Application of Prior Knowledge-Driven Neural Networks for Remote Sensing Image Processing

Dear Colleagues,

Deep learning has developed rapidly in recent years. With the great improvement of computing power, many ideas of deep learning have been realized. However, deep learning has a disadvantage: it requires a large number of samples to train in order to achieve better generalization. But for many applications, it is not easy to obtain sufficient and high-quality data to model such problems. Furthermore, because many of the models we have established lack common sense, they do not have the knowledge of the human world, so they are easily attacked. Compared with machines, humans rely on prior knowledge of the target (such as visual information, context layout, etc.), and can easily and efficiently find the target object in an unknown dynamic environment. In order to solve these problems, additional prior knowledge is incorporated into the training process of the model. Prior knowledge plays a role in guiding and constraining the learning process of the model. By incorporating prior knowledge into the model, we can learn and understand the data more effectively and improve the performance and generalization ability of the model. The aim of this topic is to provide high-quality, up-to-date approaches to process remote sensing images. The key point is to develop efficient remote sensing image processing technology based on prior knowledge-driven neural networks. Articles may address, but are not limited to, the following topics:

1. Deep learning based on prior knowledge-driven neural networks;
2. Image classification based on prior knowledge-driven neural networks;
3. Target detection based on prior knowledge-driven neural networks;
4. Prior knowledge-driven neural networks for environmental monitoring;
5. Prior knowledge-driven deep learning networks for image recovery;
6. Intelligent navigation based on prior knowledge-driven neural networks;
7. Remote sensing image registration based on prior knowledge-driven neural networks;
8. Intelligent image segmentation based on prior knowledge-driven neural networks;
9. Intelligent target positioning and precise guidance.

Prof. Dr. Hu Zhu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• remote sensing image processing
• deep learning
• image classification