ArticlePublisher preview available

Road cycling safety scoring based on geospatial analysis, computer vision and machine learning

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract and Figures

Road cycling is a cycling discipline in which riders ride on public roads. Traffic calming measures are made to make public roads safer for everyday usage for all its users. However, these measures are not always yielding a safer cycling racecourse. In this paper we present a methodology that inspects the safety of roads tailored to road bicycle racing. The automated approach uses computer vision and geospatial analysis to give an indicative racecourse safety score based on collected, calculated and processed multimodal data. The current version of our workflow uses OpenStreetMap (OSM), turn detection and stage type / bunch sprint classification for the geospatial analysis and uses road segmentation and an extensible object detector that is currently trained to detect road cracks and imperfections for visual analysis. These features are used to create a mechanism that penalizes dangerous elements on the route based on the remaining distance and the generated penalties with its relative importance factors. This results in a comprehensive safety score along with a detailed breakdown of the most concerning passages on the course which can be used by race organizers and officials to help them in the iterative process to create an engaging, yet safe course for the riders.
This content is subject to copyright. Terms and conditions apply.
1207: INNOVATIONS IN MULTIMEDIA INFORMATION PROCESS-
ING & RETRIEVAL
Road cycling safety scoring based on geospatial
analysis, computer vision and machine learning
Jelle De Bock
1
&Steven Verstockt
1
Received: 27 January 2021 /Revised: 11 March 2022 /Accepted: 14 July 2022
#The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022
Abstract
Road cycling is a cycling discipline in which riders ride on public roads. Traffic calming
measures are made to make public roads safer for everyday usage for all its users.
However, these measures are not always yielding a safer cycling racecourse. In this
paper we present a methodology that inspects the safety of roads tailored to road bicycle
racing. The automated approach uses computer vision and geospatial analysis to give an
indicative racecourse safety score based on collected, calculated and processed multi-
modal data. The current version of our workflow uses OpenStreetMap (OSM), turn
detection and stage type / bunch sprint classification for the geospatial analysis and uses
road segmentation and an extensible object detector that is currently trained to detect road
cracks and imperfections for visual analysis. These features are used to create a mecha-
nism that penalizes dangerous elements on the route based on the remaining distance and
the generated penalties with its relative importance factors. This results in a comprehen-
sive safety score along with a detailed breakdown of the most concerning passages on the
course which can be used by race organizers and officials to help them in the iterative
process to create an engaging, yet safe course for the riders.
Keywords Machine learning .Computer vision .Data analysis .Geospatial analysis .Sports data
science
1 Introduction
Road cycling is an endurance sport in which athletes ride their bicycles on courses that mainly
contain public roads. The number of vehicles using these public roads is slowly increasing
Multimedia Tools and Applications
https://doi.org/10.1007/s11042-022-13552-1
*Jelle De Bock
jelle.debock@ugent.be
Steven Verstockt
steven.verstockt@ugent.be
1
IDLab, Ghent University, Technologiepark-Zwijnaarde 122, 9052 Ghent, Belgium
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
With the growing rate of urban population and transport congestion, it is important for a city to have bike riding as an attractive travel choice but one of its biggest barriers for people is the perceived lack of safety. To improve the safety of urban cycling, identification of high-risk location and routes are major obstacles for safety countermeasures. Risk assessment is performed by crash data analysis, but the lack of data makes that approach less effective when applied to cyclist safety. Furthermore, the availability of data collected with the modern technologies opens the way to different approaches. This research aim is to analyse data needs and capability to identify critical cycling safety events for urban context where bicyclist behaviour can be recorded with different equipment and bicycle used as a probe vehicle to collect data. More specifically, three different sampling frequencies have been investigated to define the minimum one able to detect and recognize hard breaking. In details, a novel signal processing procedure has been proposed to correctly deal with speed and acceleration signals. Besides common signal filtering approaches, wavelet transformation and Dynamic Time Warping (DTW) techniques have been applied to remove more efficiently the instrument noise and align the signals with respect to the reference. The Euclidean distance of the DTW has been introduced as index to get the best filter parameters configuration. Obtained results, both during the calibration and the investigated real scenario, confirm that at least a GPS signal with a sampling frequency of 1Hz is needed to track the rider’s behaviour to detect events. In conclusion, with a very cheap hardware setup is possible to monitor riders’ speed and acceleration.
