Investigación

Publicación (Artículos en revistas científicas)

Night Time and Low Visibility Driving Assistance Based on the Application of Colour and Geometrical Features Extraction

Meneses Chaus, Juan Manuel; Eckert, Martina
Resumen:
The present work shows an application to detect cars in night environments as a means to assist the car driving through HSV (Hue, Saturation, Value) colour extraction and geometric modelling. The developed algorithm has been implemented in smart devices through the platform Android. The detection and tracking of vehicles are implemented in low visibility environments such as night time, raining or snowing conditions; the different tests carried out confirm high performance rates of detection (p = 95.2 %). The information provided by the different sensors of the smart devices have been used to generate virtual information in a real driving environment (Augmented Reality) in order to complement the functionalities of the purposed solution. This information consists of visual, vibratory and auditory warnings that detect possible collisions and dangerous driving situations.
Año:
2016
Tipo de publicación:
Artículos en revistas científicas
Revista:
nternational Conference on Smart Cities
Número:
118-127
Mes:
Junio
DOI:
10.1007/978-3-319-39595-1_12
Hits: 3933