Ghost-YOLO: 轻量化口罩人脸检测算法 |
| |
引用本文: | 陈继平,陈永平,谢懿,朱建清,曾焕强. Ghost-YOLO: 轻量化口罩人脸检测算法[J]. 信号处理, 2022, 38(9): 1954-1964. DOI: 10.16798/j.issn.1003-0530.2022.09.018 |
| |
作者姓名: | 陈继平 陈永平 谢懿 朱建清 曾焕强 |
| |
作者单位: | 1.华侨大学工学院,福建 泉州 362021 |
| |
基金项目: | 国家重点研发计划项目2021YFE0205400国家自然科学基金面上项目61976098福建省自然科学基金杰出青年项目2022J06023福厦泉国家自主创新示范区协同创新平台项目2021FX03 |
| |
摘 要: | 在嵌入式设备上,由于算力及存储空间的限制,当前的大型高精度目标检测模型的推理速度较低。为此,本文设计了一种轻量化目标检测模型,用于口罩人脸检测。首先,本文设计了一种高激活性鬼影(High Active Ghost,HAG)模块,以轻量的计算代价减少特征图中的冗余。其次,利用HAG实现高激活性鬼影跨段部分(High Active Ghost Cross Stage Partial,HAG-CSP)连接模块,提升了跨段部分连接网络结构的特征学习能力。再次,利用HAG-CSP对你只需看一次(You Only Look Once,YOLO)模型进行轻量化改造来得到完整的Ghost-YOLO网络,并构造出一个口罩人脸检测器。实验结果表明,本文提出方法在NVIDIA Jetson NX嵌入式设备上,在检测精度优于其他目标检测算法的前提下,对于640×640的图片,实现了24.72 ms每帧的检测速度,并且减少了模型的参数量。
|
关 键 词: | ??嵌入式设备 目标识别 鬼影模块 YOLOv5 跨阶段部分模块 |
收稿时间: | 2021-08-09 |
Ghost-YOLO: Lightweight Masked Face Detection Algorithm |
| |
Affiliation: | 1.College of Engineering, Huaqiao University, Quanzhou, Fujian 362021, China2.Xiamen Yealink Network Technology Co., Ltd, Xiamen, Fujian 361015, China |
| |
Abstract: | ? ?In embedded devices, due to the limitation of low computing power and small storage space, the inference speed of current large-scale high-precision object detection algorithms is low. For that, this paper designed a lightweight masked face detection algorithm. Firstly, a high active ghost (HAG) module was designed to reduce the redundancy in feature learning with a light computational cost. Secondly, based on HAG, a high active ghost cross stage partial (HAG-CSP) connection module was designed to improve the feature learning ability. Thirdly, the HAG-CSP was used to lightweight the you only look once (YOLO) model to raise a Ghost-YOLO model for masked face detection. Experimental results show that the speed of proposed method is 24.72 milliseconds per image for 640×640 sized images on a NVIDIA Jetson NX embedded device and reduces the number of parameters, under the condition that the proposed method had a better accuracy performance than existing object detection models. |
| |
Keywords: | |
|
| 点击此处可从《信号处理》浏览原始摘要信息 |
|
点击此处可从《信号处理》下载免费的PDF全文 |