Special Issue "Novel Methods and Applications of 3D Data Processing"
Deadline for manuscript submissions: 31 January 2021.
Interests: 3D perception; human–robot interaction; intelligent robot grasping; computer graphics and virtual reality
Interests: 3D reconstruction, RGB-D computer vision, computer graphics, robotic perception, active perception
In the last decade, the appearance of cheap depth sensors on the market has allowed researchers to experiment using 3D and RGB-D cameras, developing novel perception algorithms and methods.
Ten years later, research fields such as augmented reality and robotics have been transformed by the availability of 3D information. The processing of 3D data is becoming almost as ubiquitous as 2D machine vision. Moreover, depth sensors are being successfully applied in industries, entertainment, and cultural heritage.
As 3D data is often copiously available, it needs to be interpreted, merged, and processed in a consistent way, guaranteeing accuracy and efficiency. Due to the abundance of such 3D data, issues have arisen relating to storage and visualization. Furthermore, many common methods of 2D computer vision, up to convolutional neural networks, strongly depend on input data structure and have to be reworked and adapted for 3D perception.
This Special Issue is dedicated to novel achievements in the field of 3D and RGB-D sensor data processing in any form. Topics of interest include but are not limited to the following:
- 3D perception
- 3D reconstruction
- Sensor fusion
- Sensor tracking and pose estimation
- Mapping and SLAM
- Segmentation, object detection, and recognition from 3D data
- Active perception, viewpoint optimization, and next best view planning
- Robotic 3D perception
- Processing of large scale 3D datasets
- Computational geometry for 3D data
- Deep learning and convolutional neural networks for 3D data
- Visualization of 3D information
- 3D sensors for virtual and augmented reality
- 2D/3D machine vision for industrial applications
Dr. Riccardo Monica
Prof. Jacopo Aleotti
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. Information 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 1000 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.
- 3D perception
- 3D reconstruction
- Active perception
- 3D data processing
- 3D visualization
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Title: Automatizing Bone Surface Mapping in 3D Reconstructed Tomographies
Authors: Rodrigo Schroll Astolfi; Amanda Vieira Batista; Henrique César Temoteo Ribeiro; Alexandre Leme Godoy dos Santos; José Alberto Dias Leite
Affiliation: Federal University of Ceará
Abstract: Introduction: In orthopedic surgery, having the bone in its exactly position is the most important factor for success. In comminuted fractures there is no bone edge to fit, surgeon`s ability becomes fundamental and human error is common. The way to diminish the human factor is to provide anatomically contoured implants so they can be guides for the surgeon. To make these implants it is necessary to compare the 3D bone contour in the population and find the most fitable implant. Materials and Methods: Twenty ankle tomographies were selected and 3D reconstructed for this research. We design and tested a software for semi-automatized bone superficial scanning. The software marked points on bone surface and constructed a spreadsheet with the 3D cartographic reference for each point. Results: The software was able to set the points in bone surface and the reconstruction of the original bone from the spreadsheet was successful. We were not able to reconstruct an average ankle from the averages of the points. Conclusion: Despite the transformation of the 3D bone surface in its numeric presentation was successful, we were still not able to compare individuals. We believe that volumetric paring could be a solution.