IPTV Research Articles

Workpiece Pose Classification Framework for Flexible Part Feeding Systems Using Machine Learning and Synthetic Datasets

In previous work, a concept for a novel flexible part feeding system based on aerodynamic feeding was presented. In contrast to conventional part feeding systems, such as vibratory bowl feeders, aerodynamic part feeding systems use controlled pressurized air jets to reorient the workpieces. The proposed concept aims to increase flexibility and eliminate retooling times to meet the challenges of modern automated production with regard to increasing uncertainties, shorter product life cycles and higher cost pressure. Regarding these objectives, the determination of the workpiece poses in the feeding system requires flexible image processing, which will be enabled using machine learning and synthetic datasets.This work presents a framework which enables the classification of workpiece poses using a standard industrial camera and convolutional neural networks (CNN). The training of CNNs usually requires large datasets. However, in order to eliminate the need to create and label datasets of real images, which would cause machine downtimes and increase the retooling effort, the CNNs will be trained with synthetic datasets. Based on the CAD-data of the workpieces, artificial images of each pose are rendered using the open source engine Blender. Several CNN architectures are selected, trained with the artificial datasets and evaluated using real images of the workpieces. The results show that high classification accuracies of over 99 % can be achieved. It is concluded that the presented approach enables the classification of workpiece poses with high accuracy, while eliminating the need for the cumbersome creation of real image datasets. The approach is not limited to the use in the aerodynamic part feeding system but can be transferred to other applications in which the orientation of a workpiece has to be classified.

Creation of a High-Precision, Single-Board Computer-Based Intelligent Passenger Counting System

This paper introduces research aimed at developing and implementing an intelligent passenger counting system in public transportation. The goal is to enhance fare evasion control and reduce financial losses for transit operators by automatically monitoring the entering and exiting of passengers. Utilizing the advanced capabilities of YOLO and DeepSORT algorithms, the system demonstrates high accuracy in detecting and tracking passengers, even in congested scenarios. Practical experiments have highlighted several challenges, including real-time frame processing rates, single-board computer performance, and the accuracy of passenger counts. It was discovered that the selection and positioning of USB cameras significantly influence system efficiency. Notably, changing the IP cameras to USB cameras significantly improves the processing speeds. A dataset containing images was created to improve the YOLO model's accuracy in detecting passengers. This dataset was particularly relevant considering the winter season, where identifying passengers could be challenging due to their bulky outerwear. To upgrade the performance of the DeepSORT system, the YOLO model was also improved with the pre-designed dataset to focus solely on the heads. This trained model achieved a recognition accuracy of 91% during peak hours. During periods of lighter traffic, when there were fewer passengers, the accuracy increased further due to reduced interference and higher precision. To enhance real-time processing efficiency, this research incorporates the status of public transport doors as a key parameter. By optimizing the number of frames forwarded to the YOLO algorithm for processing, we ensure that the system maintains accuracy without compromising on speed. Future development will focus on incorporating depth-sensing cameras and developing advanced data analysis algorithms for real-time processing on single-board computers. This will further enhance the precision of passenger counts during high-traffic periods. Expected benefits of this project include more efficient transport route planning, better management of passenger flows, improved rider satisfaction, and more effective measures against fare evasion.

Smart railways: the design and construction of an autonomous inspection and maintenance vehicle

The Railway Inspection and Maintenance Vehicle (RIMV) is a state-of-the-art autonomous ground robot for the railway environment. The robot has specialised hardware tailored for specific functionalities, ensuring optimal performance in its designated tasks. It incorporates a GPS, IMU, and encoder for robust localisation, and it integrates a LiDAR system and a depth camera for collision avoidance. Prioritising safety, the RIMV features an IP camera for real-time environmental monitoring and is equipped with emergency stop mechanisms. An Ubuntu Linux machine manages the robot’s data processing, complemented by a 5G Wi-Fi router for remote monitoring and operation when necessary. ROS2 is the primary platform for robot operations, standing out for its open-source solution and enhanced cybersecurity features. We validated the RIMV in a heritage railway setting with an ultrasonic inspection kit to detect rail-track defects. Beyond this specific application, the RIMV is versatile and designed to serve as a platform for other autonomous inspection and maintenance tasks within the railway sector. Its adaptability highlights its potential to enhance efficiency and safety in railway maintenance, offering invaluable assistance to human operators across varied scenarios.

