Geospatial Object Detection via Deconvolutional Region Proposal Network

Abstract

In the problem of geospatial object detection, the quality and amount of reference boxes significantly impact the detection performance and prediction speed of object detection networks. Nowadays, most of the popular detection methods adopt the anchor mechanism to generate reference boxes. This paper proposed an anchor-free and sliding-window-free deconvolutional region proposal network and constructed a two-stage deconvolutional object detection network. Instead of using an anchor mechanism, we proposed to use a deconvolutional neural network followed by a connected region generation module to generate reference boxes. The comparison experiments and quantitative analysis with NWPU VHR-10 dataset demonstrate that DeRPN can vastly reduce the number of reference boxes and improve the precision of the reference box coordinates. The experiments also suggest that our proposed two-stage object detection network can not only obtain the nearly state-of-the-art detection results but also achieve the prediction speed close to that of the one-stage detection network.