Vision Applications Research Articles

Unveiling the power of Haar frequency domain: Advancing small target motion detection in dim light

Visual small target motion detection finds successful applications in varied scenarios. However, dim-light conditions, such as the tunnel scenes and nighttime environments, present significant challenges to existing detection methods which mainly operate within the spatiotemporal domain. This is because the transmission of small target motion information suffers from the inevitable interference of image noise caused by dim light in the spatiotemporal domain, resulting in the detriment of extracting essential spatiotemporal features of the target motion. Given the significant obstacles posed by dim-light imaging to small target motion detection within the spatiotemporal domain, the exploration of an alternative observation domain for small target motion, alongside the development of a corresponding detection method, emerges as a viable solution. To address this, in this paper, we discovered the remarkable potential of the Haar frequency domain in characterizing the small target motion in dim light. To investigate the advantages of integrating Haar frequency processing in small target motion detection, we introduce a Haar-windowed summation mechanism into an existing bio-inspired small target motion detection model. The proposed mechanism integrates visual information in spatiotemporal windows regulated by frequency parameters of Haar wavelets and effectively discriminates the small target motion from the disturbance of random noise caused by dim light. Theoretical analysis and numerical experiments confirm the superior performance of integrating the Haar frequency processing. This study provides a new vision of small target motion detection through the lens of the frequency domain and extends the limits of existing bio-inspired models for practical applications in dim light.

Design of Virtual Reality System for 3D Visualization and Interaction

Nowadays, a virtual environment or metaverse environment is becoming more popular and can be used for various purposes. There are many computer games and more applications for them such as for training, learning and planning. Currently the presentations of 3-Dimensional (3D) models using mixed reality (MR) technology can be used to avoid misinterpretations of oral and 2-Dimensional (2D) model presentations. As an independent concept and MR applications, MR combines the best of virtual reality (VR) and augmented reality (AR). Therefore, this research aimed to present the descriptions of MR systems, which include its devices, applications, literature reviews and create 3D models that were then implemented in Unity 3D using VR applications for 3D architectural visualization. In addition, the assessment results of the VR application showed that the mean score of 2.85 and 3.45 (“neutral”) indicated that the VR application was a new one for the students and they had never used it before, but they certify that learning with VR is not as difficult as with other simulations. The mean scores of 4.55, 4.70, and 4.75 (“strongly agree”) indicated that the use of the VR application’s 3D objects in the scene was beautiful, clear, and realistic. Besides, the student also enjoyed the immersive experience and the learning was very interesting and they felt that they were in the real world.

Nonclassical Spin‐Multiplexing Metasurfaces Enabled Multifunctional Meta‐Scope

AbstractDielectric metasurfaces have emerged as attractive devices for advanced imaging systems because of their high efficiency, ability of wavefront manipulation, and lightweight. The classical spin‐multiplexing metasurfaces can only provide two orthogonal circular polarization channels and require high phase contrast which limits their applications. Here, metasurfaces with arbitrary three independent channels are demonstrated by proposing a nonclassical spin‐multiplexing approach exploring the low refractive index meta‐atoms. A zoom microscope with on‐axis tri‐foci and a synchronous achiral‐chiral microscope with in‐plane tri‐foci based on silicon nitride metasurfaces are experimentally demonstrated. Based on the on‐axis tri‐foci metasurface, singlet zoom imaging with three magnifications and a broadband response (blue to red) based on a single metasurface is first demonstrated. A compact microscope (meta‐scope) consisting of two metasurfaces with three magnifications of 9.5, 10, and 29X with diffraction‐limited resolutions is further constructed, respectively. Utilizing the in‐plane tri‐foci metasurface, a singlet microscope with three achiral‐chiral channels is demonstrated. It offers a magnification of 53X and a diffraction‐limited resolution, enabling simultaneous imaging of an object's achiral and chiral properties. Our multifunctional metasurfaces and meta‐scope approaches could boost the applications in biological imaging and machine vision.

Applications of Computer Vision, 2nd Edition

Computer vision (CV) is a broad term mainly used to refer to processing image and video data [...]

Application of machine vision in food computing: A review

With global intelligence advancing and the awareness of sustainable development growing, artificial intelligence technology is increasingly being applied to the food industry. This paper, grounded in practical application cases, reviews the current research status and prospects of machine vision–based image recognition technology in food computing. It explores the general workflow of image recognition, applications based on traditional machine learning and deep learning methods. The paper covers areas including food safety detection, dietary nutrition analysis, process monitoring, and enterprise management model optimization. The aim is to provide a solid theoretical foundation and technical guidance for the integration and cross-fertilization of the food industry with artificial intelligence technology.

