CNN based renormalization method for ship detection in VHR remote sensing images

Ship detection with very high resolution (VHR) remote sensing image has recently been an attractive topic due to rapid development of deep learning. Current researches on ship detection are generally confronted with a big challenge that existing methods failed to get high quality of object proposal with good intersection-over-union (IOU) before detection. In this paper, a Convolutional Neural Network (CNN) based renormalization method is proposed to improve the quality of object proposal. First, CNN is used to predict shape information of candidate ships' which are involved with rotation, location and scale in patches. Then, a renormalization net is designed to adjust the candidate ships in patches by correcting the shape information and renormalizing it to uniform patch. In this way, good candidate objects in patches could be generated and will be helpful with improving following ship detection. The proposed renormalization net was tested on a Google-Earth handcraft dataset. The experimental result demonstrates the proposed renormalization net greatly improve the ship detection with both of good detection accuracy and high IOU.