Oriented object detection is a practical and challenging task in remote sensing image interpretation. Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them. However, the horizontal boxes are inclined to get small Intersection-over-Unions (IoUs) with ground truths, which may have some undesirable effects, such as introducing redundant noise, mismatching with ground truths, detracting from the robustness of detectors, etc. In this paper, we propose a novel Anchor-free Oriented Proposal Generator (AOPG) that abandons horizontal box-related operations from the network architecture. AOPG first produces coarse oriented boxes by a Coarse Location Module (CLM) in an anchor-free manner and then refines them into high-quality oriented proposals. After AOPG, we apply a Fast R-CNN head to produce the final detection results. Furthermore, the shortage of large-scale datasets is also a hindrance to the development of oriented object detection. To alleviate the data insufficiency, we release a new dataset on the basis of our DIOR dataset and name it DIOR-R. Massive experiments demonstrate the effectiveness of AOPG. Particularly, without bells and whistles, we achieve the accuracy of 64.41%, 75.24% and 96.22% mAP on the DIOR-R, DOTA and HRSC2016 datasets respectively. Code and models are available at https://github.com/jbwang1997/AOPG.
翻译:定向物体探测是遥感图像判读方面的一项实际而具有挑战性的任务。如今,定向探测器大多使用横向箱作为中间介质,从中取出定向箱。然而,横向箱倾向于获得具有地面真相的小型交叉联盟(IoUs),这可能有一些不良效果,例如引入多余的噪音、与地面真相不匹配、减损探测器的稳健性等。在本文件中,我们提议建立一个新型的无锁无源建议生成器(AOPG),放弃网络结构中的横向框相关操作。AOPG首先以无锚方式用Coarse定位模块(CLM)生产粗金箱,然后将其改进为高质量的定向提议。在AOPG之后,我们用快速R-CN头来生成最后的检测结果。此外,大型数据集的短缺也阻碍了定向物体探测的开发。为了减轻数据不足,我们根据我们的DIOR数据集集和名称发布一个新的数据集 DIOR-ROB-RSDA,在SAL 75 massal 和SIGOB% 中,我们在SOLB-DG-DOLA 和SOLB-D-G-DOB-G-B-B-G-B-R-B-B-B-B-Ms AS-D-DAR-IAR-D-D-D-D-D-D-G-IAR-IAR-G-G-G-G-G-G-G-G-B-G-G-B-B-B-B-G-G-G-G-G-G-G-G-G-G-G-G-G-B-G-G-G-G-S-IAR-S-G-T-IAR-T-IAR-IAR-Q-Q-S-S-Q-S-Q-Q-Q-Q-Q-Q-Q-IL-ILs-Q-Q-ILisals AS AS AS-S-S-S-Q-S-S-Q-Q-D-Q-Q-I-I-IL-IL-IL-IL-D-Q-D-Q-D-D-D-D-D-Q-Q-D-I-