Search Results (63)

Urban greening initiatives, including the incorporation of street trees, have been widely recognized for a variety of environmental benefits. However, their economic impact on retail, in particular, the impact of street trees on the visibility of signs, has been underexplored. Street trees can obscure retail signs, potentially reducing customer engagement and discouraging retailers from paying higher rents for such locations. This paper investigates how the blocking of retail signage by street trees affects monthly rent in developed commercial districts in Seoul. It identifies, through Google Street View and state-of-the-art deep-learning-based semantic segmentation methods, environmental elements such as street trees, sidewalks, and buildings; quantifies their proportions; and analyzes their impact on rent using OLS regression, controlling for socio-economic variables. The results reveal that rents significantly diminish when street trees blocking views of retail signs increase. Our findings require more nuanced consideration by planners and policymakers in balancing both environmental and economic demands toward sustainable street design and planning. Full article

Image segmentation is a foundation for autonomous driving frameworks that empower vehicles to explore and navigate their surrounding environment. It gives a fundamental setting to the dynamic cycles by dividing the image into significant parts like streets, vehicles, walkers, and traffic signs. Precise segmentation ensures safe navigation and the avoidance of collisions, while following the rules of traffic is very critical for seamless operation in self-driving cars. The most recent deep learning-based image segmentation models have demonstrated impressive performance in structured environments, yet they often fall short when applied to the complex and unpredictable conditions encountered in autonomous driving. This study proposes an Adaptive Ensemble Attention (AEA) mechanism within a Generative Adversarial Network architecture to deal with dynamic and complex driving conditions. The AEA integrates the features of self, spatial, and channel attention adaptively and powerfully changes the amount of each contribution as per input and context-oriented relevance. It does this by allowing the discriminator network in GAN to evaluate the segmentation mask created by the generator. This explains the difference between real and fake masks by considering a concatenated pair of an original image and its mask. The adversarial training will prompt the generator, via the discriminator, to mask out the image in such a way that the output aligns with the expected ground truth and is also very realistic. The exchange of information between the generator and discriminator improves the quality of the segmentation. In order to check the accuracy of the proposed method, the three widely used datasets BDD100K, Cityscapes, and KITTI were selected to calculate average IoU, where the value obtained was 89.46%, 89.02%, and 88.13% respectively. These outcomes emphasize the model’s effectiveness and consistency. Overall, it achieved a remarkable accuracy of 98.94% and AUC of 98.4%, indicating strong enhancements compared to the State-of-the-art (SOTA) models. Full article

The prevalence of car dependence and sedentary lifestyles has created concern in the transportation and health sectors. Walking is the most popular and practical kind of exercise that can significantly enhance health. In Chile, more than half of older adults have health issues and almost 72% of the elderly population never engages in physical activity. This study aims to investigate the relationship between older adults’ walking behavior and the built environment along the streets and parks in Santiago’s middle-income neighborhoods. Six medium-income central and pericentral neighborhoods of Santiago were selected. The average number of older persons who walk along the paths and two modified audit forms were used to measure walking behavior and built environment features, respectively. Both correlation analysis and backward regression were used to examine the associations. While elements like the existence of bus stops, pedestrian streets, and general cleanliness contribute to the enhanced number of older adults who walk along street segments, the presence of insecurity signs was found to be negatively associated with the number of older adults who walk in the neighborhood parks. Furthermore, complexity and mystery showed a negative association with the number of older adults in the neighborhood parks. Urban policymakers might use these findings to encourage older adults to walk more in Santiago’s medium-income neighborhoods. Full article

