Computer Vision Research Articles

Validation of computer vision-based ergonomic risk assessment tools for real manufacturing environments.

This study contributes to understanding semi-automated ergonomic risk assessments in industrial manufacturing environments, proposing a practical tool for enhancing worker safety and operational efficiency. In the Industry 5.0 era, the human-centric approach in manufacturing is crucial, especially considering the aging workforce and the dynamic nature of the entire modern industrial sector, today integrating digital technology, automation, and sustainable practices to enhance productivity and environmental responsibility. This approach aims to adapt work conditions to individual capabilities, addressing the high incidence of work-related musculoskeletal disorders (MSDs). The traditional, subjective methods of ergonomic assessment are inadequate for dynamic settings, highlighting the need for affordable, automatic tools for continuous monitoring of workers' postures to evaluate ergonomic risks effectively during tasks. To enable this perspective, 2D RGB Motion Capture (MoCap) systems based on computer vision currently seem the technologies of choice, given their low intrusiveness, cost, and implementation effort. However, the reliability and applicability of these systems in the dynamic and varied manufacturing environment remain uncertain. This research benchmarks various literature proposed MoCap tools and examines the viability of MoCap systems for ergonomic risk assessments in Industry 5.0 by exploiting one of the benchmarked semi-automated, low-cost and non-intrusive 2D RGB MoCap system, capable of continuously monitoring and analysing workers' postures. By conducting experiments across varied manufacturing environments, this research evaluates the system's effectiveness in assessing ergonomic risks and its adaptability to different production lines. Results reveal that the accuracy of risk assessments varies by specific environmental conditions and workstation setups. Although these systems are not yet optimized for expert-level risk certification, they offer significant potential for enhancing workplace safety and efficiency by providing continuous posture monitoring. Future improvements could explore advanced computational techniques like machine learning to refine ergonomic assessments further.

Improving Visual Object Detection using General UFIR Filtering

Object detection is a fundamental task in computer vision, which involves the identification and localization of objects within image frames or video sequences. The problem is complicated by large variations in the video camera bounding box, which can be thought of as colored measurement noise (CMN). In this paper, we use the general unbiased finite impulse response (GUFIR) approach to improve detection performance under CMN. The results are compared to the general Kalman filter (GKF) and two detection methods: “Faster-RCNN” and “Tensorflow PASCAL Visual Object Classes (VOC)”. Experimental testing is carried out using the benchmark data ”Car4”. It is shown that GUFIR significantly improves the detection accuracy and demonstrates the properties of the effective tool for visual object tracking.

Three Years of Google Earth Engine-Based Archaeological Surveys in Iraqi Kurdistan: Results from the Ground

This paper presents the results of a three-year survey (2021–2023), conducted in an area of approximately 356 km2 in Iraqi Kurdistan with the aim of identifying previously undetected archaeological sites. Thanks to the development of a multi-temporal approach based on open multispectral satellite data, greater effectiveness was achieved for the recognition of archaeological sites when compared to the use of single archival or freely accessible satellite images, which are typically employed in archaeological research. In particular, the Google Earth Engine services allowed for the efficient utilization of cloud computing resources to handle hundreds of remote sensing images. Using different datasets, namely Landsat 5, Landsat 7 and Sentinel-2, several products were obtained by processing entire stacks of images acquired at different epochs, thus minimizing the adverse effects on site visibility caused by vegetation, crops and cloud coverage and permitting an effective visual inspection and site recognition. Furthermore, spectral signature analysis of every potential site complemented the method. The developed approach was tested on areas that belong to the Land of Nineveh Archaeological Project (LoNAP) and the Upper Greater Zab Archaeological Reconnaissance (UGZAR) project, which had been intensively surveyed in the recent past. This represented an additional challenge to the method, as the most visible and extensive sites (tells) had already been detected. Three years of direct ground-truthing in the field enabled assessment of the outcomes of the remote sensing-based analysis, discovering more than 60 previously undetected sites and confirming the utility of the method for archaeological research in the area of Northern Mesopotamia.

