Real-time Object Research Articles

Mathematical model of quality control assessment of the technical condition radio electronic equipment

The article examines the issue of monitoring the technical condition of special-purpose radio-electronic equipment under the influence of external factors. The main attention is paid to the formalization of the control process through the construction of a mathematical model that describes the dependence of the initial parameters of the control system on internal and external influences. The existing control methods are analyzed, which reflect the difficulties of selecting control points in modern integrated circuits. The necessity of introducing new, more flexible and adaptive solutions in solving the problems of technical diagnostics is shown. The work proposes an improved mathematical model for monitoring the technical condition of radio-electronic equipment, which allows more accurate assessment of the functional state of the control object in real time. The control process is described in the model through probabilities of changing the state of a generalized indicator that ensures the accuracy of the control system. This approach to quality control of the functional state of the object based on the construction of stochastic graphs allows to estimate the probability of error and accuracy during the control of the technical condition. The results of the research can be applied to the effective maintenance of radio-electronic equipment, as well as improving indicators of diagnosing the technical condition and predicting possible failures of the control object.

Evaluating YOLO Models for Efficient Crack Detection in Concrete Structures Using Transfer Learning

The You Only Look Once (YOLO) network is considered highly suitable for real-time object detection tasks due to its characteristics, such as high speed, single-shot detection, global context awareness, scalability, and adaptability to real-world conditions. This work introduces a comprehensive analysis of various YOLO models for detecting cracks in concrete structures, aiming to assist in the selection of an optimal model for future detection and segmentation tasks. The YOLO models are initially trained on a dataset containing both images with and without cracks, producing a generalized model capable of extracting abstract features beneficial for crack detection. Subsequently, transfer learning is employed using a dataset that reflects real-world conditions, such as occlusions, varying crack sizes, and rotations, to further refine the model. Crack detection in concrete remains challenging due to the wide variation in crack sizes, aspect ratios, and complex backgrounds. To achieve optimal performance, we test different versions of YOLO, a state-of-the-art single-shot detector, and aim to balance inference speed and mean average precision (mAP). Our results indicate that YOLOv10 demonstrates superior performance, achieving a mean average precision (mAP) of 74.52% with an inference time of 19.5 milliseconds per image, making it the most effective among the models tested.

Implementation of Deep Learning Algorithm for Vehicle Count Monitoring System

Vehicle detection plays a crucial role in various applications such as traffic surveillance, license plate recognition, and the development of autonomous vehicles. The You Only Look Once (YOLO) object detection method is renowned for its high-speed real-time object detection capabilities. In this study, YOLO is employed to detect vehicles in images and videos. YOLO treats object detection as a direct regression problem for bounding boxes and class predictions. The aim of this research is to develop a vehicle counting system using the YOLO method. The Midpoint algorithm is utilized to calculate the midpoint between two points in a coordinate plane. Another objective is to analyze the strengths and weaknesses of the method and algorithm in the context of vehicle detection while identifying related research trends. The test results indicate that the system is capable of detecting vehicles with an average accuracy of 92.42% across four different time periods. In the morning, the system detected 156 vehicles (manual count: 147, accuracy: 94.23%); at midday, it detected 246 vehicles (manual count: 225, accuracy: 91.46%); in the evening, 377 vehicles were detected (manual count: 351, accuracy: 93.10%); and at night, the system identified 526 vehicles (manual count: 225, accuracy: 92.58%). This study contributes to the development of a more effective vehicle counting system for smart city applications while also paving the way for further research on vehicle detection under varying lighting and environmental conditions.

AI Powered Smart Glass for Visually Impaired Individuals

Visually impaired individuals often face difficulties navigating and interacting with their environments. This paper presents a cost-effective solution in the form of AI- powered smart glasses, which use the Arduino Uno microcontroller and ESP32 Camera to enable real-time object detection, text recognition, and obstacle avoidance. The system provides auditory and tactile feedback, making it suitable for independent navigation. The smart glasses are designed for offline functionality, utilizing edge AI to perform object and text recognition directly on the device. The paper covers the hardware design, software implementation, and evaluation of this assistive technology. Key Words: Assistive technology, Arduino Uno, ESP32 Camera, visually impaired, object detection, text-to-speech, obstacle detection, IoT.