Article
Full-text available
A challenge still to be overcome in the field of visual perception for vehicle and robotic navigation on heavily damaged and unpaved roads is the task of reliable path and obstacle detection. The vast majority of the researches have scenario roads in good condition, from developed countries. These works cope with few situations of variation on the road surface and even fewer situations presenting surface damages. In this paper we present an approach for road detection considering variation in surface types, identifying paved and unpaved surfaces and also detecting damage and other information on other road surfaces that may be relevant to driving safety. Our approach makes use of Convolutional Neural Networks (CNN) to perform semantic segmentation, we use the U-NET architecture with ResNet34, in addition we use the technique known as Transfer Learning, where we first train a CNN model without using weights in the classes as a basis for a second CNN model where we use weights for each class. We also present a new Ground Truth with image segmentation, used in our approach and that allowed us to evaluate our results. Our results show that it is possible to use passive vision for these purposes, even using images captured with low cost cameras.
Article
Full-text available
The type of road pavement directly influences the way vehicles are driven. It’s common to find papers that deal with path detection but don’t take into account major changes in road surface patterns. The quality of the road surface has a direct impact on the comfort and especially on the safety of road users. In emerging countries it’s common to find unpaved roads or roads with no maintenance. Unpaved or damaged roads also impact in higher fuel costs and vehicle maintenance. This kind of analysis can be useful for both road maintenance departments as well as for autonomous vehicle navigation systems to verify potential critical points. For the experiments accomplishment upon the surface types and quality classification, we present a new dataset, collected with a low-cost camera. This dataset has examples of good and bad asphalt (with potholes and other damages) other types of pavement and also many examples of unpaved roads (with and without potholes). We also provide several frames from our dataset manually sorted in surface types for tests accuracy verification. Our road type and quality classifier was done through a simple Convolutional Neural Network with few steps and presents promising results in different datasets.
Article
Full-text available
The realizing and improvement of road infrastructure, of modern road networks provides normal, safe and pleasant road traffic conditions and also help prevent road accidents. The road network, with its constructive characteristics, has to offer optimal conditions for the movement of vehicles, pedestrians and other categories of participants in the road traffic. Starting from the case study of a road sector with heavy road traffic, the current paper analyzes the increase in road safety in Romanian localities along European and national roads through the implementation of specific measures such as setting up sidewalks, installing New Jersey median barriers, expanding the road sectors with 2+1 lanes, replacing normal pedestrian crossings with elevated crossings or with pedestrian crossing with mid-road waiting areas etc.
Article
Full-text available
Transportation agencies need efficient methods to determine how to reduce bicycle accidents while promoting cycling activities and prioritizing safety improvement investments. Many studies have used standalone methods, such as level of traffic stress (LTS) and bicycle level of service (BLOS), to better understand bicycle mode share and network connectivity for a region. However, in most cases, other studies rely on crash severity models to explain what variables contribute to the severity of bicycle related crashes. This research uniquely correlates bicycle LTS with reported bicycle crash locations for four cities in New Hampshire through geospatial mapping. LTS measurements and crash locations are compared visually using a GIS framework. Next, a bicycle injury severity model, that incorporates LTS measurements, is created through a mixed logit modeling framework. Results of the visual analysis show some geospatial correlation between higher LTS roads and "Injury" type bicycle crashes. It was determined, statistically, that LTS has an effect on the severity level of bicycle crashes and high LTS can have varying effects on severity outcome. However, it is recommended that further analyses be conducted to better understand the statistical significance and effect of LTS on injury severity. As such, this research will validate the use of LTS as a proxy for safety risk regardless of the recorded bicycle crash history. This research will help identify the clustering patterns of bicycle crashes on high-risk corridors and, therefore, assist with bicycle route planning and policy making. This paper also suggests low-cost countermeasures or treatments that can be implemented to address high-risk areas. Specifically, with the goal of providing safer routes for cyclists, such countermeasures or treatments have the potential to substantially reduce the number of fatalities and severe injuries.
