Explainable, automated urban interventions to improve pedestrian and vehicle safety
Cristina Bustos,Daniel Rhoads,Albert Solé-Ribalta,David Masip,Alex Arenas,Agata Lapedriza,Agata Lapedriza,Javier Borge-Holthoefer +7 more
Reads0
Chats0
TLDR
This paper combines public data sources, large-scale street imagery and computer vision techniques to approach pedestrian and vehicle safety with an automated, relatively simple, and universally-applied data-processing scheme.Abstract:
At the moment, urban mobility research and governmental initiatives are mostly focused on motor-related issues, e.g. the problems of congestion and pollution. And yet, we cannot disregard the most vulnerable elements in the urban landscape: pedestrians, exposed to higher risks than other road users. Indeed, safe, accessible, and sustainable transport systems in cities are a core target of the UN’s 2030 Agenda. Thus, there is an opportunity to apply advanced computational tools to the problem of traffic safety, in regards especially to pedestrians, who have been often overlooked in the past. This paper combines public data sources, large-scale street imagery and computer vision techniques to approach pedestrian and vehicle safety with an automated, relatively simple, and universally-applicable data-processing scheme. The steps involved in this pipeline include the adaptation and training of a Residual Convolutional Neural Network to determine a hazard index for each given urban scene, as well as an interpretability analysis based on image segmentation and class activation mapping on those same images. Combined, the outcome of this computational approach is a fine-grained map of hazard levels across a city, and an heuristic to identify interventions that might simultaneously improve pedestrian and vehicle safety. The proposed framework should be taken as a complement to the work of urban planners and public authorities.read more
Citations
More filters
Journal ArticleDOI
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
TL;DR: This survey presents a comprehensive review of current literature on Explainable Artificial Intelligence (XAI) methods for cyber security applications and proposes a clear roadmap for navigating the XAI literature in the context of applications in cyber security.
Journal ArticleDOI
A sustainable strategy for Open Streets in (post)pandemic cities
Daniel Rhoads,Albert Solé-Ribalta,Albert Solé-Ribalta,Marta C. González,Marta C. González,Javier Borge-Holthoefer +5 more
TL;DR: This work uses sidewalk data from ten cities in three continents, to first analyse the distribution of sidewalk and roadbed geometries, and finds that cities present an unbalanced distribution of public space, favouring automobiles at the expense of pedestrians.
Proceedings ArticleDOI
Predicting Driver Self-Reported Stress by Analyzing the Road Scene
Cristina Bustos,Neska Elhaouij,Albert Solé-Ribalta,Javier Borge-Holthoefer,Agata Lapedriza,Rosalind W. Picard +5 more
TL;DR: In this article, the authors used the AffectiveROAD video recordings and their corresponding stress labels, a continuous human-driver-provided stress metric, to test if the visual driving scene can be used to estimate a drivers' subjective stress levels.
Journal ArticleDOI
Data-Driven Approach to Assess Street Safety: Large-Scale Analysis of the Microscopic Design
TL;DR: Based on multisource big data, a data-driven approach to assess the safety of street microscope design on a large scale from the perspective of individual perception is proposed in this article , where four dimensions of walkability, spatial enclosure, visual permeability, and vitality are constructed, which reflect the individual perceptions of the street space.
Journal ArticleDOI
Sensing accident-prone features in urban scenes for proactive driving and accident prevention
TL;DR: A visual notification of accident-prone features to drivers, based on real-time images obtained via dashcam, is proposed, using Google Street View images around accident hotspots identified by accident dataset to train a family of deep convolutional neural networks (CNNs).
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.