Road Signs Research Articles

A real-time ghost machine learning model built on YOLOv8 for traffic road signs detection and classification in Germany

A real-time ghost machine learning model built on YOLOv8 for traffic road signs detection and classification in Germany

The material and immaterial in Lyotard, Benjamin and contemporary Indigenous art

ABSTRACT Powerful arguments have been made that art is moving from the material to the immaterial in an age of ‘virtual reality’ (Jean-François Lyotard). Equally powerful arguments have been put that it is moving from the immaterial to the material in an age of mechanical reproduction (Walter Benjamin). In this essay, we propose that the material and immaterial are inseparable, and that this is what both Lyotard and Benjamin are ultimately suggesting. This would go against those critics who claim that art is becoming too material (Clement Greenberg and Michael Fried), and they themselves can be seen to be admitting that this materiality is possible only because of a certain immateriality. In response to this, Rosalind Krauss’ notion of ‘post-medium’ can be read as an expression of the immateriality that allows the materiality of medium. We conclude by considering three examples of Australian Indigenous art that also point to the inseparability of the material and immaterial: the digital exhibition Connection, the street sign works of Yolngu artist Wanapati Yunupingu and the installation kith and kin by Kamilaroi Bigambul artist Archie Moore, recently exhibited at the Venice Biennale.

The risks of unconcern: low sensitivity to threat can have unfortunate consequences

Each one of us is confronted with warnings of danger or threats to wellbeing in our everyday life, whether in the form of certain road signs, Public Service Announcements, ominous changes in bodily functioning, or cautionary tales heard from family or friends. There is great inter-individual variation in how people respond to such threats, with some people habitually tending to ignore or dismiss them, often to their peril. The first purpose of the present paper is to review several studies showing that individuals—most often men—who score very low on measures of trait anxiety are more likely to engage in behaviors that could jeopardize their physical wellbeing. The general hypothesis that is derived from that review is that when attention to everyday threats is chronically muted by way of a dispositional trait, the likelihood of proceeding down some dangerous path is increased. Those findings are then discussed within the broader context of personality theory to highlight the importance of recognizing the bipolarity of common traits. Here the case is made for replacing the term trait anxiety with the term threat sensitivity in order to capture the full breadth of this basic personality variable. A discussion of the neurobiological underpinnings of threat sensitivity is then presented with an emphasis on individual and sex differences in the workings of the defensive survival circuitry. Taken together, this paper has implications for two subfields within psychology. For the area of personality theory, this paper provides support for the adaptationist view with the argument that low threat sensitivity has both adaptive and maladaptive potential. For the area of health psychology, it is argued that some individuals who demonstrate a habitual tendency to neglect their physical wellbeing may be acting—at least in part—in accordance with their innate neurobiological constitution.

Partnering with Communities to Understand Social Determinants of Health (SDoH) Impacts on Access to Shared Micromobility

This study explored the facilitators and barriers of community bike share use in a mid-sized city with high incidence of poverty and racial diversity using a community-based participatory action research (CBPAR) photovoice framework with the Stanford Our Voice (OV) Discovery Tool digital application. Community members participated in one of three community citizen science walks with follow up focus groups facilitated by osteopathic medical student researcher to address “What makes it easy or hard to ride a bike using the bike share?” Twenty-seven diverse community members partnered with four osteopathic medical students exploring vulnerable individuals’ lived experiences, beliefs/understanding of the Social Determinants of Health (SDoH) and access to the bike share program. A total of 322 photos and narrative comments from citizen science walk audits developed deductive themes and follow up focus groups informed inductive themes. Themes addressed challenges to access, maintenance, safety in bike transit, comfort, and environment that create barriers to use and increase inequities for lower income and historically underrepresented communities. The use of OV provided photograph, narrative, and geocoded photo location. This novel approach served as an effective tool for community action with city decision makers. The narrative research identified the impact of the barriers, and the photographs and geocoding provided clear descriptions for locations to prioritize change by adding street signs for access and safety, fixing road safety issues or bike maintenance concerns. It actively engaged the community with the city to drive discussions and plans for change in repair systems and infrastructure that also addressed equity and acknowledged the SDoH supporting residents in lower income or historically underrepresented communities. Citizen science engaged community voices, supporting change in city policies and transportation initiatives to support the sustainability of the bike share program.

Toowoomba Healthy Towns: A Citizen Science Initiative on Active Transport in Regional South East Queensland, Australia.