Systematic Literature Review on Artificial Intelligence and Sustainable Practices in the Apparel Industry

This systematic literature review (SLR) investigates the role of artificial intelligence (AI) in promoting sustainable practices within the apparel industry, addressing the critical need for efficient and environmentally responsible solutions in a sector facing increasing sustainability pressures. The research methodology adheres to PRISMA guidelines, encompassing a comprehensive literature search across databases such as Scopus and Web of Science for articles published between 2010 and 2024. The review process involved rigorous filtering and screening, ultimately analyzing 31 relevant journal articles. Key findings reveal that AI applications significantly enhance operational efficiency and sustainability in apparel manufacturing and supply chains. Techniques such as machine learning for demand forecasting, genetic algorithms for supply chain optimization, and computer vision for quality control are instrumental in reducing waste and improving resource utilization. Despite these advancements, challenges in implementation and scalability persist, indicating areas where further investigation is necessary. The implications of this review underscore the potential of AI to transform the apparel industry by integrating sustainable practices into core operations. However, notable research gaps remain, particularly regarding the ethical implications of AI adoption, its impact on labour practices, and the need for interdisciplinary approaches that bridge technology with environmental sustainability. Future research directions should focus on developing innovative AI methodologies tailored to sustainability challenges, examining the socio-economic impacts of AI on labour within the apparel sector, and enhancing collaboration between academia and industry to foster practical applications of AI technologies. This SLR not only contributes to academic discourse but also serves as a valuable resource for practitioners seeking to implement sustainable practices through AI in the apparel industry.

From analytics to empathy and creativity: Charting the AI revolution in marketing practice and education

The rapid advancement of artificial intelligence (AI) increasingly demands an understanding of its impact on marketing practice and education. Our hybrid literature review synthesizes 312 peer-reviewed articles on AI in marketing and consumer behavior, using scientometrics and the TCCM (Theory, Context, Characteristics, Methodology) framework. We identify five research areas: human–AI interaction in services, natural language processing (NLP) and computer vision for consumer insights, AI for e-commerce and decision support, marketing automation and creativity, and AI ethics. AI’s evolution is marked by a transition from analytical to empathetic and intuitive technologies like affective computing and generative AI. We highlight the changing dynamics between humans and AI, AI integration in marketing practices and education, and the transformed AI-enhanced marketing workplace. We underscore the significance of ethical considerations, the well-being of users, and the integration of generative AI tools. This review provides a comprehensive guide for forthcoming research, practical applications, and educational advancements in AI-enhanced marketing.

Vision Aid: Developing An Assistive Mobile Application for Visually Impaired Indivuals

Vision Aid is a cutting edge smartphone software that combines several assistive technologies into a unified platform to help visually impaired individuals. Integrating Computer Vision algorithms this project makes use of Bing Maps API for Step by Step navigation, Tesseract OCR for text recognition, YOLO (You Only Look Once) for real time object detection and CLIP (Contrastive Language-Image Pre training) for scene description. It offers voice commands, audio feedback for a more improved day to day life hence improving self-confidence while empowering independence to the users. This journal provides a thorough description of Vision Aid the development process, methodology, evaluation results and shows the potential for future improvements with a goal to advance mobile accessibility for visually impaired individuals

BerryPortraits: Phenotyping Of Ripening Traits cranberry (Vaccinium macrocarpon Ait.) with YOLOv8.

BerryPortraits (Phenotyping of Ripening Traits) is open source Python-based image-analysis software that rapidly detects and segments berriesand extracts morphometric data on fruit quality traits such as berry color, size, shape, and uniformity. Utilizing the YOLOv8 framework and community-developed, actively-maintained Python libraries such as OpenCV, BerryPortraits software was trained on 512 postharvest images (taken under controlled lighting conditions) of phenotypically diverse cranberry populations (Vaccinium macrocarpon Ait.) from the two largest public cranberry breeding programs in the U.S. The implementation of CIELAB, an intuitive and perceptually uniform color space, enables differentiation between berry color and berry brightness, which are confounded in classic RGB color channel measurements. Furthermore, computer vision enables precise and quantifiable color phenotyping, thus facilitating inclusion of researchers and data analysts with color vision deficiency. BerryPortraits is a phenotyping tool for researchers in plant breeding, plant genetics, horticulture, food science, plant physiology, plant pathology, and related fields. BerryPortraits has strong potential applications for other specialty crops such as blueberry, lingonberry, caneberry, grape, and more. As an open source phenotyping tool based on widely-used python libraries, BerryPortraits allows anyone to use, fork, modify, optimize, and embed this software into other tools or pipelines.

