DEVELOPING A MODEL FOR PEDESTRIAN ROUTE SELECTION AT COLBY

http://digitalcommons.colby.edu/atlasofmaine2006/1020/thumbnail.jpg

Comparative evaluation of pedestrian detection methods for mobile bus surveillance

We present a comparative evaluation of the state-of-art algorithms for detecting pedestrians in low frame rate and low resolution footage acquired by mobile sensors. Four approaches are compared: a) The Histogram of Oriented Gradient (HoG) approach [1]; b) A new histogram feature that is formed by the weighted sum of both the gradient magnitude and the filter responses from a set of elongated Gaussian filters [2] corresponding to the quantised orientation, called Histogram of Oriented Gradient Banks (HoGB) approach; c) The codebook based HoG feature with branch-and-bound (efficient subwindow search) algorithm [3] and; d) The codebook based HoGB approach. Results show that the HoG based detector achieves the highest performance in terms of the true positive detection, the HoGB approach has the lowest false positives whilst maintaining a comparable true positive rate to the HoG, and the codebook approaches allow computationally efficient detection.

Pedestrian detection for mobile bus surveillance

In this paper, we present a system for pedestrian detection involving scenes captured by mobile bus surveillance cameras in busy city streets. Our approach integrates scene localization, foreground and background separation, and pedestrian detection modules into a unified detection framework. The scene localization module performs a two stage clustering of the video data. In the first stage, SIFT Homography is applied to cluster frames in terms of their structural similarities and second stage further clusters these aligned frames in terms of lighting. This produces clusters of images which are differential in viewpoint and lighting. A kernel density estimation (KDE) method for colour and gradient foreground-background separation are then used to construct background model for each image cluster which is subsequently used to detect all foreground pixels. Finally, using a hierarchical template matching approach, pedestrians can be identified. We have tested our system on a set of real bus video datasets and the experimental results verify that our system works well in practice.

Fuzzy simulation of pedestrian walking path considering local environmental stimuli

Pedestrian steering activity is a perception-based decision making process that involves interaction with the surrounding environment and insight into environmental stimuli. There are many stimuli within the environment that influence pedestrian wayfinding behaviour during walking activities. However, compelling factors such as individual physical and psychological characteristics and trip intention cause the behaviour become a very fuzzy concept. In this paper pedestrian steering behaviour is modelled using a fuzzy logic approach. The objective of this research is to simulate pedestrian walking paths in indoor public environments during normal and non-panic situations. The proposed algorithm introduces a fuzzy logic framework to predict the impact of perceived attractive and repulsive stimuli, within the pedestrian's field of view, on movement direction. Environmental stimuli are quantified using the social force method. The algorithm is implemented in a simulated area of an office corridor consist of a printer and exit door. Stochastic simulation using the proposed fuzzy algorithm generated realistic walking trajectories, contour map of dynamic change of environmental effects in each step of movement and high flow areas in the corridor.

Pedestrian steering behaviour modelling within the built environment

Prediction of pedestrians’ steering behaviours within the built environments under normal and non-panic situations is useful for a wide range of applications, which include social science, psychology, architecture, and computer graphics. The main focus is on prediction of the pedestrian walking paths and the influences from the surrounding environment from the engineering point of view.

The association between attributions of responsibility for motor vehicle accidents and patient satisfaction: a study within a no-fault injury compensation system

This study set out to test the relationship between attributions of responsibility for motor vehicle accidents and satisfaction with personal injury compensation systems.

