This paper explores the concept of the Network Fundamental Diagram for two-dimensional pedestrian networks. In doing so, we investigate if the average performance of the network can be described as a function of the average density or accumulation of the network, in line with recent findings on discrete vehicular traffic networks. We show that this is indeed the case, by considering data from w...

Most of public travel information services nowadays are limited to the driving navigation or bus/subway guidance. Practical needs for pedestrian navigation yet haven’t got met enough and usually result in unacceptable travel route planning. This paper presents an approach on building Walkway network with different map layers for pedestrian specified facilities, and then implements pedestrian ai...

From a mobility perspective, walking is considered to be the most sustainable transport mode. One of the consequences of motor-oriented urban configuration on pedestrian mobility is urban fragmentation, which affects sustainability in cities. In this paper, we use a natural-based approach to landscape fragmentation and connectivity (inherited from landscape ecology) for pedestrian mobility plan...

⎯ This paper describes a pedestrian tracking system that uses a new movement prediction technique based on an association of Cellular Automata (CA) and a Neural Network (NN). The proposed prediction technique aims to learn the behaviour of pedestrian movement directly from images. A CA is applied to capture the pedestrian movement. The derived CA patterns are then used to train the NN. The trai...

BACKGROUND Pedestrian injuries among older people tend to occur near their residence. However, knowledge regarding whether distance travelled from home to the injury site or road environmental/socioeconomic factors affect injury severity remains limited. METHODS A cross-sectional study was performed using injury registry data from the Kurume City Fire Department, Japan. Distance travelled fro...

Observation in absolute darkness and daytime under every atmospheric situation is one of the advantages of thermal imaging systems. In spite of increasing trend of using these systems, there are still lots of difficulties in analysing thermal images due to the variable features of pedestrians and atmospheric situations. In this paper an efficient method is proposed for detecting pedestrians in ...

This paper documents experiments which have been carried out with several neural network systems designed to categorise pedestrian shapes from non-pedestrian shapes. Active Contour models (‘Snakes’) [1] have been used to obtain contours of pedestrians as they move around the visual field. Neural networks have then been trained on representations of these relaxed snakes. The neural network syste...

Across a majority of pedestrian detection datasets, it is typically assumed that pedestrians will be standing upright with respect to the image coordinate system. This assumption however, is not always valid for many visionequipped mobile platforms such as mobile phones, UAVs or construction vehicles on rugged terrain. In these situations, the motion of the camera can cause images of pedestrian...

We present a novel Dynamic Bayesian Network for pedestrian path prediction in the intelligent vehicle domain. The model incorporates the pedestrian situational awareness, situation criticality and spatial layout of the environment as latent states on top of a Switching Linear Dynamical System (SLDS) to anticipate changes in the pedestrian dynamics. Using computer vision, situational awareness i...

The paper presents an original approach for pedestrian detection using the neural network classifier called Concurrent Self-Organizing Maps (CSOM), previously introduced by first author; it represents a winner-takes-all collection of neural modules. The algorithm has the following stages: (a) feature selection using one of the three candidate techniques Histogram of Oriented Gradients (HOG)/1D ...