Special Issues
Table of Content

Machine Vision Detection and Intelligent Recognition, 2nd Edition

Submission Deadline: 31 March 2025 View: 455 Submit to Special Issue

Guest Editors

Prof. Kechen Song

Email: songkc@me.neu.edu.cn

Affiliation: School of Mechanical Engineering and Automation, Northeastern University, Shenyang, 110819, China.

Homepage: http://faculty.neu.edu.cn/songkc/en

Research Interests: vision-based inspection system for steel surface defects, surface topography, image processing, pattern recognition, and robotics 

 图片4.png


Prof. Shaopeng Hu

Email: hsp@hiroshima-u.ac.jp

Affiliation: Digital Manufacturing Education and Research Center, Hiroshima University, Hiroshima, 7398527, Japan.

Homepage: http://www.robotics.hiroshima-u.ac.jp 

Research Interests: high-speed vision, stereo measurement, smart inspection and monitoring 

 图片5.png


Dr. Xin Wen

Email: wen_xin@sut.edu.cn

Affiliation: School of Software, Shenyang University of Technology, Shenyang 110870, C, Shenyang, 110819, China.

Homepage: https://scholar.google.co.uk/citations?hl=en&user=WZLo0E4AAAAJ

Research Interests: machine vision and surface topography

图片6.png


Summary

Machine vision detection and intelligent recognition are important research areas in computer vision with wide-ranging applications in manufacturing, healthcare, security, transportation, robotics, industrial production, aerospace, and many other industries. Machine vision detection involves capturing visual information using cameras or sensors and then using techniques such as image processing and machine learning to extract relevant features or identify defects in manufacturing processes. Intelligent recognition involves using algorithms to identify and classify objects or patterns in images or videos, enabling automated decision-making in various applications.

 

Recent advancements in these areas have been driven by the acceleration of algorithms such as image processing and deep learning, as well as hardware such as CPUs and GPUs. This has made machine vision detection and recognition more accurate and efficient, particularly in areas such as defect detection, industrial monitoring, high-speed target detection, 3D measurement, intelligent recognition, and so on.

 

However, to make machine vision detection and intelligent recognition technologies more reliable and effective in practical applications, several challenges still need to be addressed. These include how to process massive amounts of image or video data, improve real-time processing, ensure data privacy and security (e.g., in healthcare and surveillance), increase detection and recognition accuracy in complex environments, and enhance the interpretability of deep learning algorithms. Addressing these challenges will be crucial to enable the widespread adoption of machine vision detection and intelligent recognition technologies in various applications.

 

Overall, machine vision detection and intelligent recognition have the potential to revolutionize many industries and are an active area of research in computer vision. This special issue provides a platform for researchers and practitioners to share their latest findings and insights in machine vision detection and intelligent recognition. The special issue welcomes original research articles and review articles that report on the latest advancements and challenges in this field. The topics of interest for this special issue include, but are not limited to:

 

· Object detection and tracking

· Deep learning and pattern recognition

· Defect detection and segmentation

· 3D measurement and reconstruction

· Surveillance and security using machine vision

· Human-computer interaction

· Visual inspection and monitoring

· High-speed vision

· Image segmentation and classification

· Real-time image processing

· Remote monitoring and control of industrial processes

· Multiple camera or sensor systems

· Scene understanding and activity recognition

· Autonomous driving and obstacle detection

· Simultaneous localization and mapping

· Visual servoing and control of robots

· Evaluation and benchmarking of algorithm or system

· Challenges and future directions


Keywords

Computer Vision, Machine Learning, Intelligent Detection, Image Processing, Intelligent Recognition, Deep Learning, Robotics, High-speed Vision, 3D Measurement

Published Papers


  • Open Access

    ARTICLE

    ACSF-ED: Adaptive Cross-Scale Fusion Encoder-Decoder for Spatio-Temporal Action Detection

    Wenju Wang, Zehua Gu, Bang Tang, Sen Wang, Jianfei Hao
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2024.057392
    (This article belongs to the Special Issue: Machine Vision Detection and Intelligent Recognition, 2nd Edition)
    Abstract Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A More >

  • Open Access

    ARTICLE

    Enhanced Multi-Scale Object Detection Algorithm for Foggy Traffic Scenarios

    Honglin Wang, Zitong Shi, Cheng Zhu
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2024.058474
    (This article belongs to the Special Issue: Machine Vision Detection and Intelligent Recognition, 2nd Edition)
    Abstract In foggy traffic scenarios, existing object detection algorithms face challenges such as low detection accuracy, poor robustness, occlusion, missed detections, and false detections. To address this issue, a multi-scale object detection algorithm based on an improved YOLOv8 has been proposed. Firstly, a lightweight attention mechanism, Triplet Attention, is introduced to enhance the algorithm’s ability to extract multi-dimensional and multi-scale features, thereby improving the receptive capability of the feature maps. Secondly, the Diverse Branch Block (DBB) is integrated into the CSP Bottleneck with two Convolutions (C2F) module to strengthen the fusion of semantic information across different… More >

  • Open Access

    ARTICLE

    LQTTrack: Multi-Object Tracking by Focusing on Low-Quality Targets Association

    Suya Li, Ying Cao, Hengyi Ren, Dongsheng Zhu, Xin Xie
    CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 1449-1470, 2024, DOI:10.32604/cmc.2024.056824
    (This article belongs to the Special Issue: Machine Vision Detection and Intelligent Recognition, 2nd Edition)
    Abstract Multi-object tracking (MOT) has seen rapid improvements in recent years. However, frequent occlusion remains a significant challenge in MOT, as it can cause targets to become smaller or disappear entirely, resulting in low-quality targets, leading to trajectory interruptions and reduced tracking performance. Different from some existing methods, which discarded the low-quality targets or ignored low-quality target attributes. LQTTrack, with a low-quality association strategy (LQA), is proposed to pay more attention to low-quality targets. In the association scheme of LQTTrack, firstly, multi-scale feature fusion of FPN (MSFF-FPN) is utilized to enrich the feature information and assist… More >

Share Link