Suburban Roads Research Articles

Hierarchical deep neural networks to detect driver drowsiness

Driver drowsiness is one of the main reasons for deadly accidents, especially on suburban roads. Researchers have used many methods for analyzing videos and detecting drowsiness, and the most up-to-date methods among them are using deep learning. This paper proposes a hierarchical framework comprising deep networks with split spatial and temporal phases referred to as hierarchical deep drowsiness detection (HDDD) network. The proposed method uses ResNet to detect the driver’s face, lighting condition, and whether the driver is wearing glasses or not. This phase also causes a significant increase in eyes and mouth detection percentage in the next stage. Afterward, the LSTM network is used to take advantage of temporal information between the frames. The average accuracy of the drowsiness detection system is reached 87.19 percent.

Use of the Safe System Assessment Framework as a Safety Key Performance Indicator

As part of the Northern and South-Eastern Suburban Roads Upgrade packages, Major Road Projects Victoria has sought to incorporate road safety metrics into the tender designs review process. The Australian Road Research Board adapted the Safe System Assessment Framework (Austroads 2016) to meet this need. Twelve road projects were assessed to provide baselines scores for the reference designs. The submitted tender designs will then be reassessed to provide an assessment of road safety in the designs. This work provided an extension in use of Safe System Assessment Framework as well as insight into current gaps in road safety design practice.

Heavy metal pollution of road dust in a city and its highly polluted suburb; quantitative source apportionment and source-specific ecological and health risk assessment

Sources of heavy metals (As, Cd, Co, Cr, Cu, Mn, Ni, Pb and Zn) in the road dust of Bandar Abbas city, Iran, and its west suburb were apportioned and the related source-specific ecological and health risks were assessed. The level of heavy metal pollution and the related ecological risk for suburban road dust (suburban RD) were far higher than those of urban RD. Accordingly, probabilistic health risk assessment showed no significant health risk in urban region but significant health risk in the suburb, especially for As with cancer risk above 10−4. Source apportionment using positive matrix factorization (PMF) identified lithogenic source (45.9%) and traffic emission (47.6%) as the main sources of heavy metals in urban and suburban regions, respectively. However, the industrial/construction activities showed the main contribution in ecological risk in both regions. On the other hand, the health risks in urban and suburban regions were mainly attributed to lithogenic source (49.7% for non-cancer risk and 36.8% of cancer risk) and traffic emission (69.4% of non-cancer risk and 46.6% of cancer risk), respectively. The sensitivity analysis showed that the Pb and As originated from traffic emission had the most impact on the non-cancer and cancer risks, respectively, in the suburb. Therefore, this study highlighted the concern about traffic emission as a critical heavy metal source in the road dust of Bandar Abbas suburb.

Traffic noise drives an immediate increase in call pitch in an urban frog

AbstractNoise pollution is an underappreciated component of global environmental change and can impact species that have a strong reliance on acoustic communication. In urban areas, traffic noise can interfere with the ability of animals to communicate and complete essential aspects of their daily lives. We investigated the impact of traffic noise on the calling behaviour of the brown tree frog (Litoria ewingii) in south‐eastern Melbourne, the fastest‐growing human population centre in Australia. We placed six acoustic recorders at increasing distances from a busy suburban road and recorded the calling behaviour (call pitch and call rate) of brown tree frogs immediately before and after loud traffic noises, and in response to different chorus sizes. Traffic noise resulted in a significant, but short‐term, increase in call pitch in the brown tree frog. Both call pitch and call rate decreased with increasing distance from the road, yet traffic noise still resulted in increased call pitch even 200–300 m from the road. Conversely, although traffic noise increased call pitch across all chorus sizes of the brown tree frog, larger chorus sizes were associated with decreased call pitch. Our study highlights the pervasive, and sustained, impact that anthropogenic noise can have on urban frog populations.

Analysis of crashes and Emergency Medical Services resources using geospatial information system on Western suburban roads of Iran

Crashes and their consequences are one of the universal major public health problems. The study aimed to analyze crashes and places of Emergency Medical Services (EMS) for suburban roads in Kermanshah province. This retrospective descriptive-analytical study was conducted from March 21, 2018, to March 20, 2019 using ArcGIS 10.6. The study sources consisted of spatial data including the map of Kermanshah province, which included city, road, emergency centers, the buffer of activities of EMS, point layer for crashes and, descriptive data related to injuries and deaths of emergency centers. To analyze the data, a geo-database of crashes was created and, then crashes status and EMS resources were analyzed. In the mentioned period, as many as 3090 crashes resulted in 409 deaths and 5112 injuries on suburban roads in Kermanshah province. In black spots, 1.36–1.7 and 0.05–0.07 people per square meter were injured and died, respectively. Lane departure of the cars was the most common cause of accidents and deaths. The Kermanshah-Kamyaran road with 38 death cases and the Kermanshah-Eslamabad road with 457 injured were the most frequent accident-prone roads in Kermanshah. Summer has the most crashes with 131 death cases and 1457 injuries. Allocating an ambulance code for each EMS, given the number of crashes in that area, is not a good policy and, new centers are required to be created in the areas of Kamyaran, Sarpol Zahab to Qasr-e-Shirin and Bisotun roads. Poor safety of vehicles and roads, distracted driving or fatigue are the main causes of crashes. Insufficient development of the road in some areas has led to crashes that have resulted in the most deaths and injuries. The distribution of EMS and essential facilities (ambulance code and specialized personnel) in the province a inappropriate. Therefore, equipping/establishing EMSs seems to be necessary.

Evaluation of disability glare caused by headlights of most common vehicles in Iran

Background and Objectives: Road traffic accident is one of the leading causes of death in some countries such as Iran. Disability glare due to headlights of vehicles can increase the risk of crashes and make dangerous conditions. This study aimed to investigate the level of glare induced by the headlights of most common vehicles in Iran. Materials and Methods: This cross-sectional study was conducted in a suburban road of Ilam province in 2019. The disability glare resulted from the headlights of Pride Saba GTX, Pride 131SL, Samand Soren, Peugeot 405, Megan, and Peugeot Pars was measured at the distances of 10–100 m away from the headlights. The Threshold Elevation index under the high-beam and low-beam conditions (headlight's operation modes) was obtained for the background luminance condition including 1 and 50 cd/m2 for the age groups of 20, 35, 70, and 83 years old. Results: When the background luminance was 1 cd/m2, the mean glare level caused by the high-beam mode of illumination exceeded the recommended disability glare thresholds of all age groups. When the background luminance was 50 cd/m2, at certain longitudinal distances, glare level exceeded the disability glare thresholds of the elderly drivers (aged 70 and 83 years). At the background luminance of 1 cd/m2, low-beam mode of illumination caused disability glare at certain distances but not in general. At the background luminance of 50 cd/m2, low-beam mode of illumination did not cause disability glare at any distance. Conclusion: The results showed the mutual effect of luminance and the angle of line of sight with respect to glare source on the emergence of disability glare. The age also exhibited a significant association with the disability glare, as the highest glare levels were obtained for older drivers.

Scanpath analysis into the wild: the spatiotemporal distribution of fixations as an indicator of driver’s mental workload

Past studies using the distribution of eye fixations as an indicator of mental workload are limited to simulations and laboratory tasks. Hence, this assessment strategy has not yet been proven useful in real- world settings. In order to bridge this gap, in this study eye movements of a group of individuals were recorded while driving a car in a suburban road. Drivers’ scanpaths during driving and during driving while performing mundane secondary tasks were compared in this study. A more grouped pattern of fixations was expected in the dual-task condition than in the driving-only condition. As expected, results showed the effectiveness the spatiotemporal distribution of fixations in correctly discriminating between task load conditions, therefore indicating its usefulness for assessing mental workload also in complex real-world tasks.

Quantification of within-vehicle exposure to NOx and particles: Variation with outside air quality, route choice and ventilation options

Vehicle use, as driver or passenger, is a key transport mode and important microenvironment for personal exposure to air pollutants. Here, the air pollution exposure of vehicle occupants, relative to external, ambient levels was explored under different vehicle ventilation settings and driving routes in an urban area. Four vehicles were driven on a consistent route encompassing three contrasting road types, measuring simultaneous within-vehicle and ambient levels of particulate matter (PM10, PM2.5, PM1), ultrafine particles number (UFP), lung surface deposited area (LSDA), nitric oxide (NO) and nitrogen dioxide (NO2). For the majority of ventilation settings available, the inside/outside (I/OVEH) ratio for PM10, PM2.5, PM1, UFP, LSDA and NO2 concentrations was below 1, with the exception of NO, for which the ratio was independent of ventilation settings, within uncertainty. The lowest within-vehicle exposure for particles and gases was observed under the conditions of windows closed, recirculation and air conditioning on. Vehicle occupants are exposed to and inhale more air pollution when traveling on urban roads, followed by ring-roads and sub-urban roads. However, through reduced within-vehicle concentrations and reduced physical activity and hence breathing rate, they inhale less air pollution than people cycling/walking on the same routes. Within-vehicle air pollution exposure displays significant dependence upon both the ventilation setting and route selected. Vehicle occupants can, therefore, modify their personal exposure through these choices. Finally, vehicle occupants inhale more mass of NO2 than PM2.5 with a trip-average inhalation dose ratio of 6.4 (NO2 dose/PM2.5 dose). These results may have significant health impacts upon highly exposed groups such as professional drivers.

A hazard-based model of the motorcyclists’ overtaking duration

The overtaking maneuver performed by motorcyclists is one of the primary causes of motorcycle accidents. However, few studies in the literature deal with this topic and there are no studies modeling the total overtaking duration, i.e. the time during which extreme hazards are manifest. The present paper aims to analyze the motorcyclists’ behavior during overtaking and to model the total overtaking duration. A field experiment, using instrumented motorcycles, was performed to collect data and a survival analysis was carried out to model the total overtaking duration. Twenty young motorcyclists drove their own motorcycles, which were instrumented with a camera and a global positioning system device (GPS), onto a two-lane suburban road in Rome. A total of 101 overtaking maneuvers were recorded. A methodology, based on video and GPS analyses, was developed to obtain data describing the motorcyclists’ behavior. The obtained results showed that the mean values of the main parameters of the overtaking maneuver (total overtaking duration - 6.6 s - and distance - 109.7 m - lateral distance from the passed vehicle - 1.50 m) were consistent with the few data available in the revised literature. The total overtaking duration was modelled using a hazard-based duration model. The parametric accelerated failure time duration model with a log-logistic distribution, which was the best-fitted distribution, identified the covariates which affected, in a statistically significant way, the total overtaking duration. The obtained model revealed that the overtaking duration depends on several covariates. The greater average impact was found for the initial distance and speed difference, while the initial lateral distance and final distance produced a minor impact. When performing a multiple overtaking, the duration of the maneuver tended to increase by 31 %. This research can be considered as a pilot study and a starting point for future advances on motorcyclists’ behavior during overtaking maneuver and for modeling the total overtaking duration. In addition, the findings of this study could contribute to the development of advanced rider assistance systems for the overtaking maneuver based on current driving conditions.

Evaluation of shade profiles while walking in urban environments: A case study from inner suburban Sydney, Australia

Precise shade distributions at the street level are an area of research of increasing importance to provide complete and high spatial and temporal resolutions of the amount and effectiveness of shade. Temporal shade distributions and profiles were evaluated for an inner Sydney tree-lined suburban street at different times of the day using an electronic sun journal (ESJ), providing detailed profiles of shade availability for various times of the day to provide very detailed street-level shade profiles and distributions that are often not included in shade audit methods and models. Further profiles were developed of streets adjoining shopfronts and public parks. Distributions of dense, light and no shade areas were calculated, revealing that tree canopy shade area during the middle of the day is considerably less effective and more prone to gaps than at other times. Distributions calculated using the ESJ were compatible with the paper-based shade auditing with less than 10% variation, whilst the ESJ has revealed a greater resolution of detail of gaps in the shade, thus records a higher amount of areas of no shade. The ESJ is a robust, low cost and portable tool that can efficiently and quickly produce shade profiles during walks in an urban environment, such as streetscapes.

Geochemical, Mineralogical and Morphological Characterisation of Road Dust and Associated Health Risks

Road dust resuspension, especially the particulate matter fraction below 10 µm (PM10), is one of the main air quality management challenges in Europe. Road dust samples were collected from representative streets (suburban and urban) of the city of Viana do Castelo, Portugal. PM10 emission factors (mg veh−1 km−1) ranging from 49 (asphalt) to 330 (cobble stone) were estimated by means of the United Stated Environmental Protection Agency method. Two road dust fractions (<0.074 mm and from 0.0074 to 1 mm) were characterised for their geochemical, mineralogical and morphological properties. In urban streets, road dusts reveal the contribution from traffic emissions, with higher concentrations of, for example, Cu, Zn and Pb. In the suburban area, agriculture practices likely contributed to As concentrations of 180 mg kg−1 in the finest road dust fraction. Samples are primarily composed of quartz, but also of muscovite, albite, kaolinite, microcline, Fe-enstatite, graphite and amorphous content. Particle morphology clearly shows the link with natural and traffic related materials, with well-formed minerals and irregular aggregates. The hazard quotient suggests a probability to induce non-carcinogenic adverse health effects in children by ingestion of Zr. Arsenic in the suburban street represents a human health risk of 1.58 × 10−4.

Transpiration by established trees could increase the efficiency of stormwater control measures

Evapotranspiration is an important aspect of the hydrological cycle in natural landscapes. In cities, evapotranspiration is typically limited by reduced vegetation and extensive impervious surfaces. Stormwater control measures (SCMs) seek, among other objectives, to move the urban hydrological cycle towards pre-development conditions, promoting processes such as infiltration and evapotranspiration. Yet, evapotranspiration is generally assumed to play a minor role in the water balance of stormwater control measures. Since established urban trees can use large quantities of water, their inclusion with stormwater control measures could potentially substantially increase evapotranspiration. We installed infiltration trenches alongside established Lophostemon confertus trees in the grassed verges of a typical suburban street to assess 1) whether redirecting stormwater to trees could increase their transpiration and 2) the contribution of transpiration to the water balance of stormwater control measures. We measured stormwater retention and transpiration for two spring-summer periods and estimated an annual water balance for the infiltration trenches. Although redirecting stormwater to trees did not increase their transpiration, these trees did use large volumes of water (up to 96 L d−1), corresponding to 3.4 mm d−1 per projected canopy area. Annually, stormwater retention was 24% of runoff and tree transpiration was equivalent to 17% of runoff. Our results suggest that streetscapes fitted with tree-based stormwater control measures, could increase the volumetric reduction of stormwater runoff by increasing the proportion of evapotranspiration in the water balance. Since public space is highly contested in cities and increasing canopy cover is a priority for many planners, integrating trees with stormwater control measures could provide dual benefits for a single management intervention, enabling a greater number of distributed stormwater control measures with smaller impervious catchments in the streetscape.

Vehicle Collisions Among Four Species of Monkeys Between 2000 and 2018 on a Suburban Road in Diani, Kenya

The impacts of road infrastructure on wildlife are of mounting concern. Amidst a growing body of literature on vehicle–wildlife collisions, few studies focus on primates. We examined a long-term dataset (2000–2018) of community-reported welfare cases for four species of monkeys: colobus (Colobus angolensis palliatus), Sykes’s monkey (Cercopithecus mitis albogularis), vervet (Chlorocebus pygerythrus hilgerti), and baboon (Papio cynocephalus cynocephalus). We analyzed collision rates using annual census data along a 10-km road section through the suburban town of Diani, Kenya. Vehicle–monkey collisions represented 705 of 1896 cases (37%), which was the most common anthropogenic cause of injury and death. The mean number of monthly vehicle–monkey collisions was 3 (range 0–10), and 83% of collisions led to death of the monkey. We found 1) higher degrees of terrestrialism were associated with lower number of collision cases; 2) no differences in the collision rates between juveniles, subadults, and adults across species, but collisions involving infants occurred at lower rates; 3) similar collision rates for female and male colobus and baboons, whereas Sykes’s monkey females and vervet males were more frequently involved in collisions than the other sex; 4) no correlation between the number of hotel bed-nights (a measure of tourist numbers) and vehicle collisions; and 5) drier days correlated with increased rates of vehicle–monkey collisions across all species. This study highlights the risks of roads for monkeys, and that collision rates vary with species, age class, and, in some species, sex and that rainfall is one factor that affects these rates.

Evaluating the environmental costs in Poland of city buses meeting the Euro VI norm based on tests in real operating conditions

The article analyzes the environmental costs which consisted of determining the annual cost for gases and particles released into the atmosphere by city buses meeting the Euro VI norm. To this end, exhaust emissions of a city bus equipped with a conventional drive system were performed. The vehicle had a length of 18m and was powered by a CI engine with a swept volume of 10,5 dm3, with a maximum power of 240 kW. In order to measure the ecological indicators, tests were performed in real driving conditions using the PEMS system. The apparatus made it possible to measure the concentration of gaseous compounds and particulate matter in the exhaust, which made it possible to determine the road exhaust emissions of the tested vehicle. The research was carried out on a test route including urban and suburban roads in accordance with legislative guidelines. The measurements showed that the bus met the exhaust emission limits determined on the basis of measuring windows defined in relation to the work generated by the drive system. In addition to information on the emissivity of the vehicle, the annual emissions from city buses meeting the Euro VI standard in Poland were also estimated. The information contained in the central vehicle register for the number of vehicles registered in Poland that meet the latest emission standards has been used for this purpose.

Registro del atropellamiento de Herpailurus yagouarundi (Carnivora: Felidae) en la zona suburbana de Puerto Vallarta, México

Herpailurus yagouaroundi es uno de los felinos más atropellados en carretera de México. En esta nota, se presenta evidencia fotográfica de un jaguarundi arrollado en una carretera suburbana de Puerto Vallarta, México. Se comentan las características ambientales del sitio donde tuvo lugar el evento.

‘Silence, lights, and a situation of expectation’: influences and themes in Gabriele Basilico's oeuvre

If you think of Gabriele Basilico's photography, it is impossible not to imagine empty cities of a silently destroyed civilisation. For instance, in Milano. Ritratti di fabbriche 1978/1980, an exemplar of Basilico's visual research, viewers can acutely experience what a deserted suburban street in Milan looks like during a hot summer day. This theme of uninhabited urban industrial space is a leitmotiv of his celebrated work. During his lifetime, Basilico's search for a photographic documentation of such experience had translated into images of empty physical spaces and abandoned factories. He gave the experience of being in such quintessentially urban conditions of abandonment and dereliction a new aesthetic value and constructed a visual poetry of magic suspension on the absence of human beings, such as that which he had captured in the empty Milanese suburbs in the early morning light. This paper unravels Basilico's choice to interpret virtually empty urbanscapes, and traces Giorgio Casali's influence on Basilico within the wider culture of Italian architectural photography.

Does familiarity breed competence or contempt? Effects of driver experience, road type and familiarity on hazard perception

Driving is one of the most complex and dangerous tasks that is regularly performed by most adults. Whereas most research examines performance in novel situations, most everyday driving occurs in highly familiar settings, such as our daily commute. Here we compared drivers’ hazard identification on familiar roads with similar but unfamiliar roads, for five road types: city streets, suburban streets, urban roads, mountain roads, and motorways. Participants were 45 experienced drivers with on average 17.6 years driving experience ( SD = 5.2), and 32 novices with on average 6.2 months solo driving ( SD = 3.5). Experienced drivers identified more hazards than novices, regardless of road type, but the magnitude of the effect was surprisingly small. The overall effect of location familiarity on hazard identification was not statistically significant, but there were significant effects of road type and significant interactions between familiarity and road type, which suggests researchers should be cautious when generalizing results obtained from one road context to another.

Microplastic pollution in vegetable farmlands of suburb Wuhan, central China

Microplastic pollution has become an emergency issue in the global environment. However, little is known about the occurrence and distribution of microplastics in agroecological system. In this study, we investigated the pollution of microplastics in vegetable farmlands in suburb of Wuhan, central China. Results showed that the abundance of microplastics ranged from 320 to 12,560 items/kgdw. Microplastic pollution adjacent to the suburban roads was about 1.8 times as serious as that in the residential areas. Microplastics with size less than 0.2 mm were dominated, reaching 70% in total. The main types of microplastics were fibers and microbeads. Moreover, polyamide (32.5%) and polypropylene (28.8%) were the main types of polymer. This study proclaims the occurrence and characteristics of microplastic pollution in typical farmland soils of suburb land. It may provide significant basis for subsequent research about microplastics contaminant in the terrestrial ecosystem.

SEMANTIC ROAD SCENE KNOWLEDGE FOR ROBUST SELF-CALIBRATION OF ENVIRONMENT-OBSERVING VEHICLE CAMERAS

Abstract. Environment-observing vehicle camera self-calibration using a structure from motion (SfM) algorithm allows calibration over vehicle lifetime without the need of special calibration objects being present in the calibration images. Scene-specific problems with feature-based correspondence search and reconstruction during the SfM pipeline might be caused by critical objects like moving objects, poor-texture objects or reflecting objects and might have negative influence on camera calibration. In this contribution, a method to use semantic road scene knowledge by means of semantic masks for a semantic-guided SfM algorithm is proposed to make the calibration more robust. Semantic masks are used to exclude image parts showing critical objects from feature extraction, whereby semantic knowledge is obtained by semantic segmentation of the road scene images. The proposed method is tested with an image sequence recorded in a suburban road scene. It has been shown that semantic guidance leads to smaller deviations of the estimated interior orientation and distortion parameters from reference values obtained by test field calibration compared to a standard SfM algorithm.

RULE-BASED MAPPING OF PARKED VEHICLES USING AERIAL IMAGE SEQUENCES

Abstract. Mapping of parking spaces in cities is a prerequisite for future applications in parking space management like community-based parking. Although terrestrial or vehicle based sensors will be the favorite data source for parking space mapping, airborne monitoring can play a role in building up city wide basis maps which include also parking spaces on ancillary and suburban roads. We present a novel framework for automatic city wide classification of vehicles in moving, stopped and parked using aerial image sequences and information from a road database. The time span of observation of a specific vehicle during an image sequence is usually not long enough to decide unambiguously, whether a vehicle stopped e.g. before a traffic light or is parking along the road. Thus, the workflow includes a vehicle detection and tracking method as well as a rule-based fuzzy-logic workflow for the classification of vehicles. The workflow classifies stopped and parked vehicles by including the neighbourhood of each vehicle via a Delaunay-Graph. The presented method reaches correctness values of around 86.3%, which is demonstrated using three different aerial image sequences. The results depend on several factors like detection quality and road database accuracy.