A genetic fuzzy system to model pedestrian walking path in a built environment

A study on the pedestrian's steering behaviour through a built environment in normal circumstances is presented in this paper. The study focuses on the relationship between the environment and the pedestrian's walking trajectory. Owing to the ambiguity and vagueness of the relationship between the pedestrians and the surrounding environment, a genetic fuzzy system is proposed for modelling and simulation of the pedestrian's walking trajectory confronting the environmental stimuli. We apply the genetic algorithm to search for the optimum membership function parameters of the fuzzy model. The proposed system receives the pedestrian's perceived stimuli from the environment as the inputs, and provides the angular change of direction in each step as the output. The environmental stimuli are quantified using the Helbing social force model. Attractive and repulsive forces within the environment represent various environmental stimuli that influence the pedestrian's walking trajectory at each point of the space. To evaluate the effectiveness of the proposed model, three experiments are conducted. The first experimental results are validated against real walking trajectories of participants within a corridor. The second and third experimental results are validated against simulated walking trajectories collected from the AnyLogic® software. Analysis and statistical measurement of the results indicate that the genetic fuzzy system with optimised membership functions produces more accurate and stable prediction of heterogeneous pedestrians' walking trajectories than those from the original fuzzy model. © 2014 Elsevier B.V. All rights reserved.

Attributions of responsibility for motor vehicle accidents and post-injury outcomes.

 This thesis explored the relationship between attributions of responsibility for motor vehicle accidents and post-injury outcomes among a large sample of TAC clients. Results demonstrated that, despite similar levels of physical injury, people who attribute responsibility for accidents to other persons or circumstances experience poorer physical and mental health recovery in comparison to those who attribute responsibility to themselves.

Developing a Model for Pedestrian Route Selection at Colby

Millions of unconscious calculations are made daily by pedestrians walking through the Colby College campus. I used ArcGIS to make a predictive spatial model that chose paths similar to those that are actually used by people on a regular basis. To make a viable model of how most travelers choose their way, I considered both the distance required and the type of traveling surface. I used an iterative process to develop a scheme for weighting travel costs which resulted in accurate least-cost paths to be predicted by ArcMap. The accuracy was confirmed when the calculated routes were compared to satellite photography and were found to overlap well-worn “shortcuts” taken between the paved paths throughout campus.

Avaliação da gravidade do trauma em condutores de motocicleta vítimas de acidentes de trânsito no Rio Grande do Norte

Descriptive exploratory study, prospective, with quantitative approach, performed on the Monsenhor Walfredo Gurgel Hospital Complex (MWGHC), in Natal/RN, aiming to identify injuries by body area and wound severity on drivers who suffered motorcycle accidents, evaluate the severity of injuries and trauma on these drivers and identify the existence of association between wound and trauma severity and some of the accident s characteristics. The population comprised 371 motorcycle drivers, with data collected between October and December 2007. We used as instruments the Abberviated Injury Scale (AIS), Injury Severity Score (ISS) and the Glasgow Coma Scale (GCE1). The results show that, concerning characterization, there was a predominance of the male gender (88.4%), aged between 18 and 24 years (39.90%), originating from the Natal metropolitan region (55.79%), with fundamental-level instruction (51.48%), catholic (75.78%), married (47.98%). 23.18% work on commerce-related activities and 75.20% have income of up to 2 minimum wages. As for the accident s characteristics, the predominant shift was the afternoon (46.36%), received up to one hour after the event (50.67%), transported by countryside ambulances colleagues and relatives (51.21%), 25.34% had the accident on Sunday; 53.91% suffered falls and vehicle rolls; among the collisions there was a predominance of the motorcycle-automoblie type (28.03%); 52,6% were licensed and among these 50.76% had up to one year of license; 65.50% declared not having suffered previous accidents; 65.77% declared waring helmets in the time of the accident; 57.41% said not to have used drugs, and among those who used, alcohol was the most consumed (98.10%). The lowest score evaluated by GCS1 (3 to 8) was linked to drivers who suffered accidents on Saturday (10.3%), those who were not wearing helmets (14.29%) and the victims of motorcycle-pedestrian/animal crashes (13.33%). The body areas most affected had AIS between 1 and 3 (95.76%) and were: external surface (39.90%) and head/neck (33.20%). As for trauma severity, the highest scores (ISS>25) belonged to those who consumed alcohol (30.73%), suffered falls or vehicle rolls (48.9%) and those attended to 3 hours or longer after the accident (50%). We conclude that for motorcycle drivers who suffered accidents, age, gender, weekday, type of accident, use of drugs and the absence of helmet use signal both to the risk of occurrence of these events, as well as for the greater severity of injuries and trauma.