计算机工程与应用2019，Vol.55Issue(12)：162-168,7.DOI:10.3778/j.issn.1002-8331.1805-0441
基于深度学习的实时场景小脸检测方法
Tiny Face Detection Based on Deep Learning Inreal-Time Scenes
叶锋 1赵兴文 1宫恩来 1杭丽君1
作者信息
- 1. 杭州电子科技大学 自动化学院,杭州 310018
- 折叠
摘要
Abstract
Tiny face detection in real-time scenes has a low detection rate and poor regression accuracy. This paper fur-ther integrates the lower-level feature maps for multi-scale prediction. According to the characteristics of face in real-time scene detection, predicted boxes of different scales are generated to better adapt to human face shape. In the prediction stage, a soft and hard nms algorithm based on Intersection of Union(IOU)discrimination is proposed to suppress the redun-dant prediction boxes. Two thresholds are set to divide the prediction frame generated by the network into three segments of low, medium and high, and different segments of the prediction boxes are treated differently to achieve accurate sup-press. The optimal architecture of the paper can obtain 45 frame per second in real-time video detection and camera detec-tion under two NVIDIA GTX 1080 graphics cards, and achieves an average accuracy of 82.6% on the Wider Face overall validation set.关键词
深度学习/小脸检测/实时检测/计算机视觉Key words
deep learning/ tiny face detection/ real-time detection/ computer vision分类
信息技术与安全科学引用本文复制引用
叶锋,赵兴文,宫恩来,杭丽君..基于深度学习的实时场景小脸检测方法[J].计算机工程与应用,2019,55(12):162-168,7.
