Vision-based Detection of Humans on the Ground from Actual Aerial Images by Informed Filters using Only Color Features

被引：0

作者：

Oki, Takuro ^{[1
]}

Aoki, Risako ^{[1
]}

Kobayashi, Shingo ^{[1
]}

Miyamoto, Ryusuke ^{[2
]}

Yomo, Hiroyuki ^{[3
]}

Hara, Shinsuke ^{[4
]}

机构：

[1] Grad Sch Sci & Technol, Dept Comp Sci, Tokyo, Japan

[2] Meiji Univ, Dept Comp Sci, Sch Sci & Technol, Tama Ku, 1-1-1 Higashimita, Kawasaki, Kanagawa, Japan

[3] Kansai Univ, Fac Engn Sci, Dept Elect & Elect Engn, 3-3-35 Yamate Cho, Suita, Osaka, Japan

[4] Osaka City Univ, Grad Sch Engn, Sumiyoshi Ku, 3-3-138 Sugimoto, Osaka, Japan

来源：

ICSPORTS: PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON SPORT SCIENCES RESEARCH AND TECHNOLOGY SUPPORT | 2019年

关键词：

Player Detection; Actual Aerial Images; Informed-filters;

D O I：

10.5220/0008166000840089

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper, we construct a novel sensor network stem that can measure real-time vital signs of the human body during exercise even at high speeds and in crowded regions. The sensor network estimates locations of sensor nodes using image processing to extract locations of humans wearing sensors. This paper evaluates the accuracy of human detection by informed-filters using only color features for actual aerial images. To carry out the evaluation, a novel dataset composed of actual images captured using a camera mounted on a drone was created. Experimental results show that significant accuracy can be achieved by the detector. In addition, the number of weak classifiers in a strong classifier can be reduced to 125 without significant degradation of the detection accuracy.

引用

页码：84 / 89

页数：6