Article
Many municipalities and road authorities seek to implement automated evaluation of road damage. However, they often lack technology, know-how, and funds to afford state-of-the-art equipment for data collection and analysis of road damages. Although some countries, like Japan, have developed less expensive and readily available Smartphone-based methods for automatic road condition monitoring, other countries still struggle to find efficient solutions. This work makes the following contributions in this context. Firstly, it assesses usability of Japanese model for other countries. Secondly, it proposes a large-scale heterogeneous road damage dataset comprising 26,620 images collected from multiple countries (India, Japan, and the Czech Republic) using smartphones. Thirdly, it proposes models capable of detecting and classifying road damages in more than one country. Lastly, the study provides recommendations for readers, local agencies, and municipalities of other countries when one other country publishes its data and model for automatic road damage detection and classification. A part of the proposed dataset was utilized for Global Road Damage Detection Challenge’2020 and can be accessed at (https://github.com/sekilab/RoadDamageDetector/).
Article
Semantic segmentation, a pixel-level vision task, is developed rapidly by using convolutional neural networks (CNNs). Training CNNs requires a large amount of labeled data, but manually annotating data is difficult. For emancipating manpower, in recent years, some synthetic datasets are released. However, they are still different from real scenes, which causes that training a model on the synthetic data (source domain) cannot achieve a good performance on real urban scenes (target domain). In this paper, we propose a weakly supervised adversarial domain adaptation to improve the segmentation performance from synthetic data to real scenes, which consists of three deep neural networks. To be specific, a detection and segmentation (“DS” for short) model focuses on detecting objects and predicting segmentation map; a pixel-level domain classifier (“PDC” for short) tries to distinguish the image features from which domains; an object-level domain classifier (“ODC” for short) discriminates the objects from which domains and predicts the objects classes. PDC and ODC are treated as the discriminators, and DS is consider as the generator. By the adversarial learning, DS is supposed to learn domain-invariant features. In experiments, our proposed method yields the new record of mIoU metric in the same problem.
Article
A global-scale calculation identifies peaks in a digital elevation model (DEM) and computes their isolation and topographic prominence. A new DEM is presented that covers the entire globe at 90 meter resolution with no substantial voids or artifacts. All peaks with at least 1 kilometer of isolation are found, and the closest higher ground is identified. For prominence, all peaks with at least ∼30 meters are found, and the key saddle is identified. The prominence algorithm uses results from Morse–Smale topology to run in parallel on standard, freely available elevation data. Thirteen previously unknown “ultra-prominent” mountains with at least 1500 meters of prominence are listed.
Article
Street scene understanding is an essential task for autonomous driving. One important step toward this direction is scene labeling, which annotates each pixel in the images with a correct class label. Although many approaches have been developed, there are still some weak points. First, many methods are based on the hand-crafted features whose image representation ability is limited. Second, they cannot label foreground objects accurately due to the data set bias. Third, in the refinement stage, the traditional Markov random filed inference is prone to over smoothness. For improving the above problems, this paper proposes a joint method of priori convolutional neural networks at superpixel level (called as "priori s-CNNs") and soft restricted context transfer. Our contributions are threefold: 1) a priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly; 2) a hierarchical data augmentation method is presented to alleviate data set bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly; and 3) a soft restricted MRF energy function is defined to improve the priori s-CNNs model's labeling performance and reduce the over smoothness at the same time. The proposed approach is verified on CamVid data set (11 classes) and SIFT Flow Street data set (16 classes) and achieves a competitive performance.