BRTPillar: boosting real-time 3D object detection based point cloud and RGB image fusion in autonomous driving

PurposeIn autonomous driving, the inherent sparsity of point clouds often limits the performance of object detection, while existing multimodal architectures struggle to meet the real-time requirements for 3D object detection. Therefore, the main purpose of this paper is to significantly enhance the detection performance of objects, especially the recognition capability for small-sized objects and to address the issue of slow inference speed. This will improve the safety of autonomous driving systems and provide feasibility for devices with limited computing power to achieve autonomous driving.Design/methodology/approachBRTPillar first adopts an element-based method to fuse image and point cloud features. Secondly, a local-global feature interaction method based on an efficient additive attention mechanism was designed to extract multi-scale contextual information. Finally, an enhanced multi-scale feature fusion method was proposed by introducing adaptive spatial and channel interaction attention mechanisms, thereby improving the learning of fine-grained features.FindingsExtensive experiments were conducted on the KITTI dataset. The results showed that compared with the benchmark model, the accuracy of cars, pedestrians and cyclists on the 3D object box improved by 3.05, 9.01 and 22.65%, respectively; the accuracy in the bird’s-eye view has increased by 2.98, 10.77 and 21.14%, respectively. Meanwhile, the running speed of BRTPillar can reach 40.27 Hz, meeting the real-time detection needs of autonomous driving.Originality/valueThis paper proposes a boosting multimodal real-time 3D object detection method called BRTPillar, which achieves accurate location in many scenarios, especially for complex scenes with many small objects, while also achieving real-time inference speed.

Enhancing real time object detection for autonomous driving using YOLO-NAS algorithm with CLEO optimizer

Enhancing real time object detection for autonomous driving using YOLO-NAS algorithm with CLEO optimizer

How do Patient-Reported Outcomes Correlate with Real-Time Objective Measures of Function after Total Knee Arthroplasty? A Prospective Study Using Daily Gait Metrics.

Patient-reported outcome measures (PROs) are essential for evaluating patients undergoing total knee arthroplasty (TKA). While wearable technologies offer objective measures of physical function through Apple HealthKit, their relationship with PROs in TKA patients is not well understood. We investigated the association between commonly used PROs and objective measures of physical function in patients undergoing TKA. We conducted a prospective cohort study involving 152 patients undergoing unilateral TKA, assessing PROs (Knee Injury and Osteoarthritis Outcome Score, Joint Replacement [KOOS, JR] and EuroQol Five-Dimensional Questionnaire [EQ-5D]) and objective HealthKit metrics (gait speed, step count, standing duration, steadiness, estimated six-minute walk test) before and at one, six, and 12 months after surgery. Pearson correlation coefficients were used to analyze the relationship between PROs and HealthKit metrics at each time point, adjusting for multiple comparisons. Significant improvements were observed in PROs post-TKA. The KOOS, JR scores improved from 52.1 ± 11.9 and rest preoperatively to 82.5 ± 13.2 at 12 months postoperatively (P < 0.001), and EQ5D scores improved from 73.9 ± 17.8 to 85.7 ± 11.6 over the same period (P < 0.001). However, correlations between PROs and HealthKit metrics were consistently low (mean r = 0.2 to 0.3) and not significant after adjusting for multiple comparisons at various operative time points. Notably, correlations among HealthKit metrics themselves remained high, indicating that objective measures were internally consistent but not strongly related to PROs. Despite their importance in patient-centered care, PROs may not fully reflect actual physical function. Clinicians should consider incorporating objective measures, such as those provided by HealthKit, into routine assessments to obtain a more comprehensive view of patient recovery post-TKA.