The quality of campus environments plays an important role in the mental health of college students. However, the impact of nighttime lighting in campus settings has received limited attention. This study examines how different landscape lighting conditions affect emotions and the perceived restorative potential, providing a mixed-method research framework to assess nighttime landscapes. The study was conducted on a section of campus roadway under three scenarios: daytime (cloudy conditions) and two nighttime settings (landscape lights and streetlights, and streetlights only). We employed wearable biosensors, visitor-employed photography tasks, affective mapping, interviews, and self-reports to comprehensively assess the participants’ emotional responses and perceptions. Statistical analyses, including the Friedman test, Wilcoxon signed-rank test, one-way ANOVA, Getis–Ord Gi* statistic and kernel density analysis, were used to evaluate differences in emotional and restorative perceptions across lighting scenarios. The results showed that nighttime environments with well-designed landscape lighting enhance the restorative potential more compared to street lighting alone and, in some cases, even surpass daytime settings. Skin conductance data, integrated with spatial–temporal trajectories and affective mapping, revealed clear patterns of emotional responses, emphasizing the role of lighting in shaping environmental quality. These findings provide actionable insights for architects and lighting designers to create nighttime landscapes that promote emotional well-being and restoration. Full article

Canine demodicosis is a contagious skin disease caused by the over-proliferation of Demodex mites in the host’s hair follicles. This study examines the prevalence, clinical signs, and hematological changes associated with demodicosis in street dogs of Rupandehi, Nepal. Between August 2023 and January 2024, 100 skin scrapings were collected from each street dog presenting dermatological symptoms. The samples, treated with 10% KOH and microscopically examined, revealed a 21% positivity rate for demodicosis, with all cases involving Demodex canis. The infection predominantly affected young puppies (37.5%), females (21.6%), mixed breeds (33.3%), and dogs with above-ideal body conditions (25%). There was no significant association between infection and variables such as age, gender, breed, or nutritional status. Clinically, all affected dogs exhibited alopecia, primarily on the legs. Hematological assessments indicated significant increases in neutrophils and eosinophils and a notable decrease in mean corpuscular hemoglobin concentration and lymphocytes among infected dogs (p < 0.05). This study underscores the importance of vigilant monitoring and comprehensive diagnostic practices in effectively managing and treating canine demodicosis, especially in street dogs. Full article

Addressing the traffic safety issues caused by pedestrian–vehicle conflicts during street crossing, this study proposes optimization strategies from both theoretical and technical perspectives. A safety braking distance model is introduced, taking into account pedestrians’ psychological safety and vehicle braking processes. Additionally, an active safety warning system for crosswalks has been designed. This system features a modular design, including detection, control, alarm, and wireless communication modules. It can monitor, in real-time, the positions and speeds of pedestrians and vehicles, assess potential conflicts between them under various scenarios, and implement different warning strategies accordingly. Compared to mainstream variable message sign (VMS) warning systems, this proposed system shows significant advantages in terms of section-weighted total delay metrics. Through simulations involving 3000 pedestrian crossings and comparative analyses of vehicle speed, pedestrian speed, vehicle deceleration rate, and accident numbers before and after the application of the active safety warning system, it was found that the critical accident rate indicator decreased from 0.27% to 0.06%. The results demonstrate that the system effectively provides bidirectional warnings to pedestrians and vehicles, significantly enhancing the safety of pedestrian street crossings. This research offers new insights into addressing pedestrian crossing safety issues. Full article

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. Full article

To address the challenge of quantitatively assessing the mentalization of emotions in color design schemes, this study uses Baidu Street View images and deep learning, integrates multi-source data, and innovatively constructs a color data model based on a comprehensive color indicator system for the quantitative assessment and visual representation of how the color environments of elementary school urban neighborhoods impact children’s mentalization of emotions. This model systematically incorporates physical color indicators, integrates elements such as perceptual frequency, and provides a novel perspective for color planning. The study’s results reveal that color metrics significantly impact children’s mentalization of emotions across multiple dimensions, with gender and age emerging as important influencing factors. Additionally, significant correlations were found between color and environmental elements such as building façades, roads, and signs. The study provides urban planners and architects with a practical color data model and recommendations for the revitalization of elementary school urban neighborhoods, offering a scientific basis for optimizing color design. Full article