Construction and Study of an Improved PP-Human Multi-Objective Tracking Method

Multiple objective tracking represents a crucial research focus within the realm of computer vision. It has a very broad application prospect in video surveillance, intelligent transportation, robot navigation and positioning and other fields.However, multi-target visual perception is affected by light, weather, occlusion and other factors, and is vulnerable to noise interference, faced with problems such as unstable image enhancement effect, target correlation accuracy and robustness.In this study, the PP-Human framework is applied to multi-target tracking. Through training and refinement of the PP-Human model, integration of a high-accuracy detector, enhancement of pedestrian re-identification (ReID) techniques, and optimization of the data association approach, the model's multi-object detection performance is enhanced, achieving efficient and precise multi-target tracking. Using the extended Market 150 dataset to comprehensively evaluate the performance of the proposed multi-objective tracking method, this paper improves the accuracy of multi-objective tracking by 5.0% and reaches 95.0% of MOTA through a series of optimization measures.To validate the efficacy and robustness of this approach, experimental evaluations were conducted. The refined PP-Human framework demonstrated strong performance in multi-target tracking tasks, establishing a reliable basis for practical applications such as pedestrian analysis, behavior recognition, and flow statistics.

Measuring Changes in Upper Body Movement Due to Fasting Using a Camera

Understanding activity levels during fasting is important for promoting healthy fasting practices. While most existing studies focus on step counts to objectively assess the impact of fasting on activity levels and behavioral changes, the results have been mixed. Despite evidence showing that individuals spend a significant amount of time sitting while fasting, there has been no objective measurement of body movement or activity levels during sitting and fasting. This research employs a video-based, unobtrusive human body movement measurement system to monitor upper body movements during fasting and non-fasting periods over several days. Key movement features, such as inactivity, movement speed, and movement scale, were automatically extracted from the video monitoring data using a computer vision pipeline. These features were then statistically compared using t tests between fasting and non-fasting periods, analyzed by hour of the day and across different days. The results of the monitoring of five participants during typical daily sitting office work and fasting for 3–5 days indicate no consistent pattern of upper body movement changes due to fasting among the participants.

Optimizing computer vision algorithms with TVM on VLIW architecture based on RVV

Optimizing computer vision algorithms with TVM on VLIW architecture based on RVV

A Nonconvex Approach with Structural Priors for Restoring Underwater Images

Underwater image restoration is a crucial task in various computer vision applications, including underwater target detection and recognition, autonomous underwater vehicles, underwater rescue, marine organism monitoring, and marine geological survey. Among other categories, the physics-based methods restore underwater images by improving the transmission map through optimization or regularization techniques. Conventional optimization-based methods often do not consider the effect of structural differences between guidance and transmission maps. To address this issue, in this paper, we present a regularization-based method for restoring underwater images that uses coherent structures between the guidance map and the transmission map. The proposed approach models the optimization of transmission maps through a nonconvex energy function comprising data and smoothness terms. The smoothness term includes static and dynamic structural priors, and the optimization problem is solved using a majorize-minimize algorithm. We evaluate the proposed method on benchmark datasets, and the results demonstrate the superiority of the proposed method over state-of-the-art techniques in terms of improving transmission maps and producing high-quality restored images.