Object Detection for Autonomous Vehicles Using YOLO Algorithm

The YOLO (You Only Look Once) algorithm is a real-time object recognition system that classifies objects as regression problems and predicts bounding boxes and class probabilities directly from the whole image in analysis. It is known for its speed and accuracy in real-time object detection. One of the best detection systems in autonomous vehicles is YOLO (You Only Look Once). It predicts bounding box and class probabilities from the entire image in a single evaluation using the same convolutional neural network. It works well in real-time applications such as autonomous driving due to its high-speed capability. YOLO’s one-step detection pipeline streamlines the process and reduces the computational burden. As a result, drivers and other road users are safer and have better situational awareness and decision-making skills.

Real-time traffic object detection using detectron 2 with faster R-CNN

Real-time traffic object detection using detectron 2 with faster R-CNN

Water Trash Detection System: An Innovative Approach to Monitoring Aquatic Pollution

Abstract: Water pollution, particularly from non-biodegradable waste such as plastics, is one of the most pressing environmental issues facing aquatic ecosystems today. This paper presents an innovative solution for detecting and classifying waste in water bodies using machine learning techniques, specifically You Only Look Once (YOLO) and Convolutional Neural Networks (CNNs). The Water Trash Detection System (WTDS) can process both static images and real-time video streams to efficiently detect various types of aquatic trash, including plastic bottles, bags, and fishing debris. The system generates detailed reports on detected waste, providing environmental organizations and researchers with actionable data for monitoring and cleaning polluted water bodies. The combination of YOLO for real-time object detection and CNNs for waste classification allows the WTDS to deliver high accuracy and real-time processing, which is essential for effective environmental management.

AI-Powered Conflict Resolution: Transforming Virtual Team Dynamics in Real-Time

This paper explores the transformative role of Artificial Intelligence (AI) in conflict resolution within virtual team dynamics. As remote work becomes increasingly prevalent, traditional conflict resolution strategies often fall short in addressing challenges like communication barriers, cultural differences, and workload imbalances. Leveraging AI-powered tools offers novel solutions by providing real-time communication clarity, data-driven insights, and objective mediation. The study emphasizes the potential of AI in fostering team cohesion through enhanced emotional intelligence, sentiment analysis, and automated conflict identification. Furthermore, it examines the ethical considerations, challenges, and future trends of AI integration, highlighting its ability to facilitate personalized, scalable, and proactive conflict resolution strategies. This research underscores AI's capacity to revolutionize virtual team management, enabling productive collaboration in an increasingly digital and globalized work environment.

Synergistic enhancement of photoluminescence and advanced deep learning model through YOLOv8x in combined effects of carbon dots and Sr₉Al₆O₁₈:Sm³⁺ phosphors

A series of orange-red-emitting Sr₉Al₆O₁₈:Sm³⁺ (1–11 mol %) phosphors are synthesized using the combustion method, while carbon dots (CDs) are produced from urea and citric acid. The incorporation of CDs into the Sr₉Al₆O₁₈:Sm³⁺ (SAO:Sm3+) matrix reduced both negative and positive defects, enhancing the crystallinity of the phosphor. A significant spectral overlap is observed between the emission of CDs and the absorption of SAO:Sm³⁺. An 11.9-folds enhancement in luminescence intensity is detected from the 5 wt% CDs@SAO:Sm³⁺ composite, along with an extended fluorescence lifetime. The energy transfer between CDs and Sm³⁺ is demonstrated, with the increased PL intensity attributed to the Förster Resonance Energy Transfer (FRET) mechanism. The CDs@SAO:Sm³⁺ composites demonstrated excellent selectivity and high contrast when developing latent fingerprints (LFPs). Level I–III structural characteristics of LFPs are easily recognized under ulta violet (UV) light. Furthermore, YOLOv8x, an effective deep learning model, has been modified for the important forensic science task of LFPs recognition. YOLOv8x is able to precisely locate LFPs in complex backgrounds by employing the real-time object detection capabilities of the architecture. With this adjusting, detection speed and accuracy are much increased, making it an effective tool for forensic analysis and law enforcement applications. The optimized orange-red-emitting CDs@SAO:Sm³⁺ composites is synthesized with soluble polyvinyl alcohol (PVA) to produce a transparent anti-counterfeiting ink. The resulting film exhibited excellent flexibility, foldability, and superior thermal and optical properties. In summary, the highly efficient CDs@SAO:Sm³⁺ composite is a versatile luminescent material with multifunctional capabilities, making it ideal for flexible films, LFPs detection, and white light-emitting diodes (w-LEDs) applications.

