Real-Time Multi-Scale Face Detector on Embedded Devices
文献类型：期刊论文
| 作者 | Zhao, Xu1,2 ; Liang, Xiaoqing1,2; Zhao, Chaoyang1,2; Tang, Ming1,2; Wang, Jinqiao1,2
|
| 刊名 | SENSORS
 |
| 出版日期 | 2019-05-01 |
| 卷号 | 19期号:9页码:22 |
| 关键词 | face detection ARM-based devices model acceleration computer vision |
| ISSN号 | 1424-8220 |
| DOI | 10.3390/s19092158 |
| 通讯作者 | Zhao, Chaoyang(chaoyang.zhao@nlpr.ia.ac.cn) |
| 英文摘要 | Face detection is the basic step in video face analysis and has been studied for many years. However, achieving real-time performance on computation-resource-limited embedded devices still remains an open challenge. To address this problem, in this paper we propose a face detector, EagleEye, which shows a good trade-off between high accuracy and fast speed on the popular embedded device with low computation power (e.g., the Raspberry Pi 3b+). The EagleEye is designed to have low floating-point operations per second (FLOPS) as well as enough capacity, and its accuracy is further improved without adding too much FLOPS. Specifically, we design five strategies for building efficient face detectors with a good balance of accuracy and running speed. The first two strategies help to build a detector with low computation complexity and enough capacity. We use convolution factorization to change traditional convolutions into more sparse depth-wise convolutions to save computation costs and we use successive downsampling convolutions at the beginning of the face detection network. The latter three strategies significantly improve the accuracy of the light-weight detector without adding too much computation costs. We design an efficient context module to utilize context information to benefit the face detection. We also adopt information preserving activation function to increase the network capacity. Finally, we use focal loss to further improve the accuracy by handling the class imbalance problem better. Experiments show that the EagleEye outperforms the other face detectors with the same order of computation costs, on both runtime efficiency and accuracy. |
| 资助项目 | Natural Science Foundation of China[61772527] ; Natural Science Foundation of China[61806200] ; Natural Science Foundation of China[61876086] |
| WOS研究方向 | Chemistry ; Electrochemistry ; Instruments & Instrumentation |
| 语种 | 英语 |
| WOS记录号 | WOS:000469766800202 |
| 出版者 | MDPI |
| 资助机构 | Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/23713]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
| 通讯作者 | Zhao, Chaoyang |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhao, Xu,Liang, Xiaoqing,Zhao, Chaoyang,et al. Real-Time Multi-Scale Face Detector on Embedded Devices[J]. SENSORS,2019,19(9):22. |
| APA | Zhao, Xu,Liang, Xiaoqing,Zhao, Chaoyang,Tang, Ming,&Wang, Jinqiao.(2019).Real-Time Multi-Scale Face Detector on Embedded Devices.SENSORS,19(9),22. |
| MLA | Zhao, Xu,et al."Real-Time Multi-Scale Face Detector on Embedded Devices".SENSORS 19.9(2019):22. |
入库方式： OAI收割
来源：自动化研究所
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。