Detecting and Counting Vehicles from High Resolution Satellite Imagery

R. Alba-Flores, S. Kuthadi, and F. Rios-Gutierrez (USA)


Image segmentation, high resolution satellite data,IKONOS


In this paper an approach for the detection, classification, and counting of vehicles from satellite images is presented. The images are 1-m panchromatic from the IKONOS satellite and contain highway scenes from different places in the United States. The approach is based on segmentation and it is divided in two parts. In the first part, the bright vehicles are detected using multiple threshold techniques. The second part detects the dark vehicles and it is based on the Otsu method. After all the vehicles are detected, the algorithm classifies them as trucks or cars. The approach is explained in detail, and the results are presented, as well as the shortcomings and future directions for improvement.

Important Links:

Go Back