Indoor Group Identification and Localization Using Privacy-Preserving Edge Computing Distributed Camera Network.

Social interaction behaviors change as a result of both physical and psychiatric problems, and it is important to identify subtle changes in group activity engagements for monitoring the mental health of patients in clinics. This work proposes a system to identify when and where group formations occur in an approximately 1700 m2 therapeutic built environment using a distributed edge-computing camera network. The proposed method can localize group formations when provided with noisy positions and orientations of individuals, estimated from sparsely distributed multiview cameras, which run a lightweight multiperson 2-D pose detection model. Our group identification method demonstrated an F1 score of up to 90% with a mean absolute error of 1.25 m for group localization on our benchmark dataset. The dataset consisted of seven subjects walking, sitting, and conversing for 35 min in groups of various sizes ranging from 2 to 7 subjects. The proposed system is low-cost and scalable to any ordinary building to transform the indoor space into a smart environment using edge computing systems. We expect the proposed system to enhance existing therapeutic units for passively monitoring the social behaviors of patients when implementing real-time interventions.

Simultaneous Coverage and Mapping of Stereo Camera Network for Unknown Deformable Object

Simultaneous Coverage and Mapping of Stereo Camera Network for Unknown Deformable Object

An Extrinsic Calibration Method for Multiple Infrastructure RGB-D Camera Networks With Small FOV

An Extrinsic Calibration Method for Multiple Infrastructure RGB-D Camera Networks With Small FOV

Stand up and be counted: Using traffic cameras to assess voting behavior in real time

Despite their ubiquity, few have used traffic camera networks for social science research. Using 1,312,977 images collected from 768 London-based cameras leading up to the 2015 UK general election, this study not only demonstrates how traffic camera data can be used to effectively measure same-day turnout, but we also provide ways such data can be used to assess political behavior more broadly. Such automated enumeration is especially important in countries where official results are only returned for the current election, making it difficult for those interested in assessing turnout at lower levels of aggregation, even when those elections are next on the calendar. Although we are not the first to suggest the value of images-as-data, this study hopes to underline the importance of video-as-data, while simultaneously offering an important foundation for future research.

Rancang Bangun Sistem Informasi Timbangan Digital Menggunakan Metode Waterfall Berbasis Desktop

A weighing bridge is a series of equipment used to weigh goods vehicles or trucks. This equipment can be installed permanently or portable. On the weighing bridge there are several bridges that are used for weighing so as not to exceed the load, but in this research the weighing bridge in question is for weighing goods in the form of cardboard, materials, etc., this weighing bridge still does not use an application or is still recording manually, therefore This research aims to design a weighing bridge application using digital scales and an IP Cam. This research has a tool to connect the load cell to the application, namely RS232. The development of this application uses the waterfall method, and this research has its own research methodology and stages which are similar to the waterfall method. The application design uses the VB.NET programming language and SQLServer database. This application has several features, namely that it can record data from weighings, automatically the weighing value appears and can take pictures from CCTV on the weighing bridge for data proof that the data that has been entered is correct. From the methods that have been used in this research, they have been successful in designing applications, success can be seen from testing and applying the methodology chosen from this research. The test used in this research is BlackBox testing.