Foreground separation knowledge distillation for object detection

In recent years, deep learning models have become predominant methods for computer vision tasks, but the large computation and storage requirements of many models make them challenging to deploy on devices with limited resources. Knowledge distillation (KD) is a widely used approach for model compression. However, when applied in the object detection problems, the existing KD methods either directly applies the feature map or simply separate the foreground from the background by using a binary mask, aligning the attention between the teacher and the student models. Unfortunately, these methods either completely overlook or fail to thoroughly eliminate noise, resulting in unsatisfactory model accuracy for student models. To address this issue, we propose a foreground separation distillation (FSD) method in this paper. The FSD method enables student models to distinguish between foreground and background using Gaussian heatmaps, reducing irrelevant information in the learning process. Additionally, FSD also extracts the channel feature by converting the spatial feature maps into probabilistic forms to fully utilize the knowledge in each channel of a well-trained teacher. Experimental results demonstrate that the YOLOX detector enhanced with our distillation method achieved superior performance on both the fall detection and the VOC2007 datasets. For example, YOLOX with FSD achieved 73.1% mean average precision (mAP) on the Fall Detection dataset, which is 1.6% higher than the baseline. The code of FSD is accessible via https://doi.org/10.5281/zenodo.13829676.

INTELLIGENT MONITORING OF THE PHYSIOLOGICAL STATE OF AGRICULTURAL PRODUCTS USING UAV

The article discusses the technology for automated neural network monitoring of the vineyard’s physiological condition. Images of leaves, obtained using an unmanned aerial vehicle (UAV), are the main indicator of the physiological vineyard’s condition. The proposed solution is based on the integrated use of convolutional neural network method (CNN) and machine vision technologies. To determine the optimal neural network (NN) model, a variant analysis was carried out. In accordance with its results, the YOLOv7 model was chosen, which satisfies the introduced time limit and provides the required detection quality. The training of the YOLOv7 neural network was implemented in the Python environment using the PyTorch framework and the OpenCV computer vision library. The dataset consisting of 6320 images of grape leaves (including healthy and diseased ones) has been used for neural network training. The obtained results showed that the detection accuracy is at least 91%. Visualization of monitoring results has been carried out using heatmap, allowing to obtain information about vineyard physiological condition in dynamics. The proposed mathematical model allows to calculate the monitored vineyard’s area made by one complex per day. The obtained results showed that effective monitoring area using one DJI Phantom 4 UAV per day is 2.5 hectares.

A data-driven approach to traditional village colors: K-Means clustering of online images

ABSTRACT This study aims to quantify the color characteristics of traditional villages, explore the key aspects of color that attract tourist attention, and propose solutions to enhance the readability and legibility of these villages. The findings are intended to provide practical guidance for the restoration and use of village colors. The research focuses on how tourists perceive the color characteristics of traditional villages. The objective is to conduct color clustering analysis to identify the composition and characteristics of village colors, and further analyze the underlying causes to offer suggestions for optimization and enhancement. It employs a methodology based on urban imagery theory, using clustering and secondary extraction of color data from online images. The results reveal distinct contrasts and harmonies in the colors of the five elements providing a basis for improving spatial readability and visual guidance. These findings not only offer practical design references for optimizing traditional village colors but also provide valuable insights for the protection and restoration of other traditional sites. In particular, the contrast between the colors of boundaries and landmarks can enhance visual recognition, while the complementary color designs of paths and boundaries can improve spatial readability, contributing to the sustainable development of traditional villages.

Design and Fabrication of the Automatic Multipurpose Agriculture Robot (AMAR)

The rapid development of robotics and automation has significantly benefited various industries, including agriculture. This project proposes the creation of an Automatic Multipurpose Agriculture Robot (AMAR) to revolutionize farming practices. AMAR will automate diverse agricultural tasks, minimize physical labour, and optimize resource use. The automatic multipurpose agricultural seed sowing robot, a state-of-the-art autonomous machine, is designed to revolutionize seed planting. It combines technologies like computer vision and precision mechanics to ensure efficient and precise seed sowing across various crops and terrains. The robot analyses optimal seed placement, ensuring even distribution. Energy-efficient and eco-friendly, it reduces labour costs, increases productivity, and enhances crop yields, fostering sustainable agricultural practices and improving profitability for farmers.The rapid development of robotics and automation has significantly benefited various industries, including agriculture. This project proposes the creation of an Automatic Multipurpose Agriculture Robot (AMAR) to revolutionize farming practices. AMAR will automate diverse agricultural tasks, minimize physical labour, and optimize resource use. The automatic multipurpose agricultural seed sowing robot, a state-of-the-art autonomous machine, is designed to revolutionize seed planting. It combines technologies like computer vision and precision mechanics to ensure efficient and precise seed sowing across various crops and terrains. The robot analyses optimal seed placement, ensuring even distribution. Energy-efficient and eco-friendly, it reduces labour costs, increases productivity, and enhances crop yields, fostering sustainable agricultural practices and improving profitability for farmers.

