Deep Learning in Video and Image Processing: Challenges, Solutions, and Future Directions

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: 15 January 2025 | Viewed by 3486

Special Issue Editors


E-Mail Website
Guest Editor
Department of Information Engineering, University of Pisa, Via Girolamo Caruso, 16, 56122 Pisa, Italy
Interests: deep learning; machine learning; video processing; image processing; Internet of Things; cybersecurity; embedded systems
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Information Engineering, University of Pisa, Via Girolamo Caruso, 16, 56122 Pisa, Italy
Interests: automotive electronics; embedded HPC (high-performance computing); enabling technologies IoT (Internet of Things)
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The Special Issue “Challenges and Solutions in Real-Time Deep Learning and Machine Learning for Video and Image Processing on Edge Platforms” focuses on advancing the integration of deep learning and machine learning (ML) techniques with video and image processing directly on edge devices. This collection of papers aims to address the unique challenges of executing computationally intensive ML algorithms in real time on resource-constrained devices, such as those with limited processing power, memory, and energy consumption. The purpose is to explore innovative solutions that enhance the efficiency, accuracy, and reliability of ML applications in real-world scenarios. The scope covers a broad spectrum of topics including, but not limited to, algorithm optimization, hardware–software co-design, energy-efficient ML models, and real-time data processing techniques. This Special Issue will significantly contribute to the existing literature by bridging the gap between theoretical ML advancements and practical edge computing implementations. While current research predominantly focuses on cloud-based solutions or offline processing, this Special Issue emphasizes the need for immediate, localized processing, which is crucial for latency-sensitive applications. Examples of real-world applications include surveillance systems that require instant anomaly detection, medical imaging for real-time diagnosis, autonomous vehicles needing immediate object recognition and decision-making, smart cameras in urban traffic management, augmented reality devices for interactive user experiences, industrial automation for monitoring and control, wildlife monitoring for real-time tracking, disaster response systems for rapid situational analysis, smart home devices for enhanced security and convenience, and wearable technology for health monitoring and personalized feedback. By presenting cutting-edge research and practical case studies, this Special Issue will serve as a valuable resource for researchers, engineers, and practitioners aiming to develop and deploy efficient ML solutions on edge platforms, ultimately advancing the field of real-time video and image processing.

Dr. Abdussalam Elhanashi
Prof. Dr. Sergio Saponara
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. Electronics 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 2400 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

  • real-time machine learning
  • edge computing
  • video processing
  • image processing
  • algorithm optimization
  • hardware–software co-design
  • energy-efficient ML
  • latency-sensitive applications
  • computational efficiency
  • resource-constrained devices
  • anomaly detection
  • real-time diagnostics
  • autonomous vehicles
  • object recognition
  • urban traffic management
  • augmented reality
  • industrial automation
  • wildlife monitoring
  • disaster response systems
  • smart home devices
  • wearable technology
  • health monitoring
  • personalized feedback
  • real-time data processing
  • ML model deployment
  • edge AI
  • smart cameras
  • low-power computing
  • data privacy
  • real-world ML applications

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 1024 KiB  
Article
A Hessian-Based Deep Learning Preprocessing Method for Coronary Angiography Image Analysis
by Yanjun Li, Takaaki Yoshimura, Yuto Horima and Hiroyuki Sugimori
Electronics 2024, 13(18), 3676; https://doi.org/10.3390/electronics13183676 - 16 Sep 2024
Viewed by 872
Abstract
Leveraging its high accuracy and stability, deep-learning-based coronary artery detection technology has been extensively utilized in diagnosing coronary artery diseases. However, traditional algorithms for localizing coronary stenosis often fall short when detecting stenosis in branch vessels, which can pose significant health risks due [...] Read more.
Leveraging its high accuracy and stability, deep-learning-based coronary artery detection technology has been extensively utilized in diagnosing coronary artery diseases. However, traditional algorithms for localizing coronary stenosis often fall short when detecting stenosis in branch vessels, which can pose significant health risks due to factors like imaging angles and uneven contrast agent distribution. To tackle these challenges, we propose a preprocessing method that integrates Hessian-based vascular enhancement and image fusion as prerequisites for deep learning. This approach enhances fuzzy features in coronary angiography images, thereby increasing the neural network’s sensitivity to stenosis characteristics. We assessed the effectiveness of this method using the latest deep learning networks, such as YOLOv10, YOLOv9, and RT-DETR, across various evaluation metrics. Our results show that our method improves AP50 accuracy by 4.84% and 5.07% on RT-DETR R101 and YOLOv10-X, respectively, compared to images without special pre-processing. Furthermore, our analysis of different imaging angles on stenosis localization detection indicates that the left coronary artery zero is the most suitable for detecting stenosis with a AP50(%) value of 90.5. The experimental results have revealed that the proposed method is effective as a preprocessing technique for deep-learning-based coronary angiography image processing and enhances the model’s ability to identify stenosis in small blood vessels. Full article
Show Figures

