An Integrated Traffic and Pedestrian Model_based Vision System

The paper describes a novel integrated vision system in which two autonomous visual modules are combined to interpret a dynamic scene. The first module employs a 3D model-based scheme to track rigid objects such as vehicles. The second module uses a 2D deformable model to track non-rigid objects such as people. The principal contribution is a novel method for handling occlusion between objects within the context of this hybrid tracking system. The practical aim of the work is to derive a scene description that is sufficiently rich to be used in a range of surveillance tasks. The paper describes each of the modules in outline before detailing the method of integration and the handling of occlusion in particular. Experimental results are presented to illustrate the performance of the system in a dynamic outdoor scene involving cars and people.

A novel shape feature for fast region-based pedestrian recognition

A new class of shape features for region classification and high-level recognition is introduced. The novel Randomised Region Ray (RRR) features can be used to train binary decision trees for object category classification using an abstract representation of the scene. In particular we address the problem of human detection using an over segmented input image. We therefore do not rely on pixel values for training, instead we design and train specialised classifiers on the sparse set of semantic regions which compose the image. Thanks to the abstract nature of the input, the trained classifier has the potential to be fast and applicable to extreme imagery conditions. We demonstrate and evaluate its performance in people detection using a pedestrian dataset.

Surveillance camera calibration from observations of a pedestrian

Calibrated cameras are an extremely useful resource for computer vision scenarios. Typically, cameras are calibrated through calibration targets, measurements of the observed scene, or self-calibrated through features matched between cameras with overlapping fields of view. This paper considers an approach to camera calibration based on observations of a pedestrian and compares the resulting calibration to a commonly used approach requiring that measurements be made of the scene.

Effect of building gap to improve pedestrian comfort levels and ventilation

Rapid rates of urbanization have resulted into increased concerns of urban environment. Amongst them, wind and thermal comfort levels for pedestrians have attracted research interest. In this regards, urban wind environment is seen as a crucial components that can lead to improved thermal comfort levels for pedestrian population. High rise building in modern urban setting causes high levels of turbulence that renders discomfort to pedestrians. Additionally, a higher frequency of high ris e buildings at a particular region acts as a shield against the wind flow to the lower buildings beyond them resulting into higher levels of discomfort to users or residents. Studies conducted on developing wind flow models using Computational Fluid Dynami cs (CFD) simulations have revealed improvement in interval to height ratios can results into improved wind flow within the simulation grid. However, high value and demand for land in urban areas renders expansion to be an impractical solution. Nonetheless, innovative utilization of architectural concepts can be imagined to improve the pedestrian comfort levels through improved wind permeability. This paper assesses the possibility of through-building gaps being a solution to improve pedestrian comfort levels.

The application of social marketing in reducing road traffic accidents amoung young male drivers: an investigation using physical fear threat appeals

There were 338 road fatalities on Irish roads in 2007. Research in 2007 by the Road Safety Authority in Ireland states that young male drivers (17 – 25 years) are seven times more likely to be killed on Irish roads than other road users. The car driver fatality rate was found to be approximately 10 times higher for young male drivers than for female drivers in 2000. Young male drivers in particular demonstrate a high proclivity for risky driving behaviours. These risky behaviours include drink driving, speeding, rug-driving and engaging in aggressive driving. Speed is the single largest contributing factor to road deaths in Ireland. Approximately 40% of fatal accidents are caused by excessive or inappropriate speed. This study focuses on how dangerous driving behaviours may be addressed through social marketing. This study analyses the appropriate level of fear that needs to be induced in order to change young male driving behaviour.

An evaluation of the pedestrian classification in a multi-domain multi-modality setup

The objective of this article is to study the problem of pedestrian classification across different light spectrum domains (visible and far-infrared (FIR)) and modalities (intensity, depth and motion). In recent years, there has been a number of approaches for classifying and detecting pedestrians in both FIR and visible images, but the methods are difficult to compare, because either the datasets are not publicly available or they do not offer a comparison between the two domains. Our two primary contributions are the following: (1) we propose a public dataset, named RIFIR , containing both FIR and visible images collected in an urban environment from a moving vehicle during daytime; and (2) we compare the state-of-the-art features in a multi-modality setup: intensity, depth and flow, in far-infrared over visible domains. The experiments show that features families, intensity self-similarity (ISS), local binary patterns (LBP), local gradient patterns (LGP) and histogram of oriented gradients (HOG), computed from FIR and visible domains are highly complementary, but their relative performance varies across different modalities. In our experiments, the FIR domain has proven superior to the visible one for the task of pedestrian classification, but the overall best results are obtained by a multi-domain multi-modality multi-feature fusion.