engleski

Two-stage segmentation for detection of suspicious objects in aerial and long-range surveillance applications

This paper presents a novel two-stage data segmentation approach for detection of artificial materials and objects in non-urban terrain. High resolution image of the unknown terrain taken with the digital camera from relatively large distance is divided into smaller sub-images for further processing. Each sub-image is segmented and information about obtained cluster centers is transferred to the next stage. Second segmentation stage uses information about cluster centers from all sub-images and applies the same clustering method to this data set. Finally, decision-making module evaluates all potential candidate segments and eventually proposes segments that have high possibility of presenting artificial material or object in the input image.

Image segmentation; mean shift; object detection; aerial images

nije evidentirano