Multi-Scale Ship Detection From SAR and Optical Imagery Via A More Accurate YOLOv3
Multi-Scale Ship Detection From SAR and Optical Imagery Via A More Accurate YOLOv3
复制标题
通过更准确的 YOLOv3 根据 SAR 和光学图像进行多尺度船舶检测
DOI：
10.1109/jstars.2021.3087555
复制
发表时间：
2021-01-01
影响因子：
5.5
通讯作者：
Liu, Sichong
中科院分区：
文献类型：
--
作者：
Hong, Zhonghua;Yang, Ting;Liu, Sichong
由于目标的尺度较小以及复杂海面的干扰，深度学习检测方法在船舶检测中的应用仍然是一个挑战。此外，现有的船舶检测方法很少验证其算法对多传感器图像的鲁棒性。因此，我们提出了一个新的改进“你只看一次”版本3（YOLOv 3）的框架，在海洋监视船舶检测，合成孔径雷达（SAR）和光学图像的基础上。首先，通过使用基于k-means++算法的线性缩放来获得用于锚框的改进的选择。这解决了反映YOLOv 3的多尺度检测的优点的困难，因为不同检测尺度之间的单个检测目标类型的锚盒具有小的差异。其次，我们通过在YOLOv 3框架中引入用于船舶检测的高斯参数，为边界框的定位添加不确定性估计。最后，由于不同分辨率的遥感图像中对象的大小和方向存在很大差异，因此在高斯-YOLO层中为每个检测尺度分配了四个锚框，而不是默认YOLOv 3设置中的三个。将该策略应用于“YOLOv 3-spp”和"YOLOv 3-tiny”，结果提高了2%-3%。与其他模型相比，改进的YOLOv 3在光学（93.56%）和SAR（95.52%）数据集上的平均精度最高。改进的YOLOv 3是强大的，即使在SAR和光学图像的混合数据集的背景下，包括来自不同卫星和不同尺度的图像。
Deep learning detection methods use in ship detection remains a challenge, owing to the small scale of the objects and interference from complex sea surfaces. In addition, existing ship detection methods rarely verify the robustness of their algorithms on multisensor images. Thus, we propose a new improvement on the “you only look once” version 3 (YOLOv3) framework for ship detection in marine surveillance, based on synthetic aperture radar (SAR) and optical imagery. First, improved choices are obtained for the anchor boxes by using linear scaling based on the k-means++ algorithm. This addresses the difficulty in reflecting the advantages of YOLOv3's multiscale detection, as the anchor boxes of a single detection target type between different detection scales have small differences. Second, we add uncertainty estimators for the positioning of the bounding boxes by introducing a Gaussian parameter for ship detection into the YOLOv3 framework. Finally, four anchor boxes are allocated to each detection scale in the Gaussian-YOLO layer instead of three as in the default YOLOv3 settings, as there are wide disparities in an object's size and direction in remote sensing images with different resolutions. Applying the proposed strategy to ``YOLOv3-spp” and ``YOLOv3-tiny,” the results are enhanced by 2%–3%. Compared with other models, the improved-YOLOv3 has the highest average precision on both the optical (93.56%) and SAR (95.52%) datasets. The improved-YOLOv3 is robust, even in the context of a mixed dataset of SAR and optical images comprising images from different satellites and with different scales.