Ship Targets Detection Based on Visual Attention

The ship targets are more attractive than the sky, the sea and the buildings, so the ship detection algorithm based on improved visual attention model is proposed. Firstly, low frequency and high frequency features are extracted by using wavelet transform theory. Then use improved Top-hat filter to suppress cloud and strong sea clutter. The orientation feature is obtained by using the improved Gabor filter, and the edge-texture feature is obtained by using the DMT. The color and movement features are also obtained by converting the images from GRB color space to HSI color space. Finally, the saliency map is got by weighted linear combinations, and the target area is segmented by adaptive threshold algorithm.