论文标题
PS-RCNN：通过主要对象抑制在人群中检测次要人类实例
PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression
论文作者
论文摘要
在高度拥挤的场景中检测人体是一个具有挑战性的问题。导致这样一个问题的两个主要原因：1）。严重阻塞实例的弱视觉提示几乎无法提供足够的信息来准确检测； 2）。严重遮挡的实例更容易被非最大抑制（NMS）抑制。为了解决这两个问题，我们介绍了称为PS-RCNN的两阶段探测器的变体。 PS-RCNN首先通过R-CNN模块（称为P-RCNN）检测到略微/无遮挡的对象，然后通过人形掩码抑制检测到的实例，以便闭塞实例的特征可以脱颖而出。之后，PS-RCNN利用了另一个R-CNN模块，专门针对严重的人类检测（称为S-RCNN）来检测P-RCNN剩下的遗漏对象。最终结果是来自这两个R-CNN的输出的合奏。此外，我们引入了高分辨率的ROI Align（HRRA）模块，以保留尽可能多的被遮挡人类可见部分的精细颗粒特征。与基线相比，我们的PS-RCNN显着提高了召回率和AP分别提高4.49％和2.92％。 PS-RCNN也实现了类似的环境改善。
Detecting human bodies in highly crowded scenes is a challenging problem. Two main reasons result in such a problem: 1). weak visual cues of heavily occluded instances can hardly provide sufficient information for accurate detection; 2). heavily occluded instances are easier to be suppressed by Non-Maximum-Suppression (NMS). To address these two issues, we introduce a variant of two-stage detectors called PS-RCNN. PS-RCNN first detects slightly/none occluded objects by an R-CNN module (referred as P-RCNN), and then suppress the detected instances by human-shaped masks so that the features of heavily occluded instances can stand out. After that, PS-RCNN utilizes another R-CNN module specialized in heavily occluded human detection (referred as S-RCNN) to detect the rest missed objects by P-RCNN. Final results are the ensemble of the outputs from these two R-CNNs. Moreover, we introduce a High Resolution RoI Align (HRRA) module to retain as much of fine-grained features of visible parts of the heavily occluded humans as possible. Our PS-RCNN significantly improves recall and AP by 4.49% and 2.92% respectively on CrowdHuman, compared to the baseline. Similar improvements on Widerperson are also achieved by the PS-RCNN.
