Evaluation of urban road vehicle detection from high resolution remote sensing imagery using object-oriented method

An object-oriented image analysis method has been developed to detect, classify and count road vehicles from airborne color digital orthoimagery. The basic difference, especially when compared with previously developed pixel-based vehicle detection procedures, is that we don't process and analyze image pixels, but rather image objects that are extracted from image segmentation. We aim to characterize the performance of the proposed method under varying conditions. For this purpose a representative set of road segment images was selected from available images. The extracted vehicle images were compared with the manually labelled vehicle images. Experimental results indicate that the proposed method has a good performance under varying conditions of road geometry, vehicle contrast, variability of pavement characteristics, and vehicle density. The detection rates of all test road-segments are high with very few false alarms.