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. Full article

Among the sensors necessary to equip vehicles with an autonomous driving system, there is a tacit agreement that cameras and some type of radar would be essential. The ability of radar to spatially locate objects (pedestrians, other vehicles, trees, street furniture, and traffic signs) makes it the most economical complement to the cameras in the visible spectrum in order to give the correct depth to scenes. From the echoes obtained by the radar, some data fusion algorithms will try to locate each object in its correct place within the space surrounding the vehicle. In any case, the usefulness of the radar will be determined by several performance parameters, such as its average error in distance, the maximum errors, and the number of echoes per second it can provide. In this work, we have tested experimentally the AWR1843 MIMO radar from Texas Instruments to measure those parameters. Full article

Over the coming years, the advancement of driverless transport systems for people and goods that are designed to be used on fixed routes will revolutionize the transportation system. Therefore, for a safe transportation system, detecting and recognizing traffic signals based on computer vision has become increasingly important. Deep learning approaches, particularly convolutional neural networks, have shown exceptional performance in various computer vision applications. The goal of this research is to precisely detect and recognize traffic signs that are present on the streets using computer vision and deep learning techniques. Previous work has focused on symbol-based traffic signals, where popular single-task learning models have been trained and tested. Therefore, several comparisons have been conducted to select accurate single-task learning models. For further improvement, these models are employed in a multi-task learning approach. Indeed, multi-task learning algorithms are built by sharing the convolutional layer parameters between the different tasks. Hence, for the multi-task learning approach, different experiments have been carried out using pre-trained architectures like, for instance, InceptionResNetV2 and DenseNet201. A range of traffic signs and traffic lights are employed to validate the designed model. An accuracy of 99.07% is achieved when the entire network has been trained. To further enhance the accuracy of the model for traffic signs obtained from the street, a region of interest module is added to the multi-task learning module to accurately extract the traffic signs available in the image. To check the effectiveness of the adopted methodology, the designed model has been successfully tested in real-time on a few Riyadh highways. Full article

Pedestrian crossings are an essential part of the urban landscape, providing safe passage for pedestrians to cross busy streets. While some are regulated by timed signals and are marked with signs and lights, others are simply marked on the road and do not have additional infrastructure. Nevertheless, the markings undergo wear and tear due to traffic, weather, and road maintenance activities. If pedestrian crossing markings are excessively worn, drivers may not be able to see them, which creates road safety issues. This paper presents a study of computer vision techniques that can be used to identify and classify pedestrian crossings. It first introduces the related concepts. Then, it surveys related work and categorizes existing solutions, highlighting their key features, strengths, and limitations. The most promising techniques are identified and described: Convolutional Neural Networks, Histogram of Oriented Gradients, Maximally Stable Extremal Regions, Canny Edge, and thresholding methods. Their performance is evaluated and compared on a custom dataset developed for this work. Insights on open issues and research opportunities in the field are also provided. It is shown that managers responsible for road safety, in the context of a smart city, can benefit from computer vision approaches to automate the process of determining the wear and tear of pedestrian crossings. Full article

A significant number of new metered parking systems have been introduced in recent years by the local authorities of various spa towns in Poland in connection with home zone conversion projects. The traffic signs posted in these locations were limited to the beginning and end of the demarcated parking area. Traffic circle (TC) is an example of a traffic calming measure (TCM) used in home zones to slow down the traffic (case study—home zone in a small spa village). This article presents the results of a study investigating the speed reductions obtained within a home zone and a traffic circle used as traffic calming measure. The indispensable speed surveys were carried out in relation to this study in two periods: in summer when the streets are crowded with tourists and in September with little pedestrian traffic. Two research hypotheses were formulated as part of the speed data analysis to verify the slowing effect of the traffic circle and the relevance of the traffic circle’s design parameters and location, road function and the surrounding streetscape. For each hypothesis, statistical analyses were carried out using two nonparametric tests: two-sample Kolmogorov–Smirnov test and median test. The third research hypothesis formulated in this study was related to sustainable development factors related to fuel consumption and traffic-related air pollution, including carbon dioxide, carbon monoxide, nitrogen oxide and hydrocarbons. This hypothesis was verified by estimating the amount of air pollution in the home zone under analysis in three different situations (scenarios): in summer with the travel speed reduced by pedestrian traffic to ca. 8–10 km/h, in September with a small number of pedestrians and 20–25 km/h resulting speed between traffic circles, reduced at the traffic circle, and in a theoretical 30 km/h zone with 25–30 km/h assumed speed between traffic circles, dropping at the traffic circle. These analyses confirmed the appropriateness of the traffic circle as a home zone traffic calming measure, as long as its design is based on a detailed analysis of the relevant factors, including location, road function and the surrounding streetscape. Full article

