AUTHOR=Tong Jingru , Zhang Guo , Kong Peijie , Rao Yu , Wei Zhengkai , Cui Hao , Guan Qing TITLE=An interpretable approach for automatic aesthetic assessment of remote sensing images JOURNAL=Frontiers in Computational Neuroscience VOLUME=16 YEAR=2022 URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2022.1077439 DOI=10.3389/fncom.2022.1077439 ISSN=1662-5188 ABSTRACT=

The increase of remote sensing images in recent decades has resulted in their use in non-scientific fields such as environmental protection, education, and art. In this situation, we need to focus on the aesthetic assessment of remote sensing, which has received little attention in research. While according to studies on human brain’s attention mechanism, certain areas of an image can trigger visual stimuli during aesthetic evaluation. Inspired by this, we used convolutional neural network (CNN), a deep learning model resembling the human neural system, for image aesthetic assessment. So we propose an interpretable approach for automatic aesthetic assessment of remote sensing images. Firstly, we created the Remote Sensing Aesthetics Dataset (RSAD). We collected remote sensing images from Google Earth, designed the four evaluation criteria of remote sensing image aesthetic quality—color harmony, light and shadow, prominent theme, and visual balance—and then labeled the samples based on expert photographers’ judgment on the four evaluation criteria. Secondly, we feed RSAD into the ResNet-18 architecture for training. Experimental results show that the proposed method can accurately identify visually pleasing remote sensing images. Finally, we provided a visual explanation of aesthetic assessment by adopting Gradient-weighted Class Activation Mapping (Grad-CAM) to highlight the important image area that influenced model’s decision. Overall, this paper is the first to propose and realize automatic aesthetic assessment of remote sensing images, contributing to the non-scientific applications of remote sensing and demonstrating the interpretability of deep-learning based image aesthetic evaluation.