Detection of High-Temperature Gas Leaks in Pipelines Using Schlieren Visualization

This paper investigates the application of Schlieren flow visualization for detecting leaks in pipelines carrying high-temperature fluids. Two experimental setups were constructed: one with a 25 mm PTFE tube featuring a 2 mm diameter perforation, and another with a 100 mm diameter pipe insulated with an aluminum jacket and featuring a 12 mm leak gap. A single-mirror-off-axis Schlieren system, employing a 150 mm diameter parabolic mirror, was used to visualize the leaks. The temperature of the leaking air varied between 20 and 100 °C, while the ambient temperature was maintained at 14 °C. To quantify the leaks, the coefficient of variation for pixel intensity within the leak region was calculated. Results showed that for the PTFE tube, leaks became detectable when the temperature difference exceeded 34 °C, with the coefficient of variation surpassing 0.1. However, in the insulated pipe, detecting clear leak patterns was challenging. This research demonstrates the potential of Schlieren visualization as a valuable tool in enhancing pipeline leak detection.

Achieving the Best Symmetry by Finding the Optimal Clustering Filters for Specific Lighting Conditions

This article explores the efficiency of various clustering methods for image segmentation under different luminosity conditions. Image segmentation plays a crucial role in computer vision applications, and clustering algorithms are commonly used for this purpose. The search for an adaptive clustering mechanism aims to ensure the maximum symmetry of real objects with objects/segments in their digital representations. However, clustering method performances can fluctuate with varying lighting conditions during image capture. Therefore, we assess the performance of several clustering algorithms—including K-Means, K-Medoids, Fuzzy C-Means, Possibilistic C-Means, Gustafson–Kessel, Entropy-based Fuzzy, Ridler–Calvard, Kohonen Self-Organizing Maps and MeanShift—across images captured under different illumination conditions. Additionally, we develop an adaptive image segmentation system utilizing empirical data. Conducted experiments highlight varied performances among clustering methods under different luminosity conditions. This research enhances a better understanding of luminosity’s impact on image segmentation and aids the method selection for diverse lighting scenarios.

A Low-Power, High-Resolution Analog Front-End Circuit for Carbon-Based SWIR Photodetector

Carbon nanotube field-effect transistors (CNT-FETs) have shown great promise in infrared image detection due to their high mobility, low cost, and compatibility with silicon-based technologies. This paper presents the design and simulation of a column-level analog front-end (AFE) circuit tailored for carbon-based short-wave infrared (SWIR) photodetectors. The AFE integrates a Capacitor Trans-impedance Amplifier (CTIA) for current-to-voltage conversion, coupled with Correlated Double Sampling (CDS) for noise reduction and operational amplifier offset suppression. A 10-bit/125 kHz Successive Approximation analog-to-digital converter (SAR ADC) completes the signal processing chain, achieving rail-to-rail input/output with minimized component count. Fabricated using 0.18 μm CMOS technology, the AFE demonstrates a high signal-to-noise ratio (SNR) of 59.27 dB and an Effective Number of Bits (ENOB) of 9.35, with a detectable current range from 500 pA to 100.5 nA and a total power consumption of 7.5 mW. These results confirm the suitability of the proposed AFE for high-precision, low-power SWIR detection systems, with potential applications in medical imaging, night vision, and autonomous driving systems.

Content-Based Image Retrieval and Feature Extraction: Analysing the Literature

A significant amount of multimedia data consists of digital images, and multimedia content analysis is used in many real-world computer vision applications. Multimedia information, especially photos, has become much more complicated in the last several years. Every day, millions of photos are posted to various websites, such as Instagram, Facebook, and Twitter. Finding a suitable image in an archive is a difficult research subject for the field of computer vision. Most search engines use standard text-based techniques that depend on metadata and captions in order to fetch photos. Over the past 20 years, a great deal of research has been conducted on content-based image retrieval (CBIR), picture categorization, and analysis. In image classification models and CBIR, high-level picture representations are represented as feature vectors made up of numerical values. Empirical evidence indicates a considerable disparity between picture feature representation and human visual understanding. Reducing the semantic gap between human visual understanding and picture feature representation is the aim of this study. This study aims to do a thorough analysis of the latest advancements in the domains of Content-Based picture Retrieval and picture representation. We performed a comprehensive analysis of many models for image retrieval and picture representation, encompassing the most recent advancements in semantic deep-learning methods and feature extraction. This paper provides an in-depth analysis of the key ideas and important studies related to image representation and content-based picture retrieval. In an effort to stimulate more research in this field, it also offers a preview of potential future study topics.

