Ship Detection in Remote Sensing Image based on Faster R-CNN with Dilated Convolution
Wei Shuaihao, Huimin Chen, Xiaojin Zhu, Hesheng Zhang
Abstract
Ship detection based on remote sensing image can provide effective assistance for maritime reconnaissance, port and fisheries management. This paper mainly presents an improved Faster R-CNN algorithm for ship detection with dilated convolution. Firstly, the image of remote sensing ship is preprocessed. This paper uses dark channel prior method to dehaze image and enhance dehazed image quality by grey world algorithm. Second, The Faster R-CNN is improved in ship detection. The dilated convolutional is introduced into Faster R-CNN to increases its feature extraction capability. Finally, ship detection software platform is built. The remote ship image preprocessing and ship detection network is integrated into an application software. The ship detection network can be trained end to end. Experimental results on the HRSC2016 datasets illustrated that the proposed presents a good performance for ship detection task.