Engaging in active transport will enable individuals across the life course to increase their habitual levels of physical activity. The aim of this study was to engage citizen scientists (CS) to identify factors that influence active transport in their community. The Our Voice citizen science methodology developed at Stanford University was employed. CS completed a "discovery walk," taking photos of things that help or hinder active transport. Three groups were recruited: children aged 10-12years (n = 11), adults (n = 12), and older adults >65years (n = 10). CS rated each photo and provided a narrative explaining their reason for taking the photo. Once all CS in a specific age group had completed the walk, they met for a group discussion. The CS worked together to analyze the data, arranging them into themes and identifying priority actions. Two CS representatives from each age group presented their findings to the local council decision makers. Children highlighted the need for safer crossings, especially from their school to the local park, and suggested zebra crossings as a solution. The adults highlighted that road signs prioritized vehicles, not pedestrians, and requested that this be reversed. Older adults noted that the poor condition of the pavements made it harder for people in wheelchairs to navigate. The CS recommendations have informed the council's walking and cycling network program. Engaging with citizen science provided the community with an opportunity to advocate for meaningful yet realistic improvements in the built environment that could promote neighborhood active transport and physical activity across the lifespan.

Review on Lane Detection Techniques

Abstract—Lane detection in current automobiles is extremely popular; it has become an inseparable part of the vehicle’s set, as it is considered indispensable nowadays to prevent an accident and limit the risk of injury or even death on the road. This review article addresses some of the different systems of line measuring features and characteristics, strengths, and weaknesses. This article starts by reviewing the literature and showing the different methods, methods, and techniques that are employed in the research line. Then, it continues with the description of the main elements of the search line, such as camera, image processing algorithms, and alerts, regarding the variety of functions that may be embodied in a line lane search, such as lane departure warning, cruise control, and automatic emergency braking. Compared the advantages and disadvantages of various camera, radar-based and lidar-based line search methods and set a comparison of accuracy, reliability, cost, and performance in different driving styles. In this report, it also discusses challenges and limitations of line calling like bad weather conditions, road signs, and poor performance, along with the risks and disadvantages of over-reliance on lane detection of the vehicles. Index Terms—Lane detection, reliability, robustness, semantic splitting, effectiveness

‘Fighting for breath’: Inhabiting uninhabitable places

In 2021, clean-air activists Choked Up put up hacked road signs in the London neighbourhoods of Catford, Brixton and Whitechapel. The signs stated: ‘People of colour are more likely to live in an area with illegal pollution levels’. They also demanded ‘Clean air for all’. The following year, Breathe: 2022 by artist Dryden Goodwin was installed across the borough of Lewisham. Depicting people struggling to breathe, like the road signs, the delicate pencil-drawn images were a way of ‘making the invisible visible’. These interventions highlight both the elevated levels of air pollution in particular locations and the unevenness of its distribution. They also point to how places and bodies are interconnected in the air that ‘we’ breathe. Foregrounding this activism, this article draws on Nirmal Puwar’s conceptualisation of the ‘somatic norm’ whereby particular spaces are (or, rather, become) ‘reserved’ for particular bodies and, concomitantly, the ‘ontological anxiety’ provoked when bodies enter into spaces not meant for them. I extend Puwar’s work on Space Invaders in two ways. First, reading air quality research data through work which has theorised the spatial–bodily relationship, the article explores how the yoking together of spaces and bodies can serve to locate people in places which are not fit for habitation. Second, I draw attention to the highly corporeal and emotional ways in which these interconnections are manifested, and like the visceral registers of ‘ontological anxiety’, I consider what this might tell us about spatialised and bodied power relations. To render the asymmetries in air pollution exposure not only visible but sense-able, the article draws on a mobile, emplaced and embodied methodology of walking and cycling through London. The processes of moving, breathing and leaving put into relief both the deep fleshiness of spatial–bodily interconnections and the palpability of the power dynamics which permeate them.

Increasing Slow Learner Reading Abilities Through Functional Reading : A Single-Case Study on An Elementary School Student

This study explored the effectiveness of teaching functional literacy to a 12-year-old slow learner in Indonesia. The participant struggles read words longer than two syllables and struggles to meet academic expectations. This research uses a qualitative approach with the single-subject design using the reversal method or the ABA research design. Data was collected through three phases: baseline, intervention, and evaluation phases. This study utilizes two sets of flashcards as instruments. The first set consists of pictorial cards displaying twelve common street signs, while the second set contains word cards with the matching names of the signs in Bahasa Indonesia. Each card is printed on a 13 cm by 7 cm flashcard. Over the intervention sessions, the participant demonstrated significant progress in functional reading skills. The data collected was then analyzed using visual analysis. The results indicates that slow learners benefit from frequent, concrete, and visually based learning abilities that aligns for their need for repetition. This study highlights the importance of functional literacy in enhancing independent living skills among slow learners, providing the students with the tool to better navigate their surroundings.

