Abstract

Many cities organize cultural festivals to promote their distinctiveness, boost the local economy, and enhance quality of life. However, urban spaces are packed with visitors on festival days, thus affecting accessibility to pedestrian spaces. This research examined visitor satisfaction with accessibility to pedestrian spaces during special events such as festivals. We particularly focused on the Hakata Dontaku festival, which is celebrated in Fukuoka, Japan. We studied three main elements that affect pedestrian satisfaction and perceived accessibility through walking, namely, safety, mobility, and amenities. We first analyzed previous studies and employed analytical hierarchy process to setup indicators for satisfaction measurement. Second, we determined visitor satisfaction through a survey questionnaire, which was conducted during the Hakata Dontaku festival. Third, we assessed the normality of the data set that was obtained from the questionnaire. Finally, we applied structural equation modeling. Results showed that the proposed model was a good fit, as indicated by the goodness of fit test, and the majority of indicators loaded significant values that supported their constructs. Satisfaction with amenities was found to be the most statistically significant variable that influences visitors׳ perceived accessibility during the Hakata Dontaku festival.

Abstract

Recent developments of information technology and mobile lifestyle have forced drivers to multitask while they drive. The in-vehicle “infotainment” technology is already taking its place in the transformation of vehicles towards more intelligent and interactive devices rather than staying as mere transportation convenience. This transformation has several advantages such as easy route navigation, real-time traffic information, and staying connected with work or people while traveling. However, it has several drawbacks concerning the impact on driver cognitive load and attention sources. Therefore, it is crucial to take advantage of state-of-the-art in-vehicle technology to produce counter-measure systems that monitor the driver status and reduce driver workload adaptively depending on the context. In recognition and analysis of the driving context together with driver status monitoring, computer vision applications supply crucial information both in the vehicle (i.e., driver head and eye tracking) and out of the vehicle (i.e., lane, pedestrian, and vehicle detection and tracking, and road sign recognition). In this chapter, we provide a broad range of computer vision applications for CA-IVS from the literature and our previous studies, and we report our current research efforts. Document type: Part of book or chapter of book

Abstract

Walkability Explorer is a software tool for the evaluation of urban walkability which, we argue, is an important aspect of the quality of life in cities. Many conventional approaches to the assessment of quality of life measure the distribution, density and distances of different opportunities in space. But distance is not all there is. To reason in terms of urban capabilities of people we should also take into account the quality of pedestrian accessibility and of urban opportunities offered by the city. The software tool we present in this paper is an user-friendly implementation of such an evaluation approach to walkability. It includes several GIS and analysis features, and is interoperable with other standard GIS and data-analysis tools. Document type: Part of book or chapter of book

Abstract

Walking may be considered one of the most sustainable and democratic ways of travelling within a city, thus providing benefits not only to pedestrians but also to the urban environment. Besides, walking is also one of the means of transport most likely subjected to factors outside an individual’s control, like social or physical abilities to walk and the presence of comfortable and safe street infrastructures and services. Therefore, improving urban conditions provided to pedestrians has positive impacts on walkability. At the same time technological solutions and innovations have the power to encourage and support people to walk by overcoming immaterial barriers due to a lack of information or boring travel and they give to decision makers the possibility to gain data to understand how and where people travel. Merging these two dimensions into a unique approach can drastically improve accessibility, attractiveness, safety, comfort and security of urban spaces. In this context, this paper aims to draw a more multifaceted context for walkability, where new technologies assume a key role for introducing new approaches to pedestrian paths planning and design and thus for enhancing this mode of transport. Indeed, by combining more traditional spatial-based and perceptual analysis of the urban environment with technological applications and social media exploitation there will be room to better support the decision on and to enhance satisfaction of walking as well as to easier plan and design more walkable cities. Document type: Part of book or chapter of book

