Pedestrian detection is a canonical problem for safety and security applications, it remains challenging due to the highly variable lighting conditions in which pedestrians must be detected. This article investigates several domain adaptation approaches adapt RGB-trained detectors thermal domain. Building on our earlier work privacy-preserving pedestrian detection, we conducted an extensive exp...

BACKGROUND Pedestrian injury frequently results in devastating and costly injuries and accounts for 11% of all road user fatalities. In the United States in 2006 there were 4,784 fatalities and 61,000 injuries from pedestrian injury, and in 2007 there were 4,654 fatalities and 70,000 injuries. In Canada, injury is the leading cause of death for those under 45 years of age and the fourth most co...

This work presents a vision-based system for detecting and localizing pedestrians in road environments by means of a statistical technique. Initially, attentive vision techniques relying on the search for specific characteristics of pedestrians such as vertical symmetry and strong presence of edges, allow to select interesting regions likely to contain pedestrians. These regions are then used t...

This paper presents the method for detecting pedestrian recently implemented on the ARGO vehicle. The perception of the environment is performed through the sole processing of images acquired from a vision system installed on board of the vehicle: the analysis of a monocular image delivers a first coarse detection, while a distance refinement is performed thanks to a stereo vision technique.

In this project, I develop an approach to post process local pedestrian detection by incorporating cues from the background. This approach uses a combination of several location specific color classifiers to quickly reduce the number of the local detector responses by discarding improbable results. An experimental method for color comparison is explored in this project to supplement existing te...

Recently, pedestrian detection from in-vehicle camera images is becoming an important technology in ITS (Intelligent Transportation System). However, it is difficult to detect pedestrians stably due to the variety of their poses and their backgrounds. To tackle this problem, we propose a method to detect various pedestrians from in-vehicle camera images by using multiple classifiers correspondi...

6 This paper presents a module for pedestrian detection from a 7 moving vehicle in low-light conditions. The algorithm make 8 use of a single far infrared camera based on a microbolometer. 9 Images of the area ahead of the vehicle are analyzed 10 to determine if any pedestrian might be in its trajectory. 11 Detection is achieved by searching for distributions of 12 temperatures in the scene sim...

Detection of human beings with accuracy in visual surveillance systems is important for various application areas like remote and mobile monitoring, traffic monitoring, public safety and abnormal event detection. The first step in detection process is to detect the object which is in motion and further classify it and track the objects. The paper further directs towards the detection and tracki...

Nowadays, pedestrian recognition in far-infrared images toward realizing a night vision system becomes a hot topic. However, sufficient performance could not be achieved by conventional schemes for pedestrian recognition in farinfrared images. Since the properties of far-infrared images are different from visible images, it is not known what kind of scheme is suitable for pedestrian recognition...

Previous vehicle-to-pedestrian simulations and experiments using pedestrian dummies and cadavers have shown that factors such as vehicle shape, pedestrian anthropometry and pre-impact conditions influence pedestrian kinematics and injury mechanisms. Generic pedestrian bucks, that approximate the geometrical and stiffness properties of current vehicles, would be useful in studying the influence ...