Peer-Reviewed Journal Details
Mandatory Fields
Hurney, P,Waldron, P,Morgan, F,Jones, E,Glavin, M
2015
February
Iet Intelligent Transport Systems
Night-time pedestrian classification with histograms of oriented gradients-local binary patterns vectors
Published
()
Optional Fields
pedestrians traffic engineering computing feature extraction image classification infrared detectors automobiles support vector machines image segmentation filtering theory night-time pedestrian classification histogram of oriented gradient-local binary pattern vectors night vision systems high end luxury cars low-cost infrared sensors far infrared automotive image streams support vector machine classifier region of interest RoF captured infrared frame seeded region growing filtering method bounding box ROI reduced false positive rate local binary pattern feature extraction histogram of oriented gradient feature extraction Kalman filter detection rates VISION TRACKING
9
75
85
The use of night vision systems in vehicles is becoming increasingly common, not just in luxury cars but also in the more cost sensitive sectors. Numerous approaches using infrared sensors have been proposed in the literature to detect and classify pedestrians in low visibility situations. However, the performance of these systems is limited by the capability of the classifier. This paper presents a novel method of classifying pedestrians in far-infrared automotive imagery. Regions of interest are segmented from the infrared frame using seeded region growing. A novel method of filtering the region growing results based on the location and size of the bounding box within the frame is described. This results in a smaller number of regions of interest for classification, leading to a reduced false positive rate. Histograms of oriented gradient features and local binary pattern features are extracted from the regions of interest and concatenated to form a feature for classification. Pedestrians are tracked with a Kalman filter to increase detection rates and system robustness. Detection rates of 98%, and false positive rates of 1% have been achieved on a database of 2000 images and streams of video; this is a 3% improvement on previously reported detection rates.
10.1049/iet-its.2013.0163
Grant Details
Publication Themes