An AI-based Image Recognition System for Early Detection of Forest and Field Fires

Forest fires and field fires (agricultural areas, grasslands, etc.) have severe global implications, causing significant environmental and economic harm. Traditional fire detection methods often rely on human personnel, which can pose safety risks and reduce their efficiency in large-scale monitoring. There is an urgent need for real-time fire detection technology to address these challenges and minimize losses. In this research, we propose the utilization of artificial intelligence techniques, specifically Deep Learning with Convolutional Neural Networks (CNN), to tackle this issue. Our proposed system analyzes real-time images captured by IP cameras and stored on a cloud server. Its primary objective is to detect signs of fires and promptly notify users through a mobile application, ensuring timely awareness. We meticulously assembled a dataset to train our model by merging three existing datasets comprising both fire and non-fire images. Also, we incorporated images that could potentially be misinterpreted as fire, such as red trees, individuals wearing red clothing, and red flags. Furthermore, we supplemented the dataset with images of unaffected areas obtained from online sources. The final dataset consisted of 1,588 fire images and 909 non-fire images. During evaluations, our model achieved an accuracy of 93.07%. This enables effective detection, thus rapid intervention and damage reduction. It is a proactive and preventive solution to combat these devastating fires.

Time-of-Day and Day-of-Week Effects on TV and OTT Media Choices: Evidence from South Korea

The objective of this manuscript is to investigate the determinants influencing the selection of over-the-top (OTT) platforms as opposed to traditional television mediums—cable, Internet protocol television (IPTV), and satellite broadcasting—for the consumption of content such as television shows and films. Employing data extracted from the 2020 Media Panel comprising 423,851 observations garnered from personal media diaries, this study scrutinizes the impacts of individual attributes, environmental conditions, and temporal factors on platform choice. The findings reveal a temporal influence characterized by a “Friday effect” and a heightened preference for OTT platforms during early afternoon (12:00–16:00) and late-night hours (00:00–04:00). Notably, the likelihood of selecting OTT platforms is significantly augmented during the late-night period in comparison to other time frames. In relation to individual characteristics, variables such as male gender, younger age, higher educational attainment, and elevated income levels were positively correlated with a predilection for OTT platforms. Additionally, environmental variables such as possession of an unlimited data plan and ownership of a tablet personal computer also emerged as significant predictors for OTT preference. Furthermore, the presence of a beam projector during late-night hours and residing in a household with multiple occupants during afternoon hours also served as contributing factors for OTT utilization. In conclusion, the study offers critical insights for stakeholders in both traditional television and burgeoning OTT markets, providing data-driven recommendations for the strategic allocation of resources in consideration of day-of-week and time-of-day variables.

Comparative analysis of passive optical networks using multiple parameters: a review

Abstract The desideratum for high-end communication networks and high-speed data transfer has surged exorbitantly in the contemporary era. To meet this demand, various optical access network technologies have been invented and assembled, including gigabit passive optical networks (GPON), Ethernet passive optical networks (EPON), and wavelength multiplexed passive optical networks (WDM-PON). Due to their huge bandwidth capacity, excellent compatibility, dynamic bandwidth allocation, and dispersion tolerance, these technologies constitute potential substitutes for imparting local loop broadband services. This paper presents a thorough review and comparative analysis of the contemporary evolution in optical access network technologies with an accentuate on their functionality, mechanism, manoeuvre, and applications. We are also looking at the upcoming development of these innovations, including the incorporation of 100 G-EPON connectivity to meet the enhanced bandwidth demands precipitated by IP video, mobile broadband, and the Internet of things (IoT).

Event detection system for the penitentiary institutions using multimodal data and deep networks

The aim of the paper is to present the distributed system for the unwanted event detection regarding inmates in the closed penitentiary facilities. The system processes large number of data streams from IP cameras (up to 180) and performs the event detection using Deep Learning neural networks. Both audio and video streams are processed to produce the classification outcome. The application-specific data set has been prepared for training the neural models. For the particular event types 3DCNN and YOLO architectures have been used. The system was thoroughly tested both in the laboratory conditions and in the actual facility. Accuracy of the particular event detection is on the satisfactory level, though problems with the particular events have been reported and will be dealt with in the future.

Mathematical Camera Array Optimization for Face 3D Modeling Application.

