Estimation of space-speed profiles: A functional approach using smoothing splines

Andrieu, Cindie; Pierre, Guillaume Saint; Bressaud, Xavier

doi:10.1109/ivs.2013.6629594

Cited by 3 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such innovative cloud-based solutions are currently under development among original equipment manufacturers (for example, the "static eHorizon" solution from Continental Automotive). Eco-driving, road safety (Chen et al 2016), vehicle-embedded driving assistance devices conception (Andrieu et al 2013) or accurate routing time estimation (Bonin 2002), are many other examples of fields where road maps need to be completed with up-to-date attributes.…”

Section: Inferring Road Attributesmentioning

confidence: 99%

“…In this paper, we apply machine learning algorithms on in-vehicle GPS speed profiles to detect traffic signals. We believe that speed profiles, as defined by Andrieu et al (2013), are potentially more explicit than raw trajectories (i.e. sequences of timestamped geo-graphic coordinates) and contain all the information needed to recognize different kinds of traffic calming infrastructures, provided that a sufficient number of traces are observed on the same road segment.…”

Section: Inferring Traffic Signsmentioning

confidence: 99%

“…Speed profiles were mathematically modeled by Andrieu et al (2013) and are a classical tool to measure the impact of traffic calming devices (Moreno and García 2013). Let us denote by x ∈ R the curvilinear abscissa of a vehicle along the track.…”

Section: Pre-processingmentioning

confidence: 99%

See 2 more Smart Citations

Traffic signal detection from in-vehicle GPS speed profiles using functional data analysis and machine learning

Méneroux¹,

Guilcher²,

Pierre

et al. 2019

Int J Data Sci Anal

View full text Add to dashboard Cite

The increasing availability of large-scale Global Positioning System (GPS) data stemming from in-vehicle embedded terminal devices enables the design of methods deriving road network cartographic information from drivers' recorded traces. Some machine learning approaches have been proposed in the past to train automatic road network map inference, and recently this approach has been successfully extended to infer road attributes as well, such as speed limitation or number of lanes. In this paper, we address the problem of detecting traffic signals from a set of vehicle speed profiles, under a classification perspective. Each data instance is a speed versus distance plot depicting over a hundred profiles on a 100-meter-long road span. We proposed three different ways of deriving features: the first one relies on the raw speed measurements; the second one uses image recognition techniques; and the third one is based on functional data analysis. We input them into most commonly used classification algorithms and a comparative analysis demonstrated that a functional description of speed profiles with wavelet transforms seems to outperform the other approaches with most of the tested classifiers. It also highlighted

show abstract

Section: Inferring Road Attributesmentioning

confidence: 99%

Section: Inferring Traffic Signsmentioning

confidence: 99%

See 1 more Smart Citation

Traffic signal detection from in-vehicle GPS speed profiles using functional data analysis and machine learning

Méneroux¹,

Guilcher²,

Pierre

et al. 2019

Int J Data Sci Anal

View full text Add to dashboard Cite

show abstract

“…The first step of a functional analysis is to convert the raw data into functional objects that leads to the use of an adapted smoothing procedure. However, the estimation of a space-speed profile from noisy measurements of position and speed is a complex nonparametric regression problem (see for example Andrieu et al 2013). Indeed, on the one hand, both the response variable (corresponding to speed) and the explanatory variable (corresponding to vehicle position) are noisy.…”

Section: Mathematical Properties Of Space-speed Profilesmentioning

confidence: 99%

A functional analysis of speed profiles: smoothing using derivative information, curve registration, and functional boxplot

Andrieu,

Pierre,

Bressaud

2013

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a functional analysis of a set of individual space-speed profiles corresponding to speed as function of the distance traveled by the vehicle from an initial point. This functional analysis begins with a functional modeling of space-speed profiles and the study of mathematical properties of these functions. Then, in a first step, a smoothing procedure based on spline smoothing is developed in order to convert the raw data into functional objets and to filter out the measurement noise as efficiently as possible. It is shown that this smoothing step leads to a complex nonparametric regression problem that needs to take into account two constraints: the use of the derivative information, and a monotonicity constraint. The performance of the proposed two-step estimator (smooth, and then monotonize) is illustrated on simulation studies and a real data example. In a second step, we use a curve registration method based on landmarks alignment in order to construct an average speed profile representative of a set of individual speed profiles. Finally, the variability of such a set is explored by the use of functional boxplots.

show abstract

“…According to [3] speed can be analyzed in three different ways: "spot measurements (by radar or loop detector), speed profile as a function of time (time-speed profile) or speed profile as a function of space (space-speed profile)". The spacespeed profiles consider speed against the vehicles position (i.e.…”

Section: Introductionmentioning

confidence: 99%

Road Speed Signatures from C-ITS messages

Moso

Cormier

Fouchal

et al. 2021

ICC 2021 - IEEE International Conference on Communications

View full text Add to dashboard Cite

Cooperative Intelligent Transport Systems(C-ITS) focus on improving safety, comfort, traffic and energy efficiency. Vehicle speed and other speed based indicators are commonly used parameters in traffic research for generation of driving profiles.The main goal for studying speed variation is to gain a better understanding on why drivers respond in certain ways to road/traffic conditions and to discover factors which affect their actions. The aim of this paper is to use a real dataset of Cooperative Awareness Messages generated in a C-ITS environment to generate speed signatures. We apply a segmentation technique and statistical analysis in generation and evaluation of road speed signatures. Based on our approach, interesting characteristics on the evolution of driving behavior are revealed from speed signatures.

show abstract

Estimation of space-speed profiles: A functional approach using smoothing splines

Cited by 3 publications

References 17 publications

Traffic signal detection from in-vehicle GPS speed profiles using functional data analysis and machine learning

Traffic signal detection from in-vehicle GPS speed profiles using functional data analysis and machine learning

A functional analysis of speed profiles: smoothing using derivative information, curve registration, and functional boxplot

Road Speed Signatures from C-ITS messages

Contact Info

Product

Resources

About