Rotated region based CNN for ship detection

• Published in: 2017 IEEE International Conference on Image Processing (ICIP) pp. 900 - 904
• Main Authors: Liu, Zikun, Hu, Jingao, Weng, Lubin, Yang, Yiping
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2017
• Subjects: Convolution; convolutional neural network; Feature extraction; Marine vehicles; Object detection; Proposals; Rotated region; ship detection; Task analysis; Training
• ISSN: 2381-8549
• DOI: 10.1109/ICIP.2017.8296411

The state-of-the-art object detection networks for natural images have recently demonstrated impressive performances. However the complexity of ship detection in high resolution satellite images exposes the limited capacity of these networks for strip-like rotated assembled object detection which are common in remote sensing images. In this paper, we embrace this observation and introduce the rotated region based CNN (RR-CNN), which can learn and accurately extract features of rotated regions and locate rotated objects precisely. RR-CNN has three important new components including a rotated region of interest (RRoI) pooling layer, a rotated bounding box regression model and a multi-task method for non-maximal suppression (NMS) between different classes. Experimental results on the public ship dataset HRSC2016 confirm that RR-CNN outperforms baselines by a large margin.