arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.07017cs.CV
收藏

检测器中检测器:人体部位的多层次分析

Detector-in-Detector: Multi-Level Analysis for Human-Parts

Beihang University(北京航空航天大学);Beijing University of Posts and Telecommunications(北京邮电大学)

Xiaojie Li, Lu Yang, Qing Song, Fuqiang Zhou

摘要:

近年来,随着深度卷积神经网络(CNN)的发展,基于视觉的人、手或面部检测方法取得了令人难以置信的成功。在本文中,我们考虑到身体和身体部位之间的内在相关性,并提出了一个新的框架,以提高检测性能的多级对象。特别是,我们采用了一个基于区域的目标检测结构,两个精心设计的检测器,分别关注人体和身体部位在一个由粗到细的方式,我们称之为检测器中检测器网络(DID-Net)。第一个检测器被设计用于检测人体、手部和面部。第二检测器基于第一检测器的身体检测结果,主要关注每个身体内部的小手和脸的检测。该框架通过优化多任务损失以端到端的方式进行训练。由于缺乏人体、面部和手部检测数据集,我们收集并标记了一个名为Human-Parts的新的大型数据集,其中包含14,962张图像和106,879条注释。实验表明,我们的方法可以取得良好的性能,人体部位。

英文摘要:

Vision-based person, hand or face detection approaches have achieved incredible success in recent years with the development of deep convolutional neural network (CNN). In this paper, we take the inherent correlation between the body and body parts into account and propose a new framework to boost up the detection performance of the multi-level objects. In particular, we adopt a region-based object detection structure with two carefully designed detectors to separately pay attention to the human body and body parts in a coarse-to-fine manner, which we call Detector-in-Detector network (DID-Net). The first detector is designed to detect human body, hand, and face. The second detector, based on the body detection results of the first detector, mainly focus on the detection of small hand and face inside each body. The framework is trained in an end-to-end way by optimizing a multi-task loss. Due to the lack of human body, face and hand detection dataset, we have collected and labeled a new large dataset named Human-Parts with 14,962 images and 106,879 annotations. Experiments show that our method can achieve excellent performance on Human-Parts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