Effective Face Detector Based on YOLOv5 and Superresolution Reconstruction.
Effective Face Detector Based on YOLOv5 and Superresolution Reconstruction.
复制标题
DOI：
10.1155/2021/7748350
复制
发表时间：
2021
影响因子：
--
通讯作者：
Zang X
中科院分区：
文献类型：
--
作者：
Xu Q;Zhu Z;Ge H;Zhang Z;Zang X
人脸检测与识别技术在安防监控系统中的应用为公共安全做出了巨大的贡献。人脸检测是许多人脸分析系统中必不可少的第一步。在复杂场景中，由于图像质量、人脸尺度、光照等因素的影响，会出现小人脸的漏检和误检，从而限制了人脸检测的准确性。针对实际场景中密集小人脸的检测问题，提出了一种两级人脸检测模型SR-YOLOv 5。该研究首先优化了YOLOv 5的主干和损失函数，旨在在平均精度（mAP）和速度方面实现更好的性能。然后，为了提高模糊场景或低分辨率情况下的人脸检测，我们在检测头上集成了图像超分辨率技术。此外，本文还讨论了一些具有代表性的基于人脸检测的深度学习算法，并详细列举了当前流行的人脸检测基准。最后，使用更广泛的人脸数据集来训练和测试SR-YOLOv 5模型。与多任务卷积神经网络（MTCNN），上下文多尺度基于区域的CNN（CMS-RCNN），发现微小的面孔（HR），单镜头尺度不变的人脸检测器（S3 FD）和TinaFace算法相比，该模型具有更高的检测精度，分别比最高的算法高出0.7%，0.6%和2.9%。SR-YOLOv 5能够有效利用人脸信息，准确检测复杂场景下的人脸难检测目标。
The application of face detection and recognition technology in security monitoring systems has made a huge contribution to public security. Face detection is an essential first step in many face analysis systems. In complex scenes, the accuracy of face detection would be limited because of the missing and false detection of small faces, due to image quality, face scale, light, and other factors. In this paper, a two-level face detection model called SR-YOLOv5 is proposed to address some problems of dense small faces in actual scenarios. The research first optimized the backbone and loss function of YOLOv5, which is aimed at achieving better performance in terms of mean average precision (mAP) and speed. Then, to improve face detection in blurred scenes or low-resolution situations, we integrated image superresolution technology on the detection head. In addition, some representative deep-learning algorithm based on face detection is discussed by grouping them into a few major categories, and the popular face detection benchmarks are enumerated in detail. Finally, the wider face dataset is used to train and test the SR-YOLOv5 model. Compared with multitask convolutional neural network (MTCNN), Contextual Multi-Scale Region-based CNN (CMS-RCNN), Finding Tiny Faces (HR), Single Shot Scale-invariant Face Detector (S3FD), and TinaFace algorithms, it is verified that the proposed model has higher detection precision, which is 0.7%, 0.6%, and 2.9% higher than the top one. SR-YOLOv5 can effectively use face information to accurately detect hard-to-detect face targets in complex scenes.
登录
查看更多内容
影响因子：
8.7
作者：
Tang, Zhenhao;Zhao, Gengnan;Ouyang, Tinghui
通讯作者：
Ouyang, Tinghui
DOI：
10.1109/tpami.2015.2389824
发表时间：
2015-09-01
影响因子：
23.6
作者：
He, Kaiming;Zhang, Xiangyu;Sun, Jian
通讯作者：
Sun, Jian
DOI：
10.1109/tpami.2017.2700390
发表时间：
2018-04-01
影响因子：
23.6
作者：
Ding, Changxing;Tao, Dacheng
通讯作者：
Tao, Dacheng
影响因子：
12.9
作者：
Huang, Chenxi;Zong, Yongshuo;Mukherjee, Mithun
通讯作者：
Mukherjee, Mithun
影响因子：
7.8
作者：
Elfwing, Stefan;Uchibe, Eiji;Doya, Kenji
通讯作者：
Doya, Kenji