SMALL OBJECT DETECTION APPROACH BASED ON ENHANCED SINGLE-SHOT DETECTOR FOR DETECTION AND RECOGNITION OF INDONESIAN TRAFFIC SIGNS

The detection and recognition of traffic signs are crucial components of advanced driving assistance systems (ADAS) that enhance road safety. Current traffic sign detection and recognition model technology is proficient in identifying and interpreting traffic signs. However, for accurate detection and recognition, the traffic sign in the image must be of a certain minimum pixel size or distance from the driver's sight line for proper detection. The ADAS system should be capable of detecting and recognizing road traffic signs from a considerable distance as they come into the driver's line of vision. The higher the vehicle speed, the greater the distance required for the sign to be detected and recognized, allowing the driver sufficient time to react according to the sign's meaning. Addressing these challenges, this research proposes an enhanced version of the single shot detector (SSD) algorithm, commonly used in object detection, to improve the algorithm's ability to detect small objects. The proposed method involves adding an auxiliary layer module to the original SSD architecture to increase the feature map resolution and expand the conventional layer's receptive space. With the Enhanced SSD algorithm, the detection capability of the SSD can be significantly enhanced in terms of accuracy. The limitations of this study are related to the influence of occlusion and clutter, which might affect the performance of object detection, especially for small objects, which are more susceptible to being influenced by various factors. The research results demonstrate that Enhanced SSD improves object detection accuracy compared to the original SSD, with a mean average precision (mAP) of 97.87 compared to 95.35 for detecting 21 traffic signs in Indonesia.

Recognition on the vital parts of the human body in traumatology, forensic medicine and acupuncture from Laoguanshan unearthed bamboo slips of metal-weapon-injury induced lethal symptoms

Eleven bamboo slips of metal-weapon-injury induced lethal symptoms, unearthed in Laoguanshan, reflect the understanding of the vital parts of human body by ancient medical masters. Through the longitudinal research of Laoguanshan unearthed bamboo slips of metal-weapon-injury induced lethal symptoms, and the handed-down literature on this aspect, the doubts remained have been clarified on the annotation and the interpretation of Laoguanshan medical bamboo slips; and the reliable road signs been discovered on the path for collating the sources of handed-down literature on metal-weapon injury, and this path had been failed to deepening. Through the horizontal comparison of metal-weapon injury with forensic medicine and acupuncture, it is found that the understanding of the vital parts of the human body, obtained through various ways in thousands of years, is highly agreed with among metal-weapon injury, forensic medicine and acupuncture, except for the differences in the terminology among different disciplines, and the discrepancy in ancient and modern literature because of the misunderstandings of the previous literature by later generations within the same discipline. Therefore, the multi-dimensional evidences have been obtained to support the recognition of the vital parts of the human body in traumatology, reflected in the Laoguanshan bamboo slips of metal-weapon-injury induced lethal symptoms. Additionally, the reliability of the relevant discipline theories, e.g. acupuncture and forensic examination, has been strongly confirmed. It provides a very typical case for solving major academic problems by applying the "dual-attestation method" to research unearthed and handed-down literature. Moreover, it explores a novel approach to the academic study of traditional Chinese medicine, especially to the effective communication among different disciplines.

DPF-YOLOv8: Dual Path Feature Fusion Network for Traffic Sign Detection in Hazy Weather

Traffic sign detection plays an integral role in intelligent driving systems. It was found that in real driving scenarios, traffic signs were easily obscured by haze leading to traffic sign detection inaccuracy in assisted driving systems. Therefore, we designed a traffic sign detection model for hazy weather that can effectively help drivers to recognize road signs and reduce the incidence of traffic accidents. A high-precision traffic sign detection network has been designed to address the problem of decreased model recognition performance caused by external factors such as small size of traffic signs and haze obstruction in real-world scenarios. First, the default YOLOv8 was found to have low model detection accuracy in hazy weather occlusion conditions through experimental studies. Therefore, a deeper lightweight and efficient multi-branch CSP (Cross Stage Partial) module was introduced. Second, a dual path feature fusion network was designed to address the problem of insufficient feature fusion due to the small size of traffic signs. Finally, in order to be able to better simulate the real haze weather scene, we added fog to the raw data to enrich the data samples. This was verified through experiments on a public Chinese traffic sign detection dataset after fogging treatment, compared to the default YOLOv8 model. The improved DPF-YOLOv8 algorithm achieved 2.1% and 2.2% improvement in mAP@0.5 and mAP@0.5:0.95 performance metrics to 65.0% and 47.4%, respectively.