Can computer vision / artificial intelligence locate key reference points and make clinically relevant measurements on axillary radiographs?

Computer vision and artificial intelligence (AI) offer the opportunity to rapidly and accurately interpret standardized x-rays. We trained and validated a machine learning tool that identified key reference points and determined glenoid retroversion and glenohumeral relationships on axillary radiographs. Standardized pre and post arthroplasty axillary radiographs were manually annotated locating six reference points and used to train a computer vision model that could identify these reference points without human guidance. The model then used these reference points to determine humeroglenoid alignment in the anterior to posterior direction and glenoid version. The model's accuracy was tested on a separate test set of axillary images not used in training, comparing its reference point locations, alignment and version to the corresponding values assessed by two surgeons. On the test set of pre- and post-operative images not used in the training process, the model was able to rapidly identify all six reference point locations to within a mean of 2mm of the surgeon-assessed points. The mean variation in alignment and version measurements between the surgeon assessors and the model was similar to the variation between the two surgeon assessors. This article reports on the development and validation of a computer vision/artificial intelligence model that can independently identify key landmarks and determine the glenohumeral relationship and glenoid version on axillary radiographs. This observer-independent approach has the potential to enable efficient human observer independent assessment of shoulder radiographs, lessening the burden of manual x-ray interpretation and enabling scaling of these measurements across large numbers of patients from multiple centers so that pre and postoperative anatomy can be correlated with patient reported clinical outcomes. Level III Study of Diagnostic Test.

Robust-DefReg: A Robust Coarse to Fine Non-rigid Point Cloud Registration Method based on Graph Convolutional Neural Networks

Abstract Point cloud registration is a critical process in computer vision and measurement science, aimed at determining transformations between corresponding sets of points for accurate spatial alignment. In particular, non-rigid registration involves estimating flexible transformations that map a source point cloud to a target point cloud, even under conditions of stretching, compression, or other complex deformations. This task becomes especially challenging when addressing measurement-specific issues like varying degrees of deformation, noise, and outliers, all of which can impact measurement accuracy and reliability.
This paper introduces Robust-DefReg, a novel method for non-rigid point cloud registration that applies graph convolutional networks (GCNNs) within a coarse-to-fine registration framework. This end-to-end pipeline harnesses global feature learning to establish robust correspondences and precise transformations, enabling high accuracy across different deformation scales and noise levels. A key contribution of Robust-DefReg is its demonstrated resilience to various challenges, such as substantial deformations, noise, and outliers, factors often underreported in existing registration literature.
In addition, we present SynBench, a comprehensive benchmark dataset specifically designed for evaluating non-rigid point cloud registration in realistic measurement scenarios. Unlike previous datasets, SynBench incorporates a range of challenges, making it a valuable tool for the fair assessment of registration methods in measurement applications. Experimental results on SynBench and additional datasets show that Robust-DefReg consistently outperforms state-of-the-art methods, offering higher registration accuracy and robustness, even with up to 45% outliers.
SynBench and the Robust-DefReg source code are publicly accessible for further research and development at https://doi.org/10.11588/data/R9IKCF and https://github.com/m-kinz/Robust-DefReg, respectively.

A new target color adaptive graying and segmentation method for gear contact spot detection

Abstract Gear contact spot plays a crucial role in evaluating gear mesh quality. Traditionally, tooth surfaces of gear pairs have been manually brushed with red lead powder and visually inspected after a certain operating period. To enhance detection accuracy and efficiency, computer vision has emerged as an appealing approach for gear contact spot detection. However, determining the graying weights and segmentation threshold poses challenges, particularly in non-ideal illumination environments. To address this problem, this paper proposes a new target color adaptive graying and segmentation (TC-AGS) method for the gear contact spot detection. With the proposed method, the illumination scene is firstly distinguished by the blue color component weight due to its high sensitivity to illumination intensity. Then, an improved adaptively graying algorithm for target color is employed to determine the graying weights for RGB, ensuring the maximum proportion of the desired red color. Finally, either a global threshold method or a local threshold method is selected for image segmentation and contact spot detection according to the illumination intensity. To validate the effectiveness of the proposed method, comprehensive simulation and experimental tests were conducted. The results demonstrate that the proposed method achieves better gear contact spot detection performance than traditional methods. It exhibits higher extraction accuracy under different illumination environments and even in the presence of blurred image sources.

