多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild

Towards Real World Human Parsing: Multiple-Human Parsing in the Wild
https://arxiv.org/abs/1705.07206

数据库没给出来啊!

本文针对当前 human parsing 数据库基本都是单人标记,而图像实际情况经常含有多人,这里我们提出了一个 Multiple-Human Parsing (MHP) 数据库,一般2-16人每张图像。接着我们提出了一个 Multiple-Human Parser (MH-Parser) 算法,在单人解析过程中同时考虑 global context and local cues,得到不错的效果。

先看数据库:
多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第1张图片
这里写图片描述

各个数据库规模:
多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第2张图片

Dataset statistics
多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第3张图片

MH-Parser:
多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第4张图片

MH-Parser 主要包含五个模块:
1)Representation learner: 是一个CNN特征器,它提取的特征由后面几个模块共享,这里使用全卷积网络,以保持 spatial 信息

2)Global parser : 获取整幅图像的全局信息,生成 a semantic parsing map of the whole image

3) Candidate nominator:包括三个子模块 Region Proposal Network (RPN), a bounding box classifier
and a bounding box regression,类似于 Faster RCNN,将每个人检测出来,得到矩形框

4)Local parser: 针对每个含有人的矩形框,进行 semantic labels 语义标记

5)Global-local aggregator :同时将 local parser and the global parser 网络中隐含的信息输入,用于单人矩形框的 semantic parsing predictions

4.2 Detect-and-parse baseline

检测阶段和解析阶段是分离的:
In the detection stage, we use the representation learner and the candidate nominator as the detection
model.

In the parsing stage, we use the representation learner and the local prediction as the
the parsing model.

多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第5张图片

多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第6张图片

多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第7张图片

多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第8张图片
多人部件解析--Towards Real World Human Parsing: Multiple-Human Parsing in the Wild_第9张图片

你可能感兴趣的:(人)