of color and three-channel remote sensing (RS) images. Quality is described by the Mean Deviation Similarity Index (MDSI), which is proven to be one of the best metrics for characterizing compressed image quality due to its high conventional and rank-order correlation with the Mean Opinion Score (MOS) values. The MDSI properties are studied and three main areas of interest are determined. It is shown that quite different quality and compression ratios (CR) can be observed for the same values of the quality parameter Q that controls compression, depending on the compressed image complexity. To provide the desired quality, a modified two-step procedure is proposed and tested. It has a preliminary stage carried out offline (in advance). At this stage, an average rate-distortion curve (MDSI on Q) is obtained and it is available until the moment when a given image has to be compressed. Then, in the first step, an image is compressed using the starting Q determined from the average rate-distortion curve for the desired MDSI. After this, the image is decompressed and the produced MDSI is calculated. In the second step, if necessary, the parameter Q is corrected using the average rate-distortion curve, and the image is compressed with the corrected Q. Such a procedure allows a decrease in the MDSI variance by around one order after two steps compared to variance after the first step. This is important for the MDSI of approximately 0.2–0.25 corresponding to the distortion invisibility threshold. The BPG performance comparison to some other coders is performed and examples of its application to real-life RS images are presented.

A tendency to increase the number of acquired remote sensing images and to make their average size larger has been observed. To manage such data, compression is needed, and lossy compression is often preferable. Since lossy compression introduces distortions, this results in worse classification and object detection. Therefore, lossy compression must be controlled, i.e., the introduced distortions must be under a certain limit. The distortions and the limit can be characterized by different metrics (quantitative criteria). Here, we consider the case of using the HaarPSI metric, which has a very high correlation with visual quality and human attention (saliency map), for three-channel optical band images compressed by the better portable graphics (BPG) encoder, one of the best modern compression techniques. We analyze a two-step procedure of providing a desired visual quality and show its peculiarities for the modes 4:4:4, 4:2:2, and 4:2:0 of image compression. We show how the HaarPSI metric relates to other known metrics of image visual quality and thresholds of distortion visibility. It is demonstrated that the two-step procedure provides about three times better accuracy in providing the desired visual quality compared to the fixed setting of parameter Q that controls compression for the BPG encoder. The provided accuracy is close to the reachable limit determined by the integer value setting of the Q parameter. We also briefly analyze the influence of compression on the classification accuracy of real-life remote sensing data.