Deep-learning object detection methods that are designed for computer vision applications tend to underperform when applied to remote sensing data. This is because contrary to computer vision, in remote sensing, training data are harder to collect and targets can be very small, occupying only a few pixels in the entire image, and exhibit arbitrary perspective transformations. Detection performance can improve by fusing data from multiple remote sensing modalities, including red, green, blue, infrared, hyperspectral, multispectral, synthetic aperture radar, and light detection and ranging, to name a few. In this article, we propose YOLOrs: a new convolutional neural network, specifically designed for real-time object detection in multimodal remote sensing imagery. YOLOrs can detect objects at multiple scales, with smaller receptive fields to account for small targets, as well as predict target orientations. In addition, YOLOrs introduces a novel mid-level fusion architecture that renders it applicable to multimodal aerial imagery. Our experimental studies compare YOLOrs with contemporary alternatives and corroborate its merits.

中文翻译：

---

YOLOrs：多模态遥感影像中的物体检测

为计算机视觉应用设计的深度学习对象检测方法在应用于遥感数据时往往表现不佳。这是因为与计算机视觉相反，在遥感中，训练数据更难收集，目标可能非常小，只占整个图像中的几个像素，并表现出任意的透视变换。通过融合来自多种遥感模式的数据，包括红、绿、蓝、红外、高光谱、多光谱、合成孔径雷达以及光探测和测距等，可以提高探测性能。在本文中，我们提出了 YOLOrs：一种新的卷积神经网络，专为多模态遥感图像中的实时目标检测而设计。YOLOrs 可以检测多个尺度的物体，用较小的感受野来解释小目标，以及预测目标方向。此外，YOLOrs 引入了一种新颖的中级融合架构，使其适用于多模态航拍图像。我们的实验研究将 YOLO 与当代替代品进行了比较，并证实了其优点。