Quantum visual feature encoding revisited

Although quantum machine learning has been introduced for a while, its applications in computer vision are still limited. This paper, therefore, revisits the quantum visual encoding strategies, the initial step in quantum machine learning. Investigating the root cause, we uncover that the existing quantum encoding design fails to ensure information preservation of the visual features after the encoding process, thus complicating the learning process of the quantum machine learning models. In particular, the problem, termed the “Quantum Information Gap” (QIG), leads to an information gap between classical and corresponding quantum features. We provide theoretical proof and practical examples with visualization for that found and underscore the significance of QIG, as it directly impacts the performance of quantum machine learning algorithms. To tackle this challenge, we introduce a simple but efficient new loss function named Quantum Information Preserving (QIP) to minimize this gap, resulting in enhanced performance of quantum machine learning algorithms. Extensive experiments validate the effectiveness of our approach, showcasing superior performance compared to current methodologies and consistently achieving state-of-the-art results in quantum modeling.

Survey on data fusion approaches for fall-detection

Human fall detection is a critical research area focused on developing methods and systems that can automatically detect and recognize falls, particularly among the elderly and individuals with disabilities. Falls are a major cause of injuries and deaths among these populations, and timely intervention can reduce the severity of consequences. This article presents a comprehensive review of fall detection systems, emphasizing the use of cutting-edge technologies such as deep learning, sensor fusion, and machine learning. The research explores a variety of methodologies and strategies employed in fall detection systems, including the integration of wearable sensors, smartphones, and cameras. By examining various fall detection techniques and their experimental results, the article highlights the effectiveness of these systems in identifying and classifying falls. The study also addresses the challenges and limitations associated with fall detection systems, emphasizing the need for ongoing research and advancements. In summary, this research contributes to the development of advanced fall detection systems, demonstrating their potential to improve the quality of life for the elderly, alleviate healthcare burdens, and provide reliable solutions for fall detection and classification.

Three-Dimensional Reconstruction of Indoor Scenes Based on Implicit Neural Representation.

Reconstructing 3D indoor scenes from 2D images has always been an important task in computer vision and graphics applications. For indoor scenes, traditional 3D reconstruction methods have problems such as missing surface details, poor reconstruction of large plane textures and uneven illumination areas, and many wrongly reconstructed floating debris noises in the reconstructed models. This paper proposes a 3D reconstruction method for indoor scenes that combines neural radiation field (NeRFs) and signed distance function (SDF) implicit expressions. The volume density of the NeRF is used to provide geometric information for the SDF field, and the learning of geometric shapes and surfaces is strengthened by adding an adaptive normal prior optimization learning process. It not only preserves the high-quality geometric information of the NeRF, but also uses the SDF to generate an explicit mesh with a smooth surface, significantly improving the reconstruction quality of large plane textures and uneven illumination areas in indoor scenes. At the same time, a new regularization term is designed to constrain the weight distribution, making it an ideal unimodal compact distribution, thereby alleviating the problem of uneven density distribution and achieving the effect of floating debris removal in the final model. Experiments show that the 3D reconstruction effect of this paper on ScanNet, Hypersim, and Replica datasets outperforms the state-of-the-art methods.

Multi-cameras calibration System Based Deep Learning Approach and Beyond: A Survey

The process of determining camera settings to deduce geometric attributes from recorded sequences is known as camera calibration. This process is essential in the fields of robotics and computer vision, encompassing both two-dimensional and three-dimensional applications. Traditional calibration methods, however, are time-consuming and require specific expertise. Recent endeavors have demonstrated that learning-based systems can replace the monotonous tasks associated with manual calibrations. Responses have been examined through a range of learning techniques, networks, geometric assumptions, and datasets. A thorough examination of camera calibration systems that rely on learning algorithms is offered in this paper, assessing their advantages and disadvantages. The primary categories of calibration presented are the regular pinhole camera model, distortion camera model, cross-sensor model, and cross-view model. These categories align with current research trends and have diverse applications. As there is no existing standard in this field, a large dataset of calibration has been created, which can be used as a public platform to assess the effectiveness of current methods. This collection consists of both artificially generated and genuine data, including images and videos obtained from various cameras in different locations. The difficulties faced will be analyzed, and alternative avenues for further research will be suggested in the next stage of this project. This survey represents the initial attempt to perform camera calibration using learning-based methods spanning a period of eight years. Our findings indicate that learning-based methods significantly reduce the time and expertise required for calibration while maintaining or improving accuracy compared to traditional methods. Specifically, our research demonstrates a calibration error reduction of up to 20% and speed improvements by a factor of three compared to traditional methods, as well as better adaptability to different camera types and environments.

