Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4
2.4
Journals
Mathematics
Special Issues
Computer Vision and Graphics: Mathematical and Statistical Perspectives
share announcement

Computer Vision and Graphics: Mathematical and Statistical Perspectives

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: closed (30 November 2023) | Viewed by 5117

Special Issue Editors

Prof. Dr. Cairong Zhao

E-Mail Website
Guest Editor
College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China
Interests: computer vision; pattern recognition; visual surveillance; face recognition; uncertainty analysis
Prof. Dr. Wankou Yang

E-Mail Website
Guest Editor
School of Automation, Southeast University, Nanjing 210096, China
Interests: pattern recognition; computer vision
Dr. Can Gao

E-Mail Website
Guest Editor
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
Interests: machine learning; pattern recognition; computer vision

Special Issue Information

Dear Colleagues,

Computer vision uses computational techniques to mimic human vision and to explore challenging tasks, such as image recognition, object detection, integrative scene understanding, etc. Computer graphics involves the generation, rendering, and utilization of 2D/3D representations and modeling, which can be applied to scientific visualization, AR/VR, computer games, and so on. Computer vision and graphics have a natural synergy with many other fields, including 3D reconstruction and human–computer interaction.

Mathematical and statistical theories, methods, and models play an important role in computer vision and graphics. In recent years, some new research fields, such as intelligent transportation and the metaverse, that are tightly related to computer vision and graphics have moved forward rapidly. As a consequence, new challenges are emerging. That is, how to understand newly proposed computer vision and graphic models from mathematical and statistical perspectives. For example, deep learning is one of most popular approaches in computer vision. Up to now, its learning scheme is not very clear, and it is still a black box method in mathematical nature. Additionally, in the AR/VR field, how to use mathematical and statistical tools to effectively integrate intelligent actions in the virtual world is an open problem. In addition, we still do not have good ideas on how to build the bridge between computer vision and computer graphics from mathematical and statistical perspectives.

This Special Issue serves as a forum for researchers all over the world to share their works and recent advances in computer vision and graphics braced by mathematical and statistical theories, methods, and models. It is expected to promote the development of computer vision and graphics in the new intelligent and virtual era.

The Special Issue seeks original contributions that address the challenges in computer vision and graphics from novel and deep mathematical and statistical perspectives. Articles with novel ideas, datasets, and comprehensive literature reviews are all welcome for submission. Related topics include, but are not limited to, the following:

  • Object detection and recognition;
  • Data augmentation;
  • Face detection and recognition;
  • Person re-identification;
  • Pedestrian detection;
  • Human pose estimation;
  • X-ray security image analysis;
  • Three-dimensional object detection and recognition;
  • Emerging vision and multimedia tasks;
  • Scene understanding;
  • Computer-aided geometric design;
  • AR/VR;
  • Three-dimensional reconstruction and modeling;
  • Computer games;
  • Scientific visualization;
  • Anomaly detection.

Prof. Dr. Cairong Zhao
Prof. Dr. Wankou Yang
Dr. Can Gao
Guest Editors

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. Mathematics 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.

Keywords

  • computer vision
  • face detection and recognition
  • person identification
  • pedestrian detection
  • image analysis
  • scene understanding
  • computer-aided geometric design
  • 3D reconstruction
  • computer games
  • AR/VR

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 7630 KiB  
Article
Optimal Coherent Point Selection for 3D Quality Inspection from Silhouette-Based Reconstructions
by Javier Pérez Soler, Jose-Luis Guardiola, Alberto Perez Jimenez, Pau Garrigues Carbó, Nicolás García Sastre and Juan-Carlos Perez-Cortes
Mathematics 2023, 11(21), 4419; https://doi.org/10.3390/math11214419 - 25 Oct 2023
Viewed by 855
Abstract
3D Geometric quality inspection involves assessing and comparing a reconstructed object to a predefined reference model or design that defines its expected volume. Achieving precise 3D object geometry reconstruction from multiple views can be challenging. In this research, we propose a camera-coherent point [...] Read more.
3D Geometric quality inspection involves assessing and comparing a reconstructed object to a predefined reference model or design that defines its expected volume. Achieving precise 3D object geometry reconstruction from multiple views can be challenging. In this research, we propose a camera-coherent point selection method to measure differences with the reference. The result is a point cloud extracted from the reconstruction that represents the best-case scenario, ensuring that any deviations from the reference are represented as seen from the cameras. This algorithm has been tested in both simulated and real conditions, reducing reconstruction errors by up to one fifth compared to traditional 3D reconstruction methodologies. Furthermore, this strategy assures that any existing difference with its reference really exists and it is a best-case scenario. It offers a fast and robust pipeline for comprehensive 3D geometric quality assurance, contributing significantly to advancements in the field of 3D object inspection. Full article
(This article belongs to the Special Issue Computer Vision and Graphics: Mathematical and Statistical Perspectives)
►▼ Show Figures

