Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes. This diminishes the detectors' speed, thereby becoming the computational bottleneck in advanced oriented object detection systems. This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN, which is a general two-stage oriented detector with promising accuracy and efficiency. To be specific, in the first stage, we propose an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner. The second stage is oriented R-CNN head for refining oriented Regions of Interest (oriented RoIs) and recognizing them. Without tricks, oriented R-CNN with ResNet50 achieves state-of-the-art detection accuracy on two commonly-used datasets for oriented object detection including DOTA (75.87% mAP) and HRSC2016 (96.50% mAP), while having a speed of 15.1 FPS with the image size of 1024$\times$1024 on a single RTX 2080Ti. We hope our work could inspire rethinking the design of oriented detectors and serve as a baseline for oriented object detection. Code is available at https://github.com/jbwang1997/OBBDetection.
翻译:目前最先进的两阶段探测器通过耗时办法产生面向性的建议。 这会降低探测器的速度, 从而成为高级定向物体探测系统中的计算瓶颈。 这项工作提出了一个有效和简单的面向物体探测框架, 称为 " 定向R- CNN ", 称为 " 定向R- CNN ", 是一个一般的面向两阶段的探测器, 其准确性和效率大有希望。 具体地说, 在第一阶段, 我们提议一个面向方向的区域建议网络( 定向RPN), 以近乎免费的方式直接产生高质量的面向性建议。 第二阶段是R-CNN 头, 改进面向利益的区域( 定向RoIs), 并承认它们。 没有技巧, 面向ResNet50 的R- CNN 能够实现对两种常用的面向物体探测数据集的状态检测准确性, 包括DOTA( 75.87% mAP) 和 HRSC2016 (96. 50 mAP), 同时速度为15.1 FPSPS\times 1024美元, 1024美元, 用于单一RTX 2080T。 我们希望, 我们的工作能够重新思考用于面向式探测器/ OB/ RB 的测试/ RB 标准的设计, 。