Department of Information, Beijing University of Technology, Beijing 100124, China.
Sensors (Basel). 2021 Mar 1;21(5):1672. doi: 10.3390/s21051672.
In object detection of remote sensing images, anchor-free detectors often suffer from false boxes and sample imbalance, due to the use of single oriented features and the key point-based boxing strategy. This paper presents a simple and effective anchor-free approach-RatioNet with less parameters and higher accuracy for sensing images, which assigns all points in ground-truth boxes as positive samples to alleviate the problem of sample imbalance. In dealing with false boxes from single oriented features, global features of objects is investigated to build a novel regression to predict boxes by predicting width and height of objects and corresponding ratios of l_ratio and t_ratio, which reflect the location of objects. Besides, we introduce ratio-center to assign different weights to pixels, which successfully preserves high-quality boxes and effectively facilitates the performance. On the MS-COCO test-dev set, the proposed RatioNet achieves 49.7% AP.
在遥感图像目标检测中，由于使用单一定向特征和基于关键点的框定策略，无锚探测器经常会出现误报框和样本不平衡的问题。本文提出了一种简单而有效的无锚方法——RatioNet，该方法具有较少的参数和更高的遥感图像精度，它将所有真实框中的点都分配为正样本，以减轻样本不平衡的问题。在处理单一定向特征的误报框时，我们研究了对象的全局特征，通过预测对象的宽度和高度以及相应的 l_ratio 和 t_ratio 比值来构建新的回归来预测框，这反映了对象的位置。此外，我们引入了 ratio-center 为像素分配不同的权重，成功地保留了高质量的框，并有效地提高了性能。在 MS-COCO test-dev 数据集上，所提出的 RatioNet 实现了 49.7%的 AP。