Against the backdrop of rising road traffic accident rates, measures to prevent road traffic accidents have always been a pressing issue in Taiwan. Road traffic accidents are mostly caused by speeding and roadway obstacles, especially in the form of rockfalls, potholes, and car crashes (involving damaged cars and overturned cars). To address this, it was necessary to design a real-time detection system that could detect speed limit signs, rockfalls, potholes, and car crashes, which would alert drivers to make timely decisions in the event of an emergency, thereby preventing secondary car crashes. This system would also be useful for alerting the relevant authorities, enabling a rapid response to the situation. In this study, a hierarchical deep-learning-based object detection model is proposed based on You Only Look Once v7 (YOLOv7) and mask region-based convolutional neural network (Mask R-CNN) algorithms. In the first level, YOLOv7 identifies speed limit signs and rockfalls, potholes, and car crashes. In the second level, Mask R-CNN subdivides the speed limit signs into nine categories (30, 40, 50, 60, 70, 80, 90, 100, and 110 km/h). The images used in this study consisted of screen captures of dashcam footage as well as images obtained from the Tsinghua-Tencent 100K dataset, Google Street View, and Google Images searches. During model training, we employed Gaussian noise and image rotation to simulate poor weather conditions as well as obscured, slanted, or twisted objects. Canny edge detection was used to enhance the contours of the detected objects and accentuate their features. The combined use of these image-processing techniques effectively increased the quantity and variety of images in the training set. During model testing, we evaluated the model’s performance based on its mean average precision (mAP). The experimental results showed that the mAP of our proposed model was 8.6 percentage points higher than that of the YOLOv7 model—a significant improvement in the overall accuracy of the model. In addition, we tested the model using videos showing different scenarios that had not been used in the training process, finding the model to have a rapid response time and a lower overall mean error rate. To summarize, the proposed model is a good candidate for road safety detection. Full article

This study determined citizens’ perceptions and impact factors of illuminated road signs installed to ensure their visibility at night when the risk of traffic accidents is high. An ordered logit model was used to measure illuminated road signs’ impact on drivers’ perception based on the data from the citizens’ survey conducted by the Road Sign Center. According to the results, the internal (optical fiber) type variable had the highest impact, followed by the frequent fog variable and the complex road line variable. This study found that most citizens positively recognized road signs, preferred internal (optical fiber) types, and desired illuminated road signs that considered climate, environment, and road structure types. In Seoul, the importance and improvement of illuminated road signs at points where road structures are complex, such as city streets, were high. Additionally, the illuminated road sign recognition and road type variable were significant in Gyeonggi-do, which reflected the high number of citizens that commute to Seoul from Gyeonggi-do. Concerning local cities and counties and intercity roads highly affected by the climate, the impact was high at points with frequent fog. Fog affects the visibility distance, generates condensation on signs, and significantly degrades visibility. Therefore, an illuminated road sign installation method must be presented based on spatial analysis for regions vulnerable to climate, environment, and road location. Additionally, the road intersection point variable was significant in local cities and counties, which reflects the relatively lagged road infrastructure. Local cities and counties are financially poor and have numerous aged drivers; hence, central government support that considers these aspects is crucial. Full article