| 散货作业区人形识别的二级分类方法 |
| |
| 引用本文： | 张志伟,宓为建,宓超,何鑫.散货作业区人形识别的二级分类方法[J].上海海事大学学报,2015,36(3):82-86. |
| |
| 作者姓名： | 张志伟 宓为建 宓超 何鑫 |
| |
| 作者单位： | 上海海事大学 物流工程学院,上海海事大学 集装箱供应链技术教育部工程研究中心,上海海事大学 物流工程学院,中国电子科技集团公司第五十研究所 |
| |
| 基金项目： | 上海市科学技术委员会部分地方院校能力建设专项计划（13510501800）；上海青年科技英才扬帆计划（15YF1404900）；上海市教育委员会科研创新项目（14ZZ140）；上海海事大学研究生创新基金（2014ycx040） |
| |
| 摘 要： | 鉴于目前散货码头运用智能视频监控系统时,由于不同方向人形的方向梯度直方图(Histogram of Oriented Gradient,HOG)特征存在较大的变化,使得用传统方法训练获得的少量特异性特征不足以支撑人形的有效分类,因此提出一种基于Ada Boost的针对不同姿势HOG特征的二级分类方法.首先将样本快速分为正(背)面人形和侧面人形,组成第一级分类;然后通过分别为两类样本训练子分类器组成第二级分类;第二级分类对人形进行识别,并对结果进行融合.以天津港干散货码头无人作业区为背景,完成一组人形识别实验.实验结果表明,相较于传统方法,该方法对正(背)面人形具有更高的识别率.二级分类方法整体上提高了人形识别的识别率.
|
| 关 键 词： | 散货码头 人形识别 方向梯度直方图（HOG） AdaBoost |
| 收稿时间： | 2/5/2015 12:00:00 AM |
| 修稿时间： | 6/2/2015 12:00:00 AM |
Two stage classification approach for human body recognition in bulk handling area |
| |
| zhangzhiwei,MI Weijian,MI Chao and HE Xin.Two stage classification approach for human body recognition in bulk handling area[J].Journal of Shanghai Maritime University,2015,36(3):82-86. |
| |
| Authors: | zhangzhiwei MI Weijian MI Chao and HE Xin |
| |
| Institution: | Logistics Engineering College, Shanghai Maritime University,Container Supply Chain Tech. Engineering Research Center, Shanghai Maritime University,Container Supply Chain Tech. Engineering Research Center, Shanghai Maritime University and The 50th Research Institute of China Electronics Technology Group Corporation |
| |
| Abstract: | At present, the intelligent video monitoring system is used in bulk terminals. However, Histogram of Oriented Gradient (HOG) features of human body in different directions show great difference, so that a small number of specific features obtained by the traditional method is insufficient to support effective classification of human body. Therefore, a kind of two stage classification method based on AdaBoost is proposed for different HOG features of different human postures. Firstly, the samples are rapidly divided into the Front & Back (F&B) human body and the side (not F&B) human body to form the first stage classification. Then, the sub classifiers are respectively trained for the two types of samples to form the second stage classification, where the human body and the non human body are recognized respectively and the results are merged. Taking the unmanned area in the bulk terminal of Tianjin Port as the background, a group of human body recognition experiments is carried out. The experimental results show that, compared with the traditional method, this method is of higher recognition rate for F&B human body. The two stage classification method improves the recognition rate of human body overall. |
| |
| Keywords: | bulk terminal human body recognition Histogram of Oriented Gradient (HOG) AdaBoost |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《上海海事大学学报》浏览原始摘要信息 |
| 点击此处可从《上海海事大学学报》下载免费的PDF全文 |
|
