Computer Vision and AI Algorithms for Diverse Scenarios

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 31 January 2026 | Viewed by 522

Special Issue Editors


E-Mail
Guest Editor
Department of Civil Engineering, The Republic of China Military Academy, No. 1, Weiwu Rd., Fengshan, Kaohsiung 830, Taiwan
Interests: crack detection; image recognition; multi-scale CNN extraction; high-resolution UAV images; machine learning; deep learning; data mining; performance evaluation of construction; construction risk management

E-Mail
Guest Editor
Department of Management Sciences, R.O.C. Military Academy, Kaohsiung 830, Taiwan
Interests: fuzzy logic; linguistic algorithms; natural language processing; military domain knowledge discovering; soft computing; risk assessment; supply chain; reliability
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, the field of computer vision has undergone transformative advancements, driven largely by the rapid evolution of artificial intelligence (AI) algorithms. As these technologies continue to evolve, there is a pressing need to explore and refine AI-driven approaches to address emerging challenges and seize opportunities in computer vision. The rapid advancement of AI technologies and their application to computer vision have significantly enhanced our ability to interpret, analyze, and understand complex visual data across various domains.

This Special Issue aims to highlight cutting-edge research and developments in computer vision and AI algorithms tailored to a broad range of scenarios. Advances in deep learning techniques, including convolutional neural networks (CNNs), transformer models, and hybrid architectures, have significantly enhanced our ability to analyze and interpret visual data. These innovations have far-reaching implications across various domains, such as autonomous systems, healthcare, environmental monitoring, and more.

We encourage researchers and practitioners to contribute original research articles, review papers, and technical notes that address these topics, as this Special Issue aims to showcase state-of-the-art methodologies and applications in computer vision that leverage AI to tackle the complexities of diverse scenarios. By advancing the field of computer vision and AI algorithms, we aim to foster innovation and drive progress across a wide range of applications and scenarios. As such, we invite contributions that explore novel approaches, methodologies, and applications in areas including but not limited to the following:

  • Advanced AI algorithms for object detection and recognition—techniques and models for analyzing and interpreting visual data across different environments;
  • AI-Driven Image and Video Analysis—advances in algorithms for object detection, image segmentation, and action recognition using AI techniques;
  • Adaptive AI Models for Varied Contexts—development of robust computer vision systems for real-time processing and analysis;
  • Benchmark Datasets and Evaluation Metrics—benchmarking and evaluation of AI-driven computer vision models on diverse datasets;
  • Cross-Domain Applications of Computer Vision—exploration of computer vision applications across different domains, including autonomous systems, security surveillance, healthcare, transportation, agriculture, and environmental monitoring;
  • Integration of Multimodal Data—approaches that combine visual data with other modalities, such as textual or sensor data, to enhance understanding and analysis in diverse scenarios.

Dr. Ching-Lung Fan
Prof. Dr. Kuei-Hu Chang
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

  • deep learning
  • computer vision
  • image classification
  • object detection
  • semantic segmentation
  • data-driven methods
  • artificial intelligence
  • linguistic algorithms
  • natural language processing
  • soft computing

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (1 paper)

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

Research

25 pages, 4360 KiB  
Article
Enhancing Aquarium Fish Tracking with Mirror Reflection Elimination and Enhanced Deep Learning Techniques
by Kai-Di Zhang, Edward T.-H. Chu, Chia-Rong Lee and Jhih-Hua Su
Electronics 2025, 14(16), 3187; https://doi.org/10.3390/electronics14163187 - 11 Aug 2025
Viewed by 32
Abstract
The popularity of keeping ornamental fish has grown increasingly, as their vibrant presence can provide a calming influence. Accurately assessing the health of ornamental fish is important but challenging. For this, researchers have focused on developing fish tracking methods that provide trajectories for [...] Read more.
The popularity of keeping ornamental fish has grown increasingly, as their vibrant presence can provide a calming influence. Accurately assessing the health of ornamental fish is important but challenging. For this, researchers have focused on developing fish tracking methods that provide trajectories for health assessment. However, issues such as mirror images, occlusion, and motion prediction errors can significantly reduce the accuracy of existing algorithms. To address these problems, we propose a novel ornamental fish tracking method based on deep learning techniques. We first utilize the You Only Look Once (YOLO) v5 deep convolutional neural network algorithm with Distance Intersection over Union–Non Maximum Suppression (DIoU-NMS) to handle occlusion problems. We then design an object removal algorithm to eliminate fish mirror image coordinates. Finally, we adopt an improved DeepSORT algorithm, replacing the original Kalman Filter with an advanced Noise Scale Adaptive (NSA) Kalman Filter to enhance tracking accuracy. In our experiment, we evaluated our method in three simulated real-world fish tank environments, comparing it with the YOLOv5 and YOLOv7 methods. The results show that our method can increase Multiple Object Tracking Accuracy (MOTA) by up to 13.3%, Higher Order Tracking Accuracy (HOTA) by up to 10.0%, and Identification F1 Score by up to 14.5%. These findings confirm that our object removal algorithm effectively improves Multiple Object Tracking Accuracy, which facilitates early disease detection, reduces mortality, and mitigates economic losses—an important consideration given many owners’ limited ability to recognize common diseases. Full article
(This article belongs to the Special Issue Computer Vision and AI Algorithms for Diverse Scenarios)
Show Figures

Figure 1

Back to TopTop