当前位置: X-MOL 学术IEEE Trans. Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Hier R-CNN: Instance-Level Human Parts Detection and A New Benchmark
IEEE Transactions on Image Processing ( IF 10.6 ) Pub Date : 2020-10-19 , DOI: 10.1109/tip.2020.3029901
Lu Yang , Qing Song , Zhihui Wang , Mengjie Hu , Chun Liu

Detecting human parts at instance-level is an essential prerequisite for the analysis of human keypoints, actions, and attributes. Nonetheless, there is a lack of a large-scale, rich-annotated dataset for human parts detection. We fill in the gap by proposing COCO Human Parts. The proposed dataset is based on the COCO 2017, which is the first instance-level human parts dataset, and contains images of complex scenes and high diversity. For reflecting the diversity of human body in natural scenes, we annotate human parts with (a) location in terms of a bounding-box, (b) various type including face, head, hand, and foot, (c) subordinate relationship between person and human parts, (d) fine-grained classification into right-hand/left-hand and left-foot/right-foot. A lot of higher-level applications and studies can be founded upon COCO Human Parts, such as gesture recognition, face/hand keypoint detection, visual actions, human-object interactions, and virtual reality. There are a total of 268,030 person instances from the 66,808 images, and 2.83 parts per person instance. We provide a statistical analysis of the accuracy of our annotations. In addition, we propose a strong baseline for detecting human parts at instance-level over this dataset in an end-to-end manner, call Hier(archy) R-CNN. It is a simple but effective extension of Mask R-CNN, which can detect human parts of each person instance and predict the subordinate relationship between them. Codes and dataset are publicly available ( https://github.com/soeaver/Hier-R-CNN ).

中文翻译:

R-CNN高层:实例级人体部位检测和新基准

在实例级别检测人体部位是分析人体关键点,动作和属性的必要前提。但是,缺少用于人体部位检测的大规模,注释丰富的数据集。我们通过提出可可人体零件来填补这一空白。拟议的数据集基于COCO 2017,这是第一个实例级人体器官数据集,其中包含复杂场景和高度多样性的图像。为了反映自然场景中人体的多样性,我们用(a)边界框来标注人体部位,(b)包括脸,头,手和脚的各种类型,(c)人与人之间的从属关系。 (d)细分类为右手/左手和左脚/右脚。可在COCO Human Parts的基础上进行许多更高级的应用和研究,例如手势识别,面部/手关键点检测,视觉动作,人与对象的互动以及虚拟现实。从66,808张图像中总共有268,030个人实例,每个人实例有2.83个零件。我们提供注释准确性的统计分析。此外,我们提出了一个强大的基线,以端到端的方式在此数据集的实例级别检测人体部位,称为Hier(archy)R-CNN。它是Mask R-CNN的简单但有效的扩展,可以检测每个人实例的人体部位并预测它们之间的从属关系。代码和数据集是公开可用的(每人实例83个零件。我们提供注释准确性的统计分析。另外,我们提出了一个强基准,以端到端的方式在此数据集的实例级别检测人体部位,称为Hier(archy)R-CNN。它是Mask R-CNN的简单但有效的扩展,可以检测每个人实例的人体部位并预测它们之间的从属关系。代码和数据集是公开可用的(每人实例83个零件。我们提供注释准确性的统计分析。此外,我们提出了一个强大的基线,以端到端的方式在此数据集的实例级别检测人体部位,称为Hier(archy)R-CNN。它是Mask R-CNN的简单但有效的扩展,可以检测每个人实例的人体部位并预测它们之间的从属关系。代码和数据集是公开可用的(它可以检测每个人实例的人体部位并预测它们之间的从属关系。代码和数据集是公开可用的(它可以检测每个人实例的人体部位并预测它们之间的从属关系。代码和数据集是公开可用的( https://github.com/soeaver/Hier-R-CNN )。
更新日期:2020-11-21
down
wechat
bug