Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no matter whether there exist objects or not. This paradigm, although effective, is inefficient because the detectors have to go through all patches, severely hindering the inference speed. This paper presents an Objectness Activation Network (OAN) to help detectors focus on fewer patches but achieve more efficient inference and more accurate results, enabling a simple and effective solution to object detection in large images. In brief, OAN is a light fully-convolutional network for judging whether each patch contains objects or not, which can be easily integrated into many object detectors and jointly trained with them end-to-end. We extensively evaluate our OAN with five advanced detectors. Using OAN, all five detectors acquire more than 30.0% speed-up on three large-scale aerial image datasets, meanwhile with consistent accuracy improvements. On extremely large Gaofen-2 images (29200$\times$27620 pixels), our OAN improves the detection speed by 70.5%. Moreover, we extend our OAN to driving-scene object detection and 4K video object detection, boosting the detection speed by 112.1% and 75.0%, respectively, without sacrificing the accuracy. Code is available at https://github.com/Ranchosky/OAN.
翻译:大型航空图像当前的主流物体探测方法通常将大片图像分成补丁,然后对所有补丁感兴趣的对象进行彻底检测,不管是否存在对象。 这个范例虽然有效,但效率不高,因为探测器必须穿过所有补丁,严重妨碍推断速度。 本文展示了一个目标感应启动网络(OAN),帮助探测器关注较少的补丁,但实现更有效的推断和更准确的结果,从而能够对大片图像中的物体探测找到一个简单而有效的解决方案。 简而言之, OAN是一个光亮的全导射网络,用来判断每个补丁是否包含物体,可以很容易地纳入许多天体探测器并与它们共同培训。 我们用5个高级探测器对 OAN 进行了广泛的评估。 我们使用OAN, 所有5个探测器在3个大型空中图像数据集上获得超过30.0%的加速率,同时不断提高精确度。 关于巨大的 Gaoofenen-2 图像(29200美元\ times 27620 pixels), 我们的OAN将检测速度提高70.5 %。 此外,我们将 OAN 的探测和速度提升为4RC。