Flying target detection and recognition by feature fusion

We present a near-real-time visual-processing approach for automatic airborne target detection and classification. Detection is based on fast and robust background modeling and shape extraction, while recognition of target classes is based on shape and texture-fused querying on a-priori built real datasets. The presented approach can be used in defense and surveillance scenarios where passive detection capabilities are preferred (or required) over a secured area or protected zone. 1 Introduction Visual detection, recognition, classification and tracking of stationary or moving targets are among the most active research areas in computer vision and image processing fields. Applications built on results of these research areas are constantly sought to be deployed for both defensive and offensive scenarios, including civilian and military use. For civilian applications, wide area surveillance, crowd and traffic monitoring, and target tracking are the most important fields, while for military applications, troops and asset protection , region of interest surveillance, target detection, and tracking are probably the most important scenarios. Aiding such tasks by intelligent and automatic visual processing is important since such methods can support the detection, recognition, and alerting tasks of security personnel. Also, visual processing sensors/nodes can provide a means for passive detection (without requiring active signals), thus making them harder to detect and disarm in case of sensitive scenarios. This paper presents a solution for one aspect of the above-described wide range of possibilities, focusing on automatic airborne target detection and classification. The presented approach can be used in defense and surveillance scenarios, where passive detection capabilities are preferred (or required) over a secured area or protected zone. The goals are to automatically detect and recognize the class of observed flying targets from varying angles, views, size, and environmental conditions, while running on commodity hardware. Lu et al. 1 presented a small-ship target detection method, where point-like infrared images of small ships are processed to automatically detect ships on the sea level from a distance. Simple edge detection on a median filtered image is used to extract possible ship locations. In other works 2 small targets above a sea or sky background are extracted by infrared processing by using directional derivative operators and clustering. Deng et al. 3 present small target detection in infrared, based on self-information maps and locally adaptive background thresholding and region growing, producing robust detection results. While infrared processing can help the detection task (especially during the night), it is not …