Abstract

Navigating through densely populated urban areas is one of the most important challenges for self-driving vehicles. Accurate predictions are required to enable safe and efficient interactions with other road users. Pedestrians in particular pose major problems for current state of the art prediction systems. Apart from well-understood short-term predictions, used for Automatic Emergency Braking Systems, long-term predictions remain largely unresolved. In this thesis, we aim to advance pedestrian prediction systems to enable human- understandable automated driving. In view of a vehicle-centred road infrastructure with high vehicle speeds and scarce pedestrian crossings, early detection of pedestrian intentions and movements are the key to enabling such behaviour. These detections can enable automated vehicles to perform light brake manoeuvres at an early stage in order to let a pedestrian pass. This can eliminate the need to stop, which could significantly improve traffic flow and at the same time increase overall safety. Long-term full trajectory predictions are both costly and error-prone. Therefore we propose a hierarchical prediction system that splits the prediction into multiple simplified sub-problems using domain knowledge. Each sub-problem is designed to predict a meaningful part of pedestrian movement and to detect and remove pedestrians that are irrelevant for the current scenario as early as possible. Utilizing the given road geometry to identify crosswalks we first predict the pedestrians’ hidden intent to cross the road. For all crossing pedestrians we then propose a sparse motion prediction, providing a small set of key figures instead of a full trajectory. We claim that these domain-specific key figures, namely a time-to- cross and designated crossing point, are more than sufficient to describe future pedestrian motions for the planning system of an automated vehicle. To overcome problems from over-confident single value predictions we propose to utilize Quantile Regression techniques to predict reasonable uncertainties. Our evaluations show that we are able to robustly classify the pedestrians’ hidden intent using both standard and deep learning algorithms. Additionally we show that our hierarchical prediction system, including the sparse motion prediction, is suitable for a real-time system integration. With our large real-world dataset, featuring recordings from different crosswalks and days, we provide an evaluation regarding prediction accuracy, computational load and generalizability. During this analysis, we also found indications that it might be possible to transfer trained models to previously unseen pedestrian crossings if the road geometry has at least approximately the same pavement dimensions. Furthermore, we show how our sparse motion prediction can be integrated into a situation-based planning approach to allow safe and efficient real-time interactions with other traffic participants. For this we evaluate different interaction scenarios regarding safety, time efficiency and comfort impairment. We were able to show that in most of the scenarios it is possible to minimize movement jerks and eliminate the need to stop. The overall performance is only limited by very high traffic densities.

Abstract

This study examines drivers’ fixation sequences and compares them to the responsiveness measured in a driving simulator. The assessment is based on a comparison of driving simulator based hazard detection skills with eye movement patterns. Sixty-three 18-24-year-old male drivers’ response to a pedestrian potentially crossing the street was examined and used as indicator of hazard perception skills (HPS). Drivers’ eye movements were examined to gain information about differences in scanning patterns between drivers with high and low HPS. Drivers with high HPS, fixated on the pedestrian continuously and had more multiple fixations on the standing pedestrian than drivers with low HPS. Moreover, more drivers that did not respond to the hazard did not fixate on the speedometer and if they did so, then mostly only once. The results show that novice drivers with high HPS differ in their eye movement patterns from drivers with low HPS. Moreover, drivers with low HPS pose an even higher risk as they consider their speed less often than drivers with high HPS.

Abstract

Two smartphone applications were developed with the aim of harvesting insights of vulnerable road user accidents. The apps require a backend database with software tools for generating and managing questionnaires, etc. Such a system was developed using a MySQL database where a user-friendly platform has been developed in CakePHP. The backend system has been successfully developed and been used to handle more than 11,000 participants. The original idea was to monitor VRU via apps to detect when they may have been involved in an accident as pedestrian or cyclist based on the motion patterns from the smartphone’s motion sensors (accelerometer, gyroscope) and collect as much information as possible regarding the accident automatically (e.g. time and location of the accident). If an accident was detected, the road user should receive a questionnaire to provide detailed information of the accident (e.g. road surface conditions, lighting conditions, other road users involved). This app was used by more than 400 participants resulting in a large amount of data.

Abstract

With the advent of location-aware smartphones, the desire for pedestrian-based navigation services has increased. Unlike car-based services where instructions generally are comprised of distance and road names, pedestrian instructions should instead focus on the delivery of landmarks to aid in navigation. OpenStreetMap (OSM) contains a vast amount of geospatial information that can be tapped into for identifying these landmark features. This paper presents a prototype navigation service that extracts landmarks suitable for navigation instructions from the OSM dataset based on several metrics. This is coupled with a short comparison of landmark availability within OSM, differences in routes between locations with different levels of OSM completeness and a short evaluation of the suitability of the landmarks provided by the prototype. Landmark extraction is performed on a server-side service, with the instructions being delivered to a pedestrian navigation application running on an Android mobile device. Document type: Article