A Robust TrafficSignNet Algorithm for Enhanced Traffic Sign Recognition in Autonomous Vehicles Under Varying Light Conditions

Recent years have witnessed significant advancements in machine perception, particularly in the context of self-driving vehicles. The accurate detection and interpretation of road signs by these vehicles are crucial for enhancing safety, intelligence, and efficiency on the roads. Consequently, there is a growing body of research dedicated to improving traffic sign recognition technologies, a key component of intelligent transportation systems. Annual statistics highlight numerous accidents attributable to factors such as excessive speed, variable lighting conditions, and the misinterpretation of traffic signs. In response to these challenges, a novel approach for the rapid and reliable recognition of traffic signs by moving vehicles has been developed. This approach leverages a custom dataset encompassing twelve object categories and seven subcategories, reflective of road sign diversities encountered in India. A specialized algorithm, TrafficSignNet, was devised to specifically identify signs related to speed, turning, zones, and bumps. This algorithm was trained on a comprehensive dataset comprising 4,962 images, with its performance evaluated using 705 images from real traffic scenarios. The evaluation demonstrates that the model achieves remarkable accuracy across various lighting conditions, processing up to 12 frames per second. This processing rate is compatible with the high-definition standards of contemporary vehicle cameras, which is 1280 × 720 pixels. The model's effectiveness is quantified through accuracy, precision, recall, and F1 score, with respective values of 0.985, 0.978, 0.964, and 0.971, showcasing its potential to significantly contribute to the advancement of smart transportation systems.

Black-Spot Identification from Ramol Cross Road to Kathwada Cross Road

Road accidents are a vital issue that is occurring all over the world. Accident severity is increasing with the exponential increase in vehicle population. Accident leads to disability, pain, suffering, grievous injuries, hospitalization expenditure, damage to health and property, social suffering, general degradation of the environment, and, in extreme cases, death. This study aims to identify black spots in the selected stretch involving four major intersections from Ramol crossroad to Kathwada crossroad of Ahmedabad. Data collection consists of collecting past accident data from traffic police station headquarters. The collected data are categorized into fatal accidents, grievous significant accidents, and minor accidents. The data is analyzed using the accident data collected, the Weighted Severity Index (WSI) method, and the PTV Visum software. WSI is estimated for the accident data for the year 2019-2023. By accident analysis, seven black spots were identified in this study. Inspecting the road stretch noted several issues and probable causes of accidents were identified. Poor road conditions, including cracks and potholes, affect road safety. Improper road markings and signs are one of the causes of accidents. The audited road stretch includes recommendations to prevent the number and severity of accidents.

Concepts of Reusing Wind Turbine Blades in Civil Engineering Constructions

Wind turbines have become an important source of renewable energy in recent years, but recycling them is difficult due to their material properties. The paper indicates the possibility of using turbine blades to produce elements that can be filled with concrete and used as members of small geotechnical structures: retaining walls, point and well foundations, foundations for railings, fences, road signs, etc., as well as excavation linings and shoring walls. In these solutions, concrete-filled elements of turbine blades constitute a form (formwork) for concrete, protecting it against environmental influences, and can also cooperate with concrete in transferring loads.

Aksi Nyata Mahasiswa KKN IAIN Palangka Raya: Membenahi Infrastruktur Desa Sumber Agung Melalui Pembuatan Plang Nama Jalan

Real Work Lecture (KKN) activities carried out by IAIN Palangka Raya students in Sumber Agung Village to improve village infrastructure through making and installing road signs. This program was motivated by observations which showed that many road signs were damaged or missing, which made navigation difficult for the public and visitors. By involving seven students, this activity not only improves regional accessibility and orientation, but also strengthens collaboration between students and the community. Implementation of this program involves coordination with village officials, site surveys, and fundraising, as well as receiving active support from village residents. It is hoped that with the new road signs, it will be easier for the community to carry out activities and recognize important locations in the village, as well as increase the sense of togetherness in efforts to advance the infrastructure of Sumber Agung Village.

