Feature Extraction for Unconventional Visual Sensors or Specific Applications
Deadline for manuscript submissions: closed (15 December 2021) | Viewed by 12639
Interests: computer vision; image sensors; image sequences; mobile robots
Interests: computer vision robotics; artificial vision; 3-D object localization; recognition and modeling
Detecting, tracking, and recognizing visual characteristics are fundamental tasks in computer vision. Despite advances in computing power, pixel resolution, and frame rate, on the one hand, and the deep learning revolution, on the other, this is still a difficult problem and existing methods are still not as robust and reliable as human vision.
This is particularly true when using non-conventional sensors with different acquisition modalities or in very specific applications for which off-the-shelf approaches are not suitable. In such cases, deep learning does not necessarily improve performance due to the absence of large databases.
This Special Issue will bring together original and innovative work on visual feature extraction either in images from unconventional visual sensors, or in classical images but for very specific applications for which standard primitives and descriptors are no longer sufficiently efficient, discriminating, or precise.
Submitted papers may focus (but not exclusively) on recent advances in primitive extraction in images from multi- and hyperspectral cameras, thermal cameras, light field or plenoptic cameras, event-based cameras, rolling-shutter cameras, time-of-flight cameras, or even scanners and MRI. In the same way, the work can concern methods for extracting and matching primitives in classical images with innovations justified by a particular application context (3D reconstruction, material characterization, inspection and quality control, specific tasks in robotics, and data fusion with range sensors such as, e.g., LiDAR or MMW radar).Dr. Omar Ait Aider
Dr. Michel Dhome
Dr. Yizhen Lao
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.
- image feature extraction
- feature descriptors
- feature matching
- unconventional cameras
- object recognition
- object tracking
- 3D vision