MULTI-SCALE FEATURE FUSION NETWORK FOR OBJECT DETECTION IN VHR OPTICAL REMOTE SENSING IMAGES

In this paper, we propose a multi-scale feature fusion network (MS-FF Net) based on convolutional neural network (CNN) to deal with object detection in VHR images. In CNN, the low-level layers contain rich detail information and the high-level layers contain rich semantic information. Inspired by the idea of feature fusion, we propose an additional multi-scale feature fusion layer (MFL) to fuse the information between detail and semantic features. Then both large and small objects are considered by this network. Moreover, the network architecture and training strategies are designed to improve performance. Experiments on NWPU VHR-10 dataset demonstrate that the method with MFLs achieves significant improvement and outperforms compared methods in terms of mean average precision. Specially, the detection precision of airplane, baseball diamond, basketball court, ground track field and harbor categories exceeds 90% which is much higher than that of compared methods.