The number of light commercial vehicles in cities is growing, which puts increasing pressure on the liveability of cities. Light electric freight vehicles (LEFV) and cargo bikes can offer a solution, as they occupy less space, can be manoeuvred easily and does not emit tailpipe pollutants. This paper presents the results of the first half-year of the LEVV-LOGIC project (2016-2018), aimed at exploring the potential of LEFVs for various urban freight flows. Delivery characteristics, trends, practical examples and the judgement of experts are combined to assess the potential of LEFVs for seven major urban freight flows. The preliminary analysis concludes that every urban freight flow has a certain level of potential for using LEFV. In particular parcel and food deliveries have high potential; however, deliveries related to services and the last phase of construction work can also be switched to LEFV. In comparison, non-food deliveries to retail establishments and the collection of waste collection have less potential. Though the latter can change when recycling standards become higher.
Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes. Different deep learning networks are considered and by leveraging the effect of transfer learning crack detection on masonry surfaces is performed on patch level with 95.3% accuracy and on pixel level with 79.6% F1 score. This is the first implementation of deep learning for pixel-level crack segmentation on masonry surfaces. Codes, data and networks relevant to the herein study are available in: github.com/dimitrisdais/crack_detection_CNN_masonry.
Seamless integration of air segment in the overall multimodal mobility chain is a key challenge to provide more efficient and sustainable transport services. Technology advances offer a unique opportunity to build a new generation of transport services able to match the evolving expectations and needs of society as a whole. In this context, the passenger-centric approach represents a method to inform the design of future mobility services, supporting quality of life, security and services to citizens traveling across Europe. Relying on the concepts of inclusive design, context of use and task analysis, in this article, we present a comprehensive methodological framework for the analysis of passenger characteristics to elicit features and requirements for future multimodal mobility services, including air leg, that are relevant from the perspective of passengers. The proposed methodology was applied to a series of specific use cases envisaged for three time horizons, 2025, 2035 and 2050, in the context of a European research project. Then, passenger-focused key performance indicators and related metrics were derived to be included in a validation step, with the aim of assessing the extent of benefit for passengers that can be achieved in the forecasted scenarios. The results of the study demonstrate the relevance of human variability in the design of public services, as well as the feasibility of personalized performance assessment of mobility services.