Exploring structural variances in monatomic metallic glasses using machine learning and molecular dynamics simulation.

BCC and FCC metals have different glass-forming abilities (GFA) and exhibit different characteristics during the glass transition. However, the structural origin of their different GFAs is still not clear. Here, we explored the structures of eight monatomic metallic glasses by combining molecular dynamics (MD) simulations and machine learning (ML). Our findings reveal that, despite their common long-range disordered atomic structure, metallic glasses can be further classified into two distinct categories indicating an underlying structural order within the disorder. Using machine learning, we found that BCC liquids can sample more diverse glass states than FCC liquids. Furthermore, glasses formed from BCC metals (GFFBs) exhibit a higher degree of disorder than glasses formed from FCC metals (GFFFs). These findings highlight the inherent differences between GFFFs and GFFBs, which help explain the different glass-forming abilities of FCC and BCC metals. Additionally, our results demonstrate the promising potential of computer vision and ML methods in exploring material structures. Classical molecular dynamics simulations were employed to generate configurations of GFFBs and GFFFs, and the simulations were performed using the LAMMPS code. Inter-atomic interactions were described using a classical embedded atom model (EAM) potential. The initial configuration of the model consists of 32,000 atoms in a three-dimensional (3D) cubic box with periodic boundary conditions applied in all three directions. For machine learning, we utilized an unsupervised machine learning method along with MobileNetV2 for classifying glass structures. Image entropy and image distances were used to measure the structural differences of the metallic glasses.

Abstract 4116410: A Novel Deep Learning Approach for Prediction of Right Heart Failure After Left Ventricular Assist Device Implantation using Pulmonary Artery Pressure Tracings

Introduction: Left ventricular assist device (LVAD) offers a lifeline for advanced heart failure patients, but ~30% experience post-operative right heart failure (RHF) with significant morbidity and mortality. Current methods for predicting RHF risk have limited accuracy. This study is the first of its kind to explore the feasibility of using a convolutional neural network (CNN) deep learning model with pulmonary artery pressure (PAP) tracings acquired during pre-operative hemodynamic assessment to identify patients at risk for early RHF. Methods: A CNN model was pre-trained on PAP tracings from the MIMIC-III Waveform Database to leverage transferable knowledge and improve model performance. The model learned general features and temporal relationships in hemodynamic tracing morphology for RHF prediction. It was then adapted for classification by modifying the output layers. Post-LVAD RHF was definitively adjudicated for each instance included from our 246 patient single center LVAD database. RHF was adjudicated using the 2020 Academic Research Consortium defintion. The database included 205 non-RHF instances and 41 RHF instances. We developed a novel signal processing method utilizing computer vision to extract PAP waveform data from pre-operative right heart catheterization reports. Data was reviewed to ensure accurate pressure tracing representation. SMOTE-ENN (synthetic oversampling) and class weighting addressed dataset imbalance during training to enhance model generalizability and RHF prediction accuracy. Results: The model achieved strong performance in classifying RHF from non-RHF outcomes, as evidenced by consistent AUC scores of 0.87 and 0.85 on validation and unseen test data, respectively. These findings indicate the potential for hemodynamic tracings to predict RHF after LVAD implantation. Notably, the model maintained its performance on unseen data, highlighting its generalizability. Conclusions: This study explored the feasibility of using a deep learning model for RHF risk stratification in patients with LVADs. The model, pre-trained on PAP tracings, achieved promising classification performance assessed by AUC. Further validation with larger, more diverse datasets will refine model performance and enhance generalizability for clinical application. Leveraging hemodynamic tracings within a deep learning framework holds promise for improved clinical outcome prediction.