Yasri Miftah Joenoes

Background: Mining accidents in truck transportation activities are the most common accidents in the mining industry in Southeast Sulawesi Province in the last 3 years and often cause fatalities. Previous studies have not identified all types of dominant causes of mining accidents in truck transportation activities, be it direct causes, basic causes, or lack of management control. The purpose of this study is to analyze the causes of mining accidents in truck transportation activities in the Southeast Sulawesi Region in 2021-2023. Method: The research used is qualitative phenomenology to understand and describe the dominant accident-causing factors from mining accident phenomena in transportation activities using trucks. Results: The dominant causes of mining accidents in truck transportation activities in Southeast Sulawesi Province in 2021-2023 were: driving above the speed limit; drivers not wearing safety belts and helmets; downhill road conditions with a grade above 12% and long; drivers lack knowledge/skills; lack of supervision; and inadequate SOP and HIRA. Conclusion: Corrective actions that can be taken to minimize the occurrence of mining accidents in truck transportation activities are: increasing supervision and socialization related to speed limits, as well as the use of safety belts and helmets; striving for engineering, maximizing supervision and completing road signs on downhill road segments with grades above 12% and long; implementing new worker training and annual refresher courses with output in the form of SIMPER which is valid for a maximum of 1 year; meeting the needs/ratio of operational supervisors, and ensuring that SOP and IBPR are adequate for truck transportation activities.

CNN MODEL FOR TRAFFIC SIGN RECOGNITION

The traffic sign recognition framework (TSRS) is an important component of intelligent transportation systems (ITS). Accurately identifying traffic signs can improve driving safety. This research provides a traffic sign recognition approach based on profound learning. It primarily focuses on the location and order of roundabout signs. First, a photograph undergoes pre-processing to highlight important facts. Hough Transform is used to distinguish and find regions. Finally, the unique street traffic signs are analyzed for further understanding. This paper proposes a photo handling-based traffic sign discovery and distinguishing proof technique that is combined with convolutional brain organization (CNN) to sort traffic signs. CNN is useful for recognizing many PC vision tasks due to its high recognition rate. TensorFlow is used to implement CNN. We have a recognition accuracy of over 98.2% for the roundabout image in the German informative collections. KEYWORDS——traffic sign recognition, traffic sign detection, deep learning, convolutional neural network

Quantum Transfer Learning with Adversarial Robustness for Classification of High‐Resolution Image Datasets

AbstractThe application of quantum machine learning to large‐scale high‐resolution image datasets is not yet possible due to the limited number of qubits and relatively high level of noise in the current generation of quantum devices. In this work, this challenge is addressed by proposing a quantum transfer learning (QTL) architecture that integrates quantum variational circuits with a classical machine learning network pre‐trained on ImageNet dataset. Through a systematic set of simulations over a variety of image datasets such as Ants & Bees, CIFAR‐10, and Road Sign Detection, the superior performance of the QTL approach over classical and quantum machine learning without involving transfer learning is demonstrated. Furthermore, the adversarial robustness of QTL architecture with and without adversarial training is evaluated, confirming that our QTL method is adversarially robust against data manipulation attacks and outperforms classical methods.

Object and Pedestrian Detection on Road in Foggy Weather Conditions by Hyperparameterized YOLOv8 Model

Connected cooperative and automated (CAM) vehicles and self-driving cars need to achieve robust and accurate environment understanding. With this aim, they are usually equipped with sensors and adopt multiple sensing strategies, also fused among them to exploit their complementary properties. In recent years, artificial intelligence such as machine learning- and deep learning-based approaches have been applied for object and pedestrian detection and prediction reliability quantification. This paper proposes a procedure based on the YOLOv8 (You Only Look Once) method to discover objects on the roads such as cars, traffic lights, pedestrians and street signs in foggy weather conditions. In particular, YOLOv8 is a recent release of YOLO, a popular neural network model used for object detection and image classification. The obtained model is applied to a dataset including about 4000 foggy road images and the object detection accuracy is improved by changing hyperparameters such as epochs, batch size and augmentation methods. To achieve good accuracy and few errors in detecting objects in the images, the hyperparameters are optimized by four different methods, and different metrics are considered, namely accuracy factor, precision, recall, precision–recall and loss.

Translation of signs and a renewed understanding of the post-pandemic cosmopolis: a diachronic study of street signs in the hybridised area of Guangzhou

ABSTRACT From a translational perspective, the researcher conducts a diachronic study of the changing street signs in one of the hybridised areas in Guangzhou. The street signs in the present study were investigated through an ethnographic process and were compared and discussed in relation to their changing contexts before and after the COVID-19 pandemic. The findings show a decrease in multilingual signs in the area post-pandemic time, which may indicate the influence of the pandemic on international visitors. In contrast, increasing monolingual Chinese signs exhibit the authorities’ reassertion of the dominant ideology and restoration of social order. On the other hand, however, a large number of bilingual and monolingual English signs in multifarious modes, among which many are from the business sectors in the 2023 corpus, may signal the open nature of an export-oriented economy in the area and recovery of international business after the pandemic. The changing translational landscape of the area constructs a gateway for us to renew our understanding of the influence of the pandemic on the cosmopolitan city and the relationship between language practice and the city.