Camera network design is a challenging task for many applications in photogrammetry, biomedical engineering, robotics, and industrial metrology, among other fields. Many driving factors are found in the camera network design including the camera specifications, object of interest, and type of application. One of the interesting applications is 3D face modeling and recognition which involves recognizing an individual based on facial attributes derived from the constructed 3D model. Developers and researchers still face difficulty in reaching the required high level of accuracy and reliability needed for image-based 3D face models. This is caused among many factors by the hardware limitations and imperfection of the cameras and the lack of proficiency in designing the ideal camera-system configuration. Accordingly, for precise measurements, we still need engineering-based techniques to ascertain the specific level of deliverables quality. In this paper, an optimal geometric design methodology of the camera network is presented by investigating different multi-camera system configurations composed of four up to eight cameras. A mathematical nonlinear constrained optimization technique is applied to solve the problem and each camera system configuration is tested for a facial 3D model where a quality assessment is applied to conclude the best configuration. The optimal configuration is found to be a 7-camera array, comprising a pentagon shape enclosing two additional cameras, offering high accuracy. For those who prioritize point density, a 9-camera array with a pentagon and quadrilateral arrangement in the X-Z plane is a viable choice. However, a 5-camera array offers a balance between accuracy and the number of cameras.

Deep learning to extract the meteorological by-catch of wildlife cameras.

Microclimate-proximal climatic variation at scales of metres and minutes-can exacerbate or mitigate the impacts of climate change on biodiversity. However, most microclimate studies are temperature centric, and do not consider meteorological factors such as sunshine, hail and snow. Meanwhile, remote cameras have become a primary tool to monitor wild plants and animals, even at micro-scales, and deep learning tools rapidly convert images into ecological data. However, deep learning applications for wildlife imagery have focused exclusively on living subjects. Here, we identify an overlooked opportunity to extract latent, ecologically relevant meteorological information. We produce an annotated image dataset of micrometeorological conditions across 49 wildlife cameras in South Africa's Maloti-Drakensberg and the Swiss Alps. We train ensemble deep learning models to classify conditions as overcast, sunshine, hail or snow. We achieve 91.7% accuracy on test cameras not seen during training. Furthermore, we show how effective accuracy is raised to 96% by disregarding 14.1% of classifications where ensemble member models did not reach a consensus. For two-class weather classification (overcast vs. sunshine) in a novel location in Svalbard, Norway, we achieve 79.3% accuracy (93.9% consensus accuracy), outperforming a benchmark model from the computer vision literature (75.5% accuracy). Our model rapidly classifies sunshine, snow and hail in almost 2 million unlabelled images. Resulting micrometeorological data illustrated common seasonal patterns of summer hailstorms and autumn snowfalls across mountains in the northern and southern hemispheres. However, daily patterns of sunshine and shade diverged between sites, impacting daily temperature cycles. Crucially, we leverage micrometeorological data to demonstrate that (1) experimental warming using open-top chambers shortens early snow events in autumn, and (2) image-derived sunshine marginally outperforms sensor-derived temperature when predicting bumblebee foraging. These methods generate novel micrometeorological variables in synchrony with biological recordings, enabling new insights from an increasingly global network of wildlife cameras.

A CRITICAL ANALYSIS OF INTERNAL RELIABILITY FOR UNCERTAINTY QUANTIFICATION OF DENSE IMAGE MATCHING IN MULTI-VIEW STEREO

Abstract. Nowadays, photogrammetrically derived point clouds are widely used in many civilian applications due to their low cost and flexibility in acquisition. Typically, photogrammetric point clouds are assessed through reference data such as LiDAR point clouds. However, when reference data are not available, the assessment of photogrammetric point clouds may be challenging. Since these point clouds are algorithmically derived, their accuracies and precisions are highly varying with the camera networks, scene complexity, and dense image matching (DIM) algorithms, and there is no standard error metric to determine per-point errors. The theory of internal reliability of camera networks has been well studied through first-order error estimation of Bundle Adjustment (BA), which is used to understand the errors of 3D points assuming known measurement errors. However, the measurement errors of the DIM algorithms are intricate to an extent that every single point may have its error function determined by factors such as pixel intensity, texture entropy, and surface smoothness. Despite the complexity, there exist a few common metrics that may aid the process of estimating the posterior reliability of the derived points, especially in a multi-view stereo (MVS) setup when redundancies are present. In this paper, by using an aerial oblique photogrammetric block with LiDAR reference data, we analyze several internal matching metrics within a common MVS framework, including statistics in ray convergence, intersection angles, DIM energy, etc. We associate these metrics to the per-point errors evaluated through LiDAR reference data and discuss their potential contributions in estimating internal reliabilities of point clouds derived from DIM algorithms. The experimental results show that ray convergence and DIM energy are relevant indicators for the accuracy of the generated point clouds. Initial investigation shows that these two indicators could be further utilized to infer the measurement errors without reference data, which could potentially estimate the reliabilities of point clouds through error propagation.

EFFICIENT UAV FLIGHT PLANNING FOR LOD2 CITY MODEL IMPROVEMENT

Abstract. Geometric errors in LoD2 building models can be caused by the modeling algorithm but are often related to the quality of input data. One approach to tackling the modeling errors caused by the quality of input data is to collect additional data with a UAV and remodel the buildings. However, no flight planning approach exists specifically designed for efficient data recollection for model improvement. In this paper, we propose an innovative flight planning approach for this purpose. Contrary to the conventional method that recollects the data covering the entire building roof, our approach only collects the data over the erroneous region and uses it to improve the erroneous model part later. Our algorithm utilizes the existing LiDAR survey data to automatically detect model errors and design the camera networks by considering the roof geometry. We optimize the trajectory that connects the viewpoints with a genetic algorithm and develops an obstacle avoidance function with ray-casting to ensure a collision-free path. The proposed flight plan is implemented in a real-world scene. Our result shows an improved point cloud created through dense image matching with the collected UAV image data. The generated point cloud is successfully used for creating partial building models for improving the original models.

Smart Traffic Management System

With the rapid urbanization and increasing vehicular density in modern cities, the demand for efficient and intelligent traffic management systems has become paramount. This paper presents a comprehensive overview of a Smart Traffic Management System (STMS) designed to optimize traffic flow, enhance safety, and minimize congestion in urban areas. The STMS leverages advanced technologies such as artificial intelligence, sensor networks, and data analytics to create a dynamic and adaptive traffic control infrastructure. The key components of the proposed system include real-time traffic monitoring, predictive analytics, and adaptive signal control. Utilizing a network of sensors, cameras, and other data sources, the STMS continuously gathers information on traffic conditions, identifying patterns and potential issues. This data is then processed through machine learning algorithms to predict traffic trends, enabling proactive management strategies. One of the innovative features of the STMS is its adaptive signal control mechanism. Traditional traffic signal timings are often static and fail to respond promptly to changing conditions. The STMS, however, dynamically adjusts signal timings based on real-time traffic data, optimizing traffic flow and minimizing delays. This adaptability is further enhanced by the integration of vehicle-to-infrastructure (V2I) communication, allowing direct communication between vehicles and the traffic management system. Additionally, the STMS incorporates intelligent decision-making algorithms to prioritize emergency vehicles, public transportation, and other critical services. This ensures a swift and efficient response to emergencies while maintaining overall traffic efficiency. Furthermore, the system includes a user-friendly interface accessible through mobile applications and web platforms. This interface provides real-time traffic updates, alternative route suggestions, and other relevant information to empower commuters with the knowledge needed to make informed travel decisions. The implementation of the Smart Traffic Management System holds the potential to revolutionize urban mobility by significantly reducing travel times, fuel consumption, and environmental impact. This paper discusses the underlying technologies, design considerations, and potential benefits of the STMS, highlighting its role in creating smarter and more sustainable urban transportation networks

COLOR-INDEX DETERMINATION OF LEO SATELLITES USING COLOR IP-CAMERAS

The study is devoted to determining the color characteristics of the structural surfaces of artificial satellites. Observations of satellites were carried out in automatic mode using software for detection fast moving object, developed at RI “MAO”. The satellite observations equipment consists of Canon EF 85mm f/1.8 USM photographic lens and professional VIVOTEK IP816A-HP network camera. The camera is directed to the zenith and has a field of view (4.9°х2.8°). The camera has progressive CMOS sensor with Bayer color filter⁰₀ array for producing RGB color image. Coordinate and photometric processing of saved images is carried out using SExtractor and Astrometry.net software along with additional Python scripts. In this paper, we present first results of our LEO satellites observations using network IP-cameras with RGB Bayer filter. To convert the instrumental magnitudes from RGB Bayer system into standard bp/rp magnitudes of the Gaia EDR3 photometric system, a system of equations was solved, where the calculated magnitudes in the bp/rp photometric system were represented as functions of magnitudes and colors in the instrumental RGB system. The mean differences between the calculated magnitudes and the catalog magnitudes are (0.03±0.15)mag and (0.01±0.16)mag for bp and rp band, respectively. The calculated Brjb_bp and Rrjb_rp magnitudes using obtained transformation coefficients show a good linear correlation with the bp and rp Gaia EDR3 magnitudes. Only main sequence’s stars in the range of (5-13)mag were used as reference stars for determining the transformation coefficients. The results of determining the color indexes (Brjb_bp - Rrjb_rp) for 8 LEO satellites with the obtained transformation coefficients were received. The average accuracy of the obtained values of color indexes is about 0.2mag.

The optical, seismic, and infrasound signature of the March 5 2022, bolide over Central Italy

On March 5, 2022, a 12 kg meteoroid crossed the sky above Central Italy and was observed by three different observational systems: the PRISMA all-sky camera network (10 stations), the Italian national seismic network (61 stations), and a 4-element infrasound array. The corresponding datasets, each with its own resolution, provided three independent assessments of the trajectory, size and speed of the meteoroid. The bolide traveled across central Italy with an azimuth of 102 degrees, becoming visible at about 91 km above sea level with a velocity of about 15.4 km/s. Its visible trajectory lasted about 15 s. Reasonably, the residual portion of the ablated bolide terminated its path in the Adriatic Sea and could not be recovered. Seismic and infrasound data well match optical observations detecting the bolide Mach cone at 68 km above sea level with a back azimuth of 25 degrees with respect to the array. By comparing results from the three different systems, discrepancies are within the estimated uncertainties, thus confirming the mutual consistency of the adopted methodologies. Therefore, this study shows that different approaches can be integrated to improve the detection capability for bolide crossing the sky in monitored regions.

Multilinear subspace learning for Person Re-Identification based fusion of high order tensor features

Video surveillance image analysis and processing is an important field in computer vision and among the challenging tasks for Person Re-Identification (PRe-ID). The latter aims at finding a target person who has already been identified and appeared on a camera network using a powerful description of their pedestrian images. The success of recent research on person PRe-ID is largely backed into the effective features extraction and representation with a powerful learning of these features to correctly discriminate pedestrian images. To this end, two powerful features, Convolutional Neural Network (CNN) and Local Maximal Occurrence (LOMO) are modeled on a multidimensional data in the proposed method, High-Dimensional Feature Fusion (HDFF). Specifically, a new tensor fusion scheme is introduced to take advantage and combine two types of features in the same tensor data even if its dimensions are not the same. To improve the accuracy, we use Tensor Cross-View Quadratic Analysis (TXQDA) to perform multilinear subspace learning followed by the Cosine similarity for matching. TXQDA efficiently ensures the learning ability and reduces the high dimensionality resulting from high-order tensor data. The effectiveness of the proposed method is verified through experiments on three challenging widely-used PRe-ID datasets namely, VIPeR, GRID, and PRID450S. Extensive experiments show that the proposed method performs very well when compared with recent state-of-the-art methods.