FL-YOLOv8: Lightweight Object Detector Based on Feature Fusion

In recent years, anchor-free object detectors have become predominant in deep learning, the YOLOv8 model as a real-time object detector based on anchor-free frames is universal and influential, it efficiently detects objects across multiple scales. However, the generalization performance of the model is lacking, and the feature fusion within the neck module overly relies on its structural design and dataset size, and it is particularly difficult to localize and detect small objects. To address these issues, we propose the FL-YOLOv8 object detector, which is improved based on YOLOv8s. Firstly, we introduce the FSDI module in the neck, enhancing semantic information across all layers and incorporating rich detailed features through straightforward layer-hopping connections. This module integrates both high-level and low-level information to enhance the accuracy and efficiency of image detection. Meanwhile, the structure of the model was optimized and designed, and the LSCD module is constructed in the detection head; adopting a lightweight shared convolutional detection head reduces the number of parameters and computation of the model by 19% and 10%, respectively. Our model achieves a comprehensive performance of 45.5% on the COCO generalized dataset, surpassing the benchmark by 0.8 percentage points. To further validate the effectiveness of the method, experiments were also performed on specific domain urine sediment data (FCUS22), and the results on category detection also better justify the FL-YOLOv8 object detection algorithm.

Improved real-time object detection method based on YOLOv8: a refined approach

Improved real-time object detection method based on YOLOv8: a refined approach

YOLOv8-GDCI: Research on the Phytophthora Blight Detection Method of Different Parts of Chili Based on Improved YOLOv8 Model

Smart farms are crucial in modern agriculture, but current object detection algorithms cannot detect chili Phytophthora blight accurately. To solve this, we introduced the YOLOv8-GDCI model, which can detect the disease on leaves, fruits, and stem bifurcations. The model uses RepGFPN for feature fusion, Dysample upsampling for accuracy, CA attention for feature capture, and Inner-MPDIoU loss for small object detection. In addition, we also created a dataset of chili Phytophthora blight on leaves, fruits, and stem bifurcations, and conducted comparative experiments. The results manifest that the YOLOv8-GDCI model demonstrates outstanding performance across a gamut of comprehensive indicators. In comparison with the YOLOv8n model, the YOLOv8-GDCI model demonstrates an improvement of 0.9% in precision, an increase of 1.8% in recall, and a remarkable enhancement of 1.7% in average precision. Although the FPS decreases slightly, it still exceeds the industry standard for real-time object detection (FPS &gt; 60), thus meeting the requirements for real-time detection.

Evaluasi Trade-off Akurasi dan Kecepatan YOLOv5 dalam Deteksi Kebakaran pada Edge Devices

Real-time object detection using the YOLO (You Only Look Once) algorithm has shown promising performance in various computer vision applications. However, its application on devices with limited resources is still a challenge due to its high computational requirements. This study aims to optimize the YOLOv5 model for fire and smoke detection on Orange Pi Zero 3 devices using quantization techniques. Using a dataset of 2247 fire and smoke images, this study applies static quantization techniques to improve model efficiency. The methodology includes training of standard YOLOv5 models, conversion to ONNX format, and application of static quantization. Results show a significant improvement in computational efficiency, with a 42.2% reduction in model size and a 65.21% increase in inference speed. Despite a decrease in the mAP value by 25.6%, the optimized model was still able to perform object detection at a significantly higher speed. In conclusion, the quantization technique is effective in optimizing the YOLOv5 model for deployment on edge computing devices, despite the trade-off between speed and accuracy.