Figure 1

14 pages, 2215 KiB  
Article
Anti-Recompression Video Watermarking Algorithm Based on H.264/AVC
by Di Fan, Huiyuan Zhao, Changying Zhang, Hongyun Liu and Xiaoming Wang
Mathematics 2023, 11(13), 2913; https://doi.org/10.3390/math11132913 - 29 Jun 2023
Viewed by 831
Abstract
The problem of information security and copyright protection of video is becoming increasingly prominent. The current video watermarking algorithm does not have strong anti-compression, which has a significant impact on the visual effect of video. To solve this problem, this paper proposes a [...] Read more.
The problem of information security and copyright protection of video is becoming increasingly prominent. The current video watermarking algorithm does not have strong anti-compression, which has a significant impact on the visual effect of video. To solve this problem, this paper proposes a video watermarking algorithm based on H.264/AVC. The algorithm combines the non-zero quantization coefficient and the energy factor to select the appropriate chroma subblock, and then an optimized modulation is designed to embed the watermark into its DCT quantization coefficients in order to minimize the number of modifications of the subblocks. The invisibility and robustness experiments of the algorithm are conducted in the paper, and the Structural Similarity Indexes are above 0.99, and the False Bit Rates are all below 0.03. The results show that the algorithm has good invisibility, anti-compression performance and obvious advantages compared with other similar methods. Full article
(This article belongs to the Special Issue Computer Vision and Graphics: Mathematical and Statistical Perspectives)
►▼ Show Figures

Figure 1

26 pages, 15980 KiB  
Article
Research on Multi-Objective Optimal Scheduling for Power Battery Reverse Supply Chain
by Kangye Tan, Yihui Tian, Fang Xu and Chunsheng Li
Mathematics 2023, 11(4), 901; https://doi.org/10.3390/math11040901 - 10 Feb 2023
Cited by 4 | Viewed by 2943
Abstract
In the context of carbon neutralization, the electric vehicle and energy storage market is growing rapidly. As a result, battery recycling is an important work with the consideration of the advent of battery retirement and resource constraints, environmental factors, resource regional constraints, and [...] Read more.
In the context of carbon neutralization, the electric vehicle and energy storage market is growing rapidly. As a result, battery recycling is an important work with the consideration of the advent of battery retirement and resource constraints, environmental factors, resource regional constraints, and price factors. Based on the theoretical research of intelligent algorithm and mathematical models, an integer programming model of urban power battery reverse supply chain scheduling was established with the goal of the highest customer satisfaction and the least total cost of logistics and distribution, to study the influence of the resources and operation status of a built city recycling center and dismantling center on the power battery reverse supply chain. The model includes vehicle load, customer demand point satisfaction range, and service capacity constraints. This study collected regional image data, conducted image analysis, and further designed an improved Non-dominated Sorting Genetic Algorithm-II (NSGA-II) optimization algorithm suitable to solve the global optimization problem by introducing the improvement strategy of convergence rate, particle search, and the traditional elite individual retention. The results verified the practicability of the model, the global optimization ability of the algorithm to solve the problem, and the operation speed through comparing the results obtained from the basic algorithm. A reasonable comprehensive solution for the location and path optimization of the urban recycling center was also obtained. Multi-objective optimization was carried out in vehicle scheduling, facility construction, and customer satisfaction construction. The basic algorithm and integrated optimization software were compared. We found that the model and the scheme provided by the algorithm can significantly reduce the operation cost of the enterprise. This research provided new insights for enterprises to effectively utilize resources and optimize the reverse supply chain scheduling of an urban power battery. Full article
(This article belongs to the Special Issue Computer Vision and Graphics: Mathematical and Statistical Perspectives)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop