Search

This paper presents a data-driven approach to estimate incident-induced delays (IIDs) using probe vehicle data while accounting for missing data. The proposed approach is applied to evaluate the effectiveness of a safety service patrol (SSP) program. Existing data-driven methods for IID estimation usually rely on complete data sets. The proposed approach employs a random forest-based classification model and an interpolation method to estimate IIDs when real-time data are completely or partially missing during the incident-impacted time period. It also identifies reference profiles from the closest spatial-temporal road segments to improve data availability. The case study shows that the SSP program in the Quad Cities area of Iowa reduces IIDs associated with various incidents by 15%–91%. This data-driven evaluation framework can be applied to other traffic incident management programs, allowing more accurate and objective evaluations of their effectiveness. [ABSTRACT FROM AUTHOR]

Urban flooding poses risks to the safety of drivers and pedestrians, and damages infrastructures and lifelines. It is important to accommodate cities and local agencies with enhanced rapid flood detection skills and tools to better understand how much flooding a region may experience at a certain period of time. This results in flood management orders being announced in a timely manner, allowing residents and drivers to preemptively avoid flooded areas. This research combines information received from ground observed data derived from road closure reports from the police department, with remotely sensed satellite imagery to develop and train machine-learning models for flood detection for the City of San Diego, CA, USA. For this purpose, flooding information are extracted from Sentinel 1 satellite imagery and fed into various supervised and unsupervised machine learning models, including Random Forest (RF), Support Vector Machine (SVM), and Maximum Likelihood Classifier (MLC), to detect flooded pixels in images and evaluate the performance of these ML models. Moreover, a new unsupervised machine learning framework is developed which works based on the change detection (CD) approach and combines the Otsu algorithm, fuzzy rules, and iso-clustering methods for urban flood detection. Results from the performance evaluation of RF, SVM, MLC and CD models show 0.53, 0.85, 0.75 and 0.81 precision measures, 0.9, 0.85, 0.85 and 0.9 for recall values, 0.67, 0.85, 0.79 and 0.85 for the F1-score, and 0.69, 0.87, 0.83 and 0.87 for the accuracy measure, respectively, for each model. In conclusion, the new unsupervised flood image classification and detection method offers better performance with the least required data and computational time for enhanced rapid flood mapping. This systematic approach will be potentially useful for other cities at risk of urban flooding, and hopefully for detecting nuisance floods, by using satellite images and reducing the flood risk of transportation design and urban infrastructure planning. [ABSTRACT FROM AUTHOR]

The point clouds acquired with a mobile LiDAR scanner (MLS) have high density and accuracy, which allows one to identify different elements of the road in them, as can be found in many scientific references, especially in the last decade. This study presents a methodology to characterize the urban space available for walking, by segmenting point clouds from data acquired with MLS and automatically generating impedance surfaces to be used in pedestrian accessibility studies. Common problems in the automatic segmentation of the LiDAR point cloud were corrected, achieving a very accurate segmentation of the points belonging to the ground. In addition, problems caused by occlusions caused mainly by parked vehicles and that prevent the availability of LiDAR points in spaces normally intended for pedestrian circulation, such as sidewalks, were solved in the proposed methodology. The innovation of this method lies, therefore, in the high definition of the generated 3D model of the pedestrian space to model pedestrian mobility, which allowed us to apply it in the search for shorter and safer pedestrian paths between the homes and schools of students in urban areas within the Big-Geomove project. Both the developed algorithms and the LiDAR data used are freely licensed for their use in further research. [ABSTRACT FROM AUTHOR]

Emergency medical service (EMS) is important for rescuing victims suffering from life-threatening illnesses or accidents, and is highly time-sensitive by nature. Many uncertain contexts in the urban environment can prolong EMS response time and deteriorate its performance. Using the enhanced two-step floating catchment area (E2SFCA) method, this study measures EMS accessibility with the effect of a regular uncertain context (i.e., the city dynamics like time-varying population and traffic) and an irregular uncertain context (i.e., an extreme pluvial flood event which can cause extensive road closures). The results indicate that, in the central urban area of Shanghai, mid-west areas with denser populations have higher accessibility than eastern peripheral areas. Flooding can cause a remarkable decline of accessibility which falls to the lowest point slightly earlier than the time when the worst road connectivity emerges. The night time exhibits better accessibility than especially the peak hours during the daytime. The GWR results reveal that increasing facility richness and road density while decreasing flood-induced road closures have a positive effect on EMS accessibility. The study indicates that both regular and irregular uncertain contextual factors can influence EMS accessibility in a highly complex manner. Carefully taking these uncertainties into account would enable EMS planning in other contexts and regions to face the enormous challenges posed by the changing climate and increasingly complex urban environment. • E2SFCA method is used to measure EMS accessibility. • The effects of city dynamics and extreme flooding are considered. • Both regular and irregular uncertain contextual factors can influence EMS accessibility in a highly complex manner. • Carefully taking contextual uncertainties into account is essential for all emergency services in other cities of the world. [ABSTRACT FROM AUTHOR]

