Recovering human body configurations: combining segmentation and recognition
Recovering human body configurations: combining segmentation and recognition
复制标题
DOI：
10.1109/cvpr.2004.204
复制
发表时间：
2004-06
期刊：
影响因子：
--
通讯作者：
Greg Mori;Xiaofeng Ren;Alexei A. Efros;Jitendra Malik
中科院分区：
文献类型：
--
作者：
Greg Mori;Xiaofeng Ren;Alexei A. Efros;Jitendra Malik
这项工作的目标是检测人物图像，并定位他的关节和四肢以及它们相关的像素掩码。在这项工作中，我们试图在一般情况下解决这个问题。我们使用的数据集是棒球运动员的体育新闻照片的集合，这些照片在姿势和服装上都有很大的变化。我们采取的方法是使用分割来引导我们的识别算法识别图像的显著部分。我们使用这种分割方法来构建肢体和躯干检测器，其输出被组装成人体图形。除了入围的全身配置外，我们还介绍了躯干定位的定量结果。
The goal of this work is to detect a human figure image and localize his joints and limbs along with their associated pixel masks. In this work we attempt to tackle this problem in a general setting. The dataset we use is a collection of sports news photographs of baseball players, varying dramatically in pose and clothing. The approach that we take is to use segmentation to guide our recognition algorithm to salient bits of the image. We use this segmentation approach to build limb and torso detectors, the outputs of which are assembled into human figures. We present quantitative results on torso localization, in addition to shortlisted full body configurations.