Vehicle detection is motivated by different fields of application,e.g. traffic flow management, road planning or estimation of airand noise pollution. Therefore, an algorithm that automatically detectsand counts vehicles in air- or space-borne images would effectively support these traffic-related analyses in urban planning.Due to the small vehicle size in satellite images detection of single vehicles would deliver ambiguous results. Hence, our schemefocuses primarily on the extraction of vehicle queues, as the pattern of a queue makes it better distinguishable (as a whole) fromsimilar objects. Hypotheses for queues are generated by sophisticated extraction of ribbons. Within these ribbons single vehiclesare searched for by least-squares fitting of Gaussian kernels to the width and contrast function of a ribbon. Based on the resultingparameter values, false and correct hypotheses are discerned. The results show that the analysis of width and contrast informationusing least square optimization is able to extract single vehiclesfrom queues with high correctness. Still, the completeness of theoverall extraction is relatively low, since only queues can be extracted but no isolated vehicles. The results clearly show thatthe approach is promising but further improvements are necessaryto achieve a higher completeness.     «

Vehicle detection is motivated by different fields of application,e.g. traffic flow management, road planning or estimation of airand noise pollution. Therefore, an algorithm that automatically detectsand counts vehicles in air- or space-borne images would effectively support these traffic-related analyses in urban planning.Due to the small vehicle size in satellite images detection of single vehicles would deliver ambiguous results. Hence, our schemefocuses primarily on the extraction of vehicl...     »