AnyFace++: Deep Multi-Task, Multi-Domain Learning for Efficient Face AI.

Accurate face detection and subsequent localization of facial landmarks are mandatory steps in many computer vision applications, such as emotion recognition, age estimation, and gender identification. Thanks to advancements in deep learning, numerous facial applications have been developed for human faces. However, most have to employ multiple models to accomplish several tasks simultaneously. As a result, they require more memory usage and increased inference time. Also, less attention is paid to other domains, such as animals and cartoon characters. To address these challenges, we propose an input-agnostic face model, AnyFace++, to perform multiple face-related tasks concurrently. The tasks are face detection and prediction of facial landmarks for human, animal, and cartoon faces, including age estimation, gender classification, and emotion recognition for human faces. We trained the model using deep multi-task, multi-domain learning with a heterogeneous cost function. The experimental results demonstrate that AnyFace++ generates outcomes comparable to cutting-edge models designed for specific domains.

420 Automated identification and behavioral estrus detection in freestall-housed dairy cows using computer vision and machine learning: A two-layered algorithm approach

Abstract A critical aspect of dairy management involves maintaining accurate records of individual animals and promptly detecting estrus behavior, which is vital for successful breeding and reproductive outcomes. Recent advancements in precision livestock management, utilizing computer vision and machine learning technologies, have paved the way for automated and precise solutions in these areas. The objective of this study is to investigate the application of computer vision and machine learning for animal identification and behavioral estrus detection in dairy cows housed in freestall settings, employing a two-layered algorithmic approach. The research was conducted at the Joe Bearden Dairy Research Center, where a total of 10 lactating Holstein-Friesian cows were assessed across a 7-d trial period. For synchronization efforts, cows were provided a single injection of Prostaglandin F2α at trial initiation with expected estrus behaviors to be exhibited within the following 56 h. Continuous video was captured in 4k resolution using a five-camera closed caption media recording system strategically placed in the pen corners and over the feed bunk alleyway to capture multiple perspectives. Video data extrapolated into frames and manual annotation was utilized to generate the machine learning algorithm’s training data. Frames were randomly selected from a scattering of 56 h of video across all five camera viewpoints and down sampled to 384 x 640 p for both layers. A two-layer approach was employed utilizing an algorithm for each aspect of the study with the first model detecting the behavior, and the second model using the detected region of interest to identify specific cows. The first layer was trained on 682 frames and validated against 123 manually annotated frames. The second layer was trained on 102 frames and validated against 16 frames manually annotated for individual animals. Results demonstrated that the model used for mounting behavior identification has high precision (0.819) and recall (0.89), achieving a 0.926 mAP at an IoU of 0.5. This model achieved an F1 score of 0.86 at a confidence threshold of 0.268. The results demonstrated that the model used for individual animal identification across different classes achieved high precision (0.861) and recall (0.842), with a mAP of 0.897 at an IoU of 0.5. The F1 score for all classes was 0.89 at a confidence threshold of 0.788. In conclusion, these promising findings underscore the potential of computer vision and machine learning technologies to revolutionize dairy cow management practices. This innovative approach not only has potential to enhance operational efficiency, but also contributes significantly to improved reproductive management, thereby advancing precision and productivity in dairy operations.

Quaternion optimized model with sparseness for color image recovery

This paper presents a novel approach for sparse regularization of low-rank quaternion matrix optimization problems. Quaternion matrices, which extend the concept of complex numbers to four dimensions, have shown promising applications in various fields. In this work, we exploit the inherent sparsity present in different signal types, such as audio formats and images, when represented in their respective bases. By introducing a sparse regularization term in the optimization objective. We propose a regularization technique that promotes sparsity in the Quaternion Discrete Cosine Transform (QDCT) domain for efficient and accurate solutions. By combining low-rank restriction with sparsity, the optimized model is updated using a two-step Alternating Direction Method of Multipliers (ADMM) algorithm. Experimental results on color images demonstrate the effectiveness of the proposed method, which outperforms existing relative methods. This superior performance underscores its potential for applications in computer vision and related fields.

