Development of probabilistic pedestrian fatality model for characterizing pedestrian-vehicle collisions

Oh, Cheol; Kang, Youn-Soo; Youn, Yongsu; Konosu, Atsuhiro

doi:10.1007/s12239-008-0024-7

Cited by 19 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reported methods used for vehicle classification in previous studies included Naïve Bayes (NB) ( 28 – 30 ), K-nearest neighbor classification (KNN) ( 31 ), decision (classification) tree ( 32 ), support vector machine (SVM) ( 21 , 33 , and 34 ), and artificial neural network (ANN) ( 5 , 7 , 35 – 37 ). This section briefly introduces these methods and applies some of them for vehicle classification.…”

Section: Vehicle Classification Methodsmentioning

confidence: 99%

Automatic Vehicle Classification using Roadside LiDAR Data

Jian

Zheng

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

This research presented a new approach for vehicle classification using roadside LiDAR sensor. Six features (one feature, object height profile, contains 10 sub-features) extracted from the vehicle trajectories were applied to distinguish different classes of vehicles. The vehicle classification aims to assign the objects into ten different types defined by FHWA. A database containing 1,056 manually marked samples and their corresponding pictures was provided for analysis. Those samples were collected at different scenarios (roads and intersections, different speed limits, day and night, different distance to LiDAR, etc.). Naïve Bayes, K-nearest neighbor classification, random forest (RF), and support vector machine were applied for vehicle classification. The results showed that the performance of different methods varied by class. RF has the highest overall accuracy among those investigated methods. Some types were merged together to serve different types of users, which can also improve the accuracy of vehicle classification. The validation indicated that the distance between the object and the roadside LiDAR can influence the accuracy. This research also provided the distribution of the overall accuracy of RF along the distance to LiDAR. For the VLP-16 LiDAR, to achieve an accuracy of 91.98%, the distance between the object and LiDAR should be less than 30 ft. Users can set up the location of the roadside LiDAR based on their own requirements of the classification accuracy.

show abstract

Section: Vehicle Classification Methodsmentioning

confidence: 99%

Automatic Vehicle Classification using Roadside LiDAR Data

Jian

Zheng

et al. 2019

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Therefore, the speed of training is much faster than the traditional back-propagation neural network (BP-NN). In this paper, PNN was implemented using the package "PNN" written in the statistical language-R [41,42]. The smoothing parameter was identified by the package automatically using a genetic algorithm [43].…”

Section: Probabilistic Neural Network (Pnn)mentioning

confidence: 99%

Object Classification with Roadside LiDAR Data Using a Probabilistic Neural Network

Zhang

Ma³

et al. 2021

Electronics

View full text Add to dashboard Cite

Object classification is important information for different transportation areas. This research developed a probabilistic neural network (PNN) classifier for object classification using roadside Light Detection and Ranging (LiDAR). The objective was to classify the road user on the urban road into one of four classes: Pedestrian, bicycle, passenger car, and truck. Five features calculated from the point cloud generated from the roadside LiDAR were selected to represent the difference between different classes. A total of 2736 records (2062 records for training, and 674 records for testing) were manually marked for training and testing the PNN algorithm. The data were collected at three different sites representing different scenarios. The performance of the classification was evaluated by comparing the result of the PNN with those of the support vector machine (SVM) and the random forest (RF). The comparison results showed that the PNN can provide the results of classification with the highest accuracy among the three investigated methods. The overall accuracy of the PNN for object classification was 97.6% using the testing database. The errors in the classification results were also diagnosed. Discussions about the direction of future studies were also provided at the end of this paper.

show abstract

“…A different approach is required when the number of cases is too high. In their recent studies, Oh et al (2008) and Rosen and Sander (2009) have developed probabilistic models that combine the analysis of real-world accident reconstruction techniques and the study of kinematic parameters and mechanisms of injury. Oh et al (2008) also complements these models with a suitable number of FEM simulations and laboratory impact tests to validate the results for the design of active safety devices.…”

Section: Virtual Reconstruction Of Real Accidentsmentioning

confidence: 99%

“…In his recent probabilistic model, Oh et al (2008) used empirical mathematical expressions such as the one developed by Schmidt and Nagel (1971) to determine the value of the collision speed. The empirical expression is based on the braliing marks, the static coefficient of friction, the height of the pedestrian center of mass and the throw-distance.…”

Section: Accident Database and Reconstruction Toolmentioning

confidence: 99%

Multivariate modeling of pedestrian fatality risk through on the spot accident investigation

Badea

Furones

Páez

et al. 2010

Int.J Automot. Technol.

View full text Add to dashboard Cite

Pedestrians are the most vulnerable users of public roads and represent one of the largest groups of road casualties; their death rate around the world due to vehicle-pedestrian collisions is high and tending to rise. In Spain, as in other countries of the European Union, steps have been taken to reduce the number and consequences of such accidents, with encouraging results in recent years. A key to countering this concern is the accident research activity that has obtained remarkable achievements in different fields, especially when multidisciplinary approaches are taken. This paper describes the development of a multivariate model that is able to detect the most influential parameters on the consequences of vehiclepedestrian collision and to quantify their impact on pedestrian fatality risk. First, an accident database containing detailed information and parameters of vehicle-pedestrian collisions in Madrid has been developed. The accidents were investigated on the spot by INSIA accident investigation teams and analyzed using advanced reconstruction techniques. The model was then developed with two components: (1) a classification tree that characterizes and selects the explanatory variables, identifying their interactions, and (2) a binary logistic regression to quantify the influence of each variable and interaction resulting from the classification tree. The whole model represents an important tool for identifying, quantifying and predicting the potential impact of measures aimed at reducing injuries in vehicle-pedestrian collisions.

show abstract

Development of probabilistic pedestrian fatality model for characterizing pedestrian-vehicle collisions

Cited by 19 publications

References 11 publications

Automatic Vehicle Classification using Roadside LiDAR Data

Automatic Vehicle Classification using Roadside LiDAR Data

Object Classification with Roadside LiDAR Data Using a Probabilistic Neural Network

Multivariate modeling of pedestrian fatality risk through on the spot accident investigation

Contact Info

Product

Resources

About