• Automatic algorithm of counting vehicles driving in opposite directions using unmanned aerial vehicle. • Data acquired from cameras mounted on UAV for analysis of urban transportation systems and its sustainability. • Analysis of the road traffic concerning local road restoration, causing road congestions. • Result of this paper may be used in the future together with the data from existing intelligent transportation systems. • Case study. Quantitative measurements and the simulation result that justify the use of UAV within smart sustainable cities. Nowadays, it is practically impossible to find a public place, where a person or object would not be under constant camera observation (mainly used to monitor traffic and to increase safety). Interpretation of such repositories, due to the huge amount of data, is not an easy task. Thus there is a need to introduce an intelligent processing systems that, through algorithmic image analysis, are able to detect e.g. situations worth of attention. The article presents methods of data acquisition from cameras mounted on unmanned aerial vehicles (UAV) and their further analysis, which may be used to improve urban transportation systems and its sustainability. The worked out data concern the situation of urban transport in points of intersection of national and local roads. The analysis of the road traffic concerning local road restoration, causing road closure was achieved using image processing and analysis algorithms. The data was obtained from unmanned aerial vehicle flights in critical city locations. Result of this paper may be used in the future together with the data from existing intelligent transportation systems (a fusion of such data will be needed). The application of used methods will allow to extend and support the existing approaches to manage public and freight transport in cities. [ABSTRACT FROM AUTHOR]

The main objective of the study was to determine the effects of the water extracts of urban road dust (URD) samples on the growth inhibition and mortality rate of Heterocypris incongruens in various site environment type. We collected 24 samples of the road dust close to highways, main roads, crossroads as well as at other places i.e. residential area, and suburbs. We determined the selected metals (Al, As, Ba, Cd, Co, Cr, Cu, Ga, Mg, Mn, Mo, Ni, Pb, Rb, Sr, Ti, Tl, V and Zn) content of the water extracts of these samples as well as we tested the toxicity of the water extracts of URD samples using a commercial test Ostracodtoxkit F. We observed the lowest values of the growth inhibition of H. incongruens for residential areas and suburbs (<50%). The highest growth inhibition we found for water extracts of URD samples collected at the main roads in the Katowice urban area and crossroads in the urban areas. Although the mortality and growth inhibition of H. incongruens were related to the road traffic emissions it was impossible to clearly relate this finding with the urban site category. [Display omitted] • Toxicity of urban road dust was related to the urban site category (suburbs, residential area, crossroads, main roads). • Water-soluble Cr, Co, As, and Cd had the most substantial influence on growth inhibition of H. incongruens. • The mortality of H. incongruens was associated with the road traffic emission. [ABSTRACT FROM AUTHOR]

The demand for mobile laser scanning in urban areas has grown in recent years. Mobile-based light detection and ranging (LiDAR) technology can be used to collect high-precision digital information on city roads and building façades. However, due to the small size of curbs, the information that can be used for curb detection is limited. Moreover, occlusion may cause the extraction method unable to correctly capture the curb area. This paper presents the development of an algorithm for extracting street curbs from mobile-based LiDAR point cloud data to support city managers in street deformation monitoring and urban street reconstruction. The proposed method extracts curbs in three complex scenarios: vegetation covering the curbs, curved street curbs, and occlusion curbs by vehicles, pedestrians. This paper combined both spatial information and geometric information, using the spatial attributes of the road boundary. It can adapt to different heights and different road boundary structures. Analyses of real study sites show the rationality and applicability of this method for obtaining accurate results in curb-based street extraction from mobile-based LiDAR data. The overall performance of road curb extraction is fully discussed, and the results are shown to be promising. Both the completeness and correctness of the extracted left and right road edges are greater than 98%. [ABSTRACT FROM AUTHOR]

The occurrence of an earthquake in an urban area not only affects the buildings but also impacts their immediate environment at the street level in ways that significantly lowers the speed of emergency response. More often, the streets get blocked with the debris of the collapsed building, resulting in the isolation of certain parts of an urban area. This paper specifically focuses on building vulnerability and its impact on road network connectivity i.e. whether a street is still accessible aftermath of an earth. The building vulnerability and its probability of collapse is assessed using rapid visual screening (RVS) procedure developed by FEMA and the resulting scores are overlaid on GIS database to identify the probable road closures. Network analysis and graph traversal algorithms are used in combination to measure the performance of a road network under probable road closure conditions, thereby identifying the isolated components of the road network and areas. The integration of the vulnerability scores of building and the road network would give a vulnerability index of an urban area. A pilot implementation of this methodology was carried out in one ward in Siliguri Municipal Corporation, which falls under seismic zone IV of India. The ward selection was done based on the population density and socioeconomic characteristics. The critical links and probable isolated areas visualized in GIS maps. This methodology make it possible for the emergency managers and decision makers to identify the critical parts of the network to take necessary precautions beforehand to avoid the delay of emergency services.Keywords: rapid visual screening, vulnerability, network analysis, Siliguri [ABSTRACT FROM AUTHOR]