Figure 1

16 pages, 9901 KiB  
Article
A Generative Approach for Document Enhancement with Small Unpaired Data
by Mohammad Shahab Uddin, Wael Khallouli, Andres Sousa-Poza, Samuel Kovacic and Jiang Li
Electronics 2024, 13(17), 3539; https://doi.org/10.3390/electronics13173539 - 6 Sep 2024
Viewed by 951
Abstract
Shipbuilding drawings, crafted manually before the digital era, are vital for historical reference and technical insight. However, their digital versions, stored as scanned PDFs, often contain significant noise, making them unsuitable for use in modern CAD software like AutoCAD. Traditional denoising techniques struggle [...] Read more.
Shipbuilding drawings, crafted manually before the digital era, are vital for historical reference and technical insight. However, their digital versions, stored as scanned PDFs, often contain significant noise, making them unsuitable for use in modern CAD software like AutoCAD. Traditional denoising techniques struggle with the diverse and intense noise found in these documents, which also does not adhere to standard noise models. In this paper, we propose an innovative generative approach tailored for document enhancement, particularly focusing on shipbuilding drawings. For a small, unpaired dataset of clean and noisy shipbuilding drawing documents, we first learn to generate the noise in the dataset based on a CycleGAN model. We then generate multiple paired clean–noisy image pairs using the clean images in the dataset. Finally, we train a Pix2Pix GAN model with these generated image pairs to enhance shipbuilding drawings. Through empirical evaluation on a small Military Sealift Command (MSC) dataset, we demonstrated the superiority of our method in mitigating noise and preserving essential details, offering an effective solution for the restoration and utilization of historical shipbuilding drawings in contemporary digital environments. Full article
Show Figures

Figure 1

27 pages, 52132 KiB  
Article
Temporally Coherent Video Cartoonization for Animation Scenery Generation
by Gustavo Rayo and Ruben Tous
Electronics 2024, 13(17), 3462; https://doi.org/10.3390/electronics13173462 - 31 Aug 2024
Viewed by 1116
Abstract
The automatic transformation of short background videos from real scenarios into other forms with a visually pleasing style, like those used in cartoons, holds application in various domains. These include animated films, video games, advertisements, and many other areas that involve visual content [...] Read more.
The automatic transformation of short background videos from real scenarios into other forms with a visually pleasing style, like those used in cartoons, holds application in various domains. These include animated films, video games, advertisements, and many other areas that involve visual content creation. A method or tool that can perform this task would inspire, facilitate, and streamline the work of artists and people who produce this type of content. This work proposes a method that integrates multiple components to translate short background videos into other forms that contain a particular style. We apply a fine-tuned latent diffusion model with an image-to-image setting, conditioned with the image edges (computed with holistically nested edge detection) and CLIP-generated prompts to translate the keyframes from a source video, ensuring content preservation. To maintain temporal coherence, the keyframes are translated into grids and the style is interpolated with an example-based style propagation algorithm. We quantitatively assess the content preservation and temporal coherence using CLIP-based metrics over a new dataset of 20 videos translated into three distinct styles. Full article
Show Figures

Figure 1

Back to TopTop