Special Issue "Formal Verification of Imaging Algorithms for Autonomous System"
A special issue of Journal of Imaging (ISSN 2313-433X).
Deadline for manuscript submissions: 31 January 2022.
Interests: topological data analysis; complex autonomous systems; entropy; human–machine interaction; artificial intelligence; machine learning; imaging; pattern recognition; data analysis
Interests: certification of AI; eXplainable AI; control of communication networks; cybersecurity
Imaging algorithms are being adopted at a fast pace and are being applied widely in many complex industrial applications. Their development has significantly accelerated in the last decade due to different concurrent technological advances, i.e., the development of increasingly powerful computational architectures and algorithms. Imaging techniques began as an obvious tool within autonomous systems. For instance, they are fundamental for generating the input for complex functions in autonomous-cars, i.e., self-driving, object detection, and obstacle avoidance. In addition, they are requested to enable autonomous airborne operations such as autonomous-taxi, and autonomous-landing. In other domains, such as manufacturing and maintenance, imaging algorithms are fundamental to enable human–robot cooperation and to increase human safety while improving operators’ performances. It is worth mentioning the broad application of imaging algorithms for supporting medical doctors during prognostic and diagnostic tasks, specifically of robot-assisted surgery. In general, imaging analysis has achieved unprecedented performance in different fields by relying on artificial neural networks. Despite this success, contemporary imaging algorithms still face fundamental challenges. Up to now, imaging algorithms, e.g., pattern recognition or object detection, are evaluated by means of quantitative analysis. The lack of methodology and tools for learning formal assurances of the correctness, resiliency, robustness, and generalizability of imaging algorithms is blocking the certification of these algorithms, and therefore this is slowing down their certification and commercialization in several fields. We request contributions presenting techniques (methods, tools, ideas, or even market evaluations) that will contribute to the future roadmap of formally verifiable imaging algorithms with applications in real-world domains. We welcome papers combining both analytical (formal robustness verification, scenario generation, formally verifiable training procedures, falsification, etc.) and data-driven approaches (e.g., statistical and topological analysis of artificial neural network) that would support the formal verification of imaging algorithms. Scientifically founded innovative and speculative research lines are welcome for proposal and evaluation.
Dr. Matteo Rucco
Dr. Maurizio Mongelli
Dr. Anastasia Mavridou
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 papers will be 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. Journal of Imaging is an international peer-reviewed open access monthly 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 1600 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.
- imaging algorithms
- neural network
- assurance learning
- scenario generation
- formal verification
- industry 4.0
- autonomous system
- autonomous aircraft
- autonomous car
- scenario generation
- perception system