Unmanned Aerial Vehicle (UAV) Based Running Person Detection from a Real-Time Moving Camera
文献类型：会议论文
| 作者 | Happiness Ugochi Dike; Qingtian Wu; Yimin Zhou; Gong Liang |
| 出版日期 | 2018 |
| 会议日期 | 2018 |
| 会议地点 | Kuala Lumpur, Malaysia |
| 英文摘要 | The information captured by Unmanned Aerial Vehicles (UAVs) are highly exploited to detect a running person which is given in this paper. In this scheme, 11 fps and an adequate detection precision in outdoor surveillance background was realized, using one dispensation thread without resorting to distinct hardware like GPU. Real-time and high precision detection were made promising by two aids. First, we used a progression of preprocessing procedures to extract the regions of interest (ROI), this includes spatial domain analysis, calculating the optical flow in every two consecutive images and having a predefined threshold built on optical flow to select actual areas as ROIs. Secondly, we also used relatively minor-batch models to train our 5-layer convolutional neural networks (CNN) in order to realize an adequate detection ratio. The experiments from numerous videos shot in diverse time and locations proved that the proposed scheme can detect running person in outdoors efficiently and enhance the Realtime necessity with a very high detection ratio |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/13853]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 推荐引用方式 GB/T 7714 | Happiness Ugochi Dike,Qingtian Wu,Yimin Zhou,et al. Unmanned Aerial Vehicle (UAV) Based Running Person Detection from a Real-Time Moving Camera[C]. 见:. Kuala Lumpur, Malaysia. 2018. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。