The analysis of comparison performed between the standard deep breathing approach and a strategy for denitrogenating patients prior to inducing general anesthesia

Most anesthesia professionals view denitrogenating as a crucial patient safety procedure that should be carried out before administering general anesthesia and creating a secure airway. According to studies, passive spontaneous mask ventilation for three to five minutes is inferior to four deep breaths over thirty seconds (the "four-breath technique") or eight deep breaths over sixty seconds (the "eight-breath technique"). Nevertheless, there aren't any published randomized studies assessing techniques to enhance deep breathing quality in a typical clinical situation during denitrogenation. This study aims to evaluate the effectiveness of a typical coaching technique with a biofeedback strategy to improve deep breathing volumes during denitrogenation. Two groups participated in this hypothetical experimental study: the Control group (N = 11) and the Investigational group (N = 11). Four conventional deep breaths (DBs) were used to prenitrogenate both groups at the beginning. Four more DBs were completed by Control individuals utilizing the conventional coaching method. On the other hand, the patients in the experimental group received increasing DB objectives in real time using a biofeedback technique, with four breaths after each of the first four DBs. When comparing the volume of DBs 5 to 8 (p=0.005) between the Investigational group and the controls, there was a statistically significant increase. DB 5 to 8 in the experimental subjects more closely approximated the projected VC when the volume of each DB was compared to the participants' predicted VC (p=0.002). In summary, when employing a breath-to-breath biofeedback technique instead of a conventional DB coaching technique, DB volumes are noticeably higher.

A Reparameterization Feature Redundancy Extract Network for Unmanned Aerial Vehicles Detection

In unmanned aerial vehicles (UAVs) detection, challenges such as occlusion, complex backgrounds, motion blur, and inference time often lead to false detections and missed detections. General object detection frameworks encounter difficulties in adequately tackling these challenges, leading to substantial information loss during network downsampling, inadequate feature fusion, and being unable to meet real-time requirements. In this paper, we propose a Real-Time Small Object Detection YOLO (RTSOD-YOLO) model to tackle the various challenges faced in UAVs detection. We further enhance the adaptive nature of the Adown module by incorporating an adaptive spatial attention mechanism. This mechanism processes the downsampled feature maps, enabling the model to better focus on key regions. Secondly, to address the issue of insufficient feature fusion, we employ combined serial and parallel triple feature encoding (TFE). This approach fuses scale-sequence features from both shallow features and twice-encoded features, resulting in a new small-scale object detection layer. While enhancing the global context awareness of the existing detection layers, this also enriches the small-scale object detection layer with detailed information. Since rich redundant features often ensure a comprehensive understanding of the input, which is a key characteristic of deep neural networks, we propose a more efficient redundant feature generation module. This module generates more feature maps with fewer parameters. Additionally, we introduce reparameterization techniques to compensate for potential feature loss while further improving the model’s inference speed. Experimental results demonstrate that our proposed RTSOD-YOLO achieves superior detection performance, with mAP50/mAP50:95 reaching 97.3%/51.7%, which represents improvement of 3%/3.5% over YOLOv8, and 2.6%/0.1% higher than YOLOv10. Additionally, it has the lowest parameter count and FLOPs, making it highly efficient in terms of computational resources.

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

Advancing Indoor Epidemiological Surveillance: Integrating Real-Time Object Detection and Spatial Analysis for Precise Contact Rate Analysis and Enhanced Public Health Strategies.

In response to escalating concerns about the indoor transmission of respiratory diseases, this study introduces a sophisticated software tool engineered to accurately determine contact rates among individuals in enclosed spaces-essential for public health surveillance and disease transmission mitigation. The tool applies YOLOv8, a cutting-edge deep learning model that enables precise individual detection and real-time tracking from video streams. An innovative feature of this system is its dynamic circular buffer zones, coupled with an advanced 2D projective transformation to accurately overlay video data coordinates onto a digital layout of the physical environment. By analyzing the overlap of these buffer zones and incorporating detailed heatmap visualizations, the software provides an in-depth quantification of contact instances and spatial contact patterns, marking an advancement over traditional contact tracing and contact counting methods. These enhancements not only improve the accuracy and speed of data analysis but also furnish public health officials with a comprehensive framework to develop more effective non-pharmaceutical infection control strategies. This research signifies a crucial evolution in epidemiological tools, transitioning from manual, simulation, and survey-based tracking methods to automated, real time, and precision-driven technologies that integrate advanced visual analytics to better understand and manage disease transmission in indoor settings.