论文标题
AMRNET：航空图像中的芯片扩大对象检测
AMRNet: Chips Augmentation in Aerial Images Object Detection
论文作者
论文摘要
由于以下原因，航空图像中的对象检测是一项具有挑战性的任务：（1）对象相对于图像而言较小且密集； （2）物体量表在较大范围内变化； （3）不同类中的对象数量不平衡。许多当前的方法采用裁剪的想法：将高分辨率图像分为串行区域（芯片）并在其上检测到。但是，在用芯片培训网络的过程中存在一些问题，例如量表变化，对象稀疏性和阶级失衡。在这项工作中，引入了三种增强方法来缓解这些问题。具体来说，我们提出了一个秤自适应模块，该模块会动态调整芯片大小以平衡对象尺度，从而缩小训练的尺度变化。另外，我们将马赛克介绍给增强数据集，从而缓解对象差异问题。为了平衡catgory，我们将面膜重新采样到带有全景分割的芯片中。我们的模型在Visdrone和UAVDT的两个流行的空中图像数据集上实现了最新的完整性。值得注意的是，可以将三种方法独立地应用于检测器，而无需牺牲推理效率，提高了性能稳定。
Object detection in aerial images is a challenging task due to the following reasons: (1) objects are small and dense relative to images; (2) the object scale varies in a wide range; (3) the number of object in different classes is imbalanced. Many current methods adopt cropping idea: splitting high resolution images into serials subregions (chips) and detecting on them. However, some problems such as scale variation, object sparsity, and class imbalance exist in the process of training network with chips. In this work, three augmentation methods are introduced to relieve these problems. Specifically, we propose a scale adaptive module, which dynamically adjusts chip size to balance object scale, narrowing scale variation in training. In addtion, we introduce mosaic to augment datasets, relieving object sparity problem. To balance catgory, we present mask resampling to paste object in chips with panoramic segmentation. Our model achieves state-of-the-art perfomance on two popular aerial image datasets of VisDrone and UAVDT. Remarkably, three methods can be independently applied to detectiors, increasing performance steady without the sacrifice of inference efficiency.