A comprehensive qualitative and quantitative survey on image dehazing based on deep neural networks

Image dehazing has become a necessary area of research with the increasing popularity and demand of computer vision systems. Image dehazing is a method to remove haze from an image to improve its visual quality. Dehazing techniques are widely employed in a variety of computer vision applications to enhance their overall performance. Many techniques have been proposed by researchers in recent years to eliminate the haze from an image. However, there is a lack of available literature that provides a summary of deep learning-based state-of-the-art image dehazing methods. In this study, we provide a detailed review of recently proposed image dehazing techniques based on deep neural networks such as CNN, GAN, RNN, RCNN, and Transformer. A concise review of significant applications of image dehazing, benchmark datasets, and various performance metrics are also presented. We compare the state-of-the-art methods quantitatively using performance evaluation metrics such as SSIM and PSNR. Finally, this study discusses the fundamental difficulties associated with image dehazing approaches that need to be further explored.

Fe3+-doped broadband near-infrared phosphor with high quantum efficiency toward multifunctional pc-LEDs applications

A broadband near-infrared (NIR) luminescence that is comparable to chromium ions activated materials is fulfilled in Li3Sc2(PO4)3:Fe3+ phosphor, which is highly desired for environmental and biomedical applications due to the non-toxicity of Fe3+ ions. Structural and spectral analysis reveal that the broadband NIR emission peaked at 805 nm with a full width at half-maximum of 130 nm is derived from the non-selective two-site occupation of Fe3+ in the Sc3+ sites. A high internal/external quantum efficiency of 53 %/38.7 % is achieved via relaxing the selection rule for the forbidden 4T1(4G) → 6A1(6S) transitions of Fe3+ by larger lattice distortion. The influence of Fe3+ concentration and environment temperature on the broadband NIR luminescence properties of the as-prepared phosphors are also investigated. Finally, a NIR pc-LED prototype is fabricated and its electro-optical performance has guaranteed the applications in non-destructive detection and night vision. All the results have validated Li3Sc2(PO4)3 as a novel matrix system for access to highly efficient broadband NIR Fe3+-doping phosphor materials.

Advanced Necklace for Real-Time PPG Monitoring in Drivers.

Monitoring heart rate (HR) through photoplethysmography (PPG) signals is a challenging task due to the complexities involved, even during routine daily activities. These signals can indeed be heavily contaminated by significant motion artifacts resulting from the subjects' movements, which can lead to inaccurate heart rate estimations. In this paper, our objective is to present an innovative necklace sensor that employs low-computational-cost algorithms for heart rate estimation in individuals performing non-abrupt movements, specifically drivers. Our solution facilitates the acquisition of signals with limited motion artifacts and provides acceptable heart rate estimations at a low computational cost. More specifically, we propose a wearable sensor necklace for assessing a driver's well-being by providing information about the driver's physiological condition and potential stress indicators through HR data. This innovative necklace enables real-time HR monitoring within a sleek and ergonomic design, facilitating seamless and continuous data gathering while driving. Prioritizing user comfort, the necklace's design ensures ease of wear, allowing for extended use without disrupting driving activities. The collected physiological data can be transmitted wirelessly to a mobile application for instant analysis and visualization. To evaluate the sensor's performance, two algorithms for estimating the HR from PPG signals are implemented in a microcontroller: a modified version of the mountaineer's algorithm and a sliding discrete Fourier transform. The goal of these algorithms is to detect meaningful peaks corresponding to each heartbeat by using signal processing techniques to remove noise and motion artifacts. The developed design is validated through experiments conducted in a simulated driving environment in our lab, during which drivers wore the sensor necklace. These experiments demonstrate the reliability of the wearable sensor necklace in capturing dynamic changes in HR levels associated with driving-induced stress. The algorithms integrated into the sensor are optimized for low computational cost and effectively remove motion artifacts that occur when users move their heads.

Bibliometric Analysis Using Vosviewer on Research Trends in Marketing with the Theme of Green Buying Behavior in Google Scholar

This paper aim to explores the emerging focus on environmentally conscious consumer practices. Utilizing a bibliometric approach, the study examines 352 scholarly articles sourced from Google Scholar, utilizing the Publish or Perish application and VOSviewer software for data visualization and mapping. Key findings highlight a steady increase in research interest, particularly after 2021, indicating a growing academic and practical emphasis on green buying behaviors. The study presents a chronological publication trend and identifies the most prolific publishers and researchers in the field. Additionally, the research network's mapping illustrates the central themes and connections among various factors influencing green buying behavior, such as consumer awareness, marketing strategies, and the environmental impact of consumer choices. This comprehensive bibliometric analysis not only charts the evolution of research in this area but also suggests that increased attention to green marketing strategies could significantly influence consumer behavior. This is visually supported by network and density visualizations that depict the relationships and research intensity in the field, pointing to potential future directions for both academic study and practical marketing applications