Recent satellite and remote sensing innovations have led to an eruption in the amount and variety of geospatial ice data available to the public, permitting in-depth study of high-definition ice imagery and digital elevation models (DEMs) for the goal of safe maritime navigation and climate monitoring. Few researchers have investigated texture in optical imagery as a predictive measure of Arctic sea ice thickness due to its cloud pollution, uniformity, and lack of distinct features that make it incompatible with standard feature descriptors. Thus, this paper implements three suitable ice texture metrics on 1640 Arctic sea ice image patches, namely (1) variance pooling, (2) gray-level co-occurrence matrices (GLCMs), and (3) textons, to assess the feasibly of a texture-based ice thickness regression model. Results indicate that of all texture metrics studied, only one GLCM statistic, namely homogeneity, bore any correlation (0.15) to ice freeboard.

Researchers have shown that the predictions of a deep neural network (DNN) for an image set can be severely distorted by one single image-agnostic perturbation, or universal perturbation, usually with an empirically fixed threshold in the spatial domain to restrict its perceivability. However, current universal perturbations have limited attack ability, and more importantly, limiting the perturbation's norm in the spatial domain may not be a suitable way to restrict the perceptibility of universal adversarial perturbations. Besides, the effects of such attacks on DNN-based texture recognition have yet to be explored. Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of learning-based image compression systems targeting both humans and machines. Also, the learning-based compressed-domain representations can be utilized to perform computer vision tasks directly in the compressed domain. In the context of universal attacks, a novel method is proposed to compute more effective universal perturbations via enhanced projected gradient descent on targeted classifiers. The perturbation is optimized by accumulating small updates on perturbed images consecutively. Performance results show that the proposed adversarial attack method can achieve much higher fooling rates as compared to state-of-the-art universal attack methods. In order to reduce the perceptibility of universal attacks without compromising their effectiveness, a frequency-tuned universal attack framework is proposed to adopt JND thresholds to guide the perceptibility of universal adversarial perturbations. The proposed frequency-tuned attack method can achieve cutting-edge quantitative results, realize a good balance between perceptibility and effectiveness in terms of fooling rate on both natural and texture image datasets. In the context of compressed-domain image recognition, a novel feature adaptation module integrating a lightweight attention model is proposed to adaptively emphasize and enhance the key features within the extracted channel-wise information. Also, an adaptation training strategy is designed to utilize the pretrained pixel-domain weights. The obtained performance results show that the proposed compressed-domain classification model can distinctly outperform the existing compressed-domain classifiers, and that it can also yield similar accuracy results with a much higher computational efficiency as compared to the decoded image trained pixel-domain models.