Experimental results using the public building dataset, SpaceNet, show that our method can detect buildings with skewed bounding boxes and has a state-of-the-art performance compared with other algorithms. The AM-ROI Align not only reduces abundant noise but also preserves the proper information of an object in ROI. For extracting fixed-size features from rotated proposals, we propose Auto Mask Region-Of-Interest Align (AM-ROI Align). Then, a Rotation Fast-Region Convolutional Neural Network (RFast-RCNN) is performed, which extracts fixed-size features from rotated proposals and utilizes them to obtain fine-detections.
First, the U-Rotation Region Proposal Network (U-RRPN) is proposed to generate rotated proposals through rotated anchors. To address these problems, we present the U-Rotation Detection Network (U-RDN), which can effectively detect buildings with arbitrarily orientated detection bounding boxes. Moreover, most algorithms detect rotated buildings with horizontal bounding boxes leading to many background pixels being preserved in the final detection, which is not beneficial for post-processing. SpaceNet focuses on four open source key pillars: data, challenges, algorithms, and tools. Before SpaceNet, computer vision researchers had minimal options to obtain free, precision-labeled, and high-resolution satellite imagery. Although many methods have been proposed, building detection is still a challenging problem due to complex scenes and small or arbitrarily orientated buildings. SpaceNet delivers access to high-quality geospatial data for developers, researchers, and startups. The data is comprised of 382,534 building footprints, covering an area of 2,544 sq. Building detection in high spatial resolution optical remote sensing images is important for city planning, navigation, population estimation and many other applications. SpaceNet 1 (SpaceNet 1: Building Detection v1) SpaceNet 1: Building Detection v1 is a dataset for building footprint detection.
0 kommentar(er)
