基于改进MTCNN算法的低功耗边缘人脸检测跟踪系统
2021年电子技术应用第5期
祁星晨，卓旭升
武汉工程大学 电气信息学院，湖北 武汉430205
摘要： 边缘设备的快速发展和深度学习的落地应用越来越多，两者结合的趋势越发明显。而针对低功耗边缘设备AI应用的潜力还未完全开发出来，大量设备隐藏着大量计算能力，释放其潜力所带来的社会效益和经济效益是非常明显的。因此，以目标检测任务中较为常见的人脸检测为例，将MTCNN人脸检测算法改进并移植到资源极其紧张的低功耗嵌入式平台，在一定环境条件下，最终成功地检测到人脸，并绘制出人脸候选框，结合舵机云台具备了一定的人脸跟踪能力。
中图分类号： TP391
文献标识码： A
DOI：10.16157/j.issn.0258-7998.201100
中文引用格式： 祁星晨，卓旭升. 基于改进MTCNN算法的低功耗边缘人脸检测跟踪系统[J].电子技术应用，2021，47(5)：40-44.
英文引用格式： Qi Xingchen，Zhuo Xusheng. Low-power edge AI face detection and tracking system based on improved MTCNN algorithm[J]. Application of Electronic Technique，2021，47(5)：40-44.
Low-power edge AI face detection and tracking system based on improved MTCNN algorithm
Qi Xingchen，Zhuo Xusheng
School of Information and Electrical Engineering，Wuhan Institute of Technology，Wuhan 430205，China
Abstract： The rapid development of edge devices and the application of deep learning are increasing, the trend of combining the two is becoming more and more obvious. The potential of AI applications for low-power edge devices has not yet been fully developed. A large number of devices hide a lot of computing power. The social and economic benefits brought by the release of its potential are very obvious. Therefore, taking the more common face detection in objective detection tasks as an example, the MTCNN face detection algorithm is improved and transplanted to a low-power embedded platform with extremely limited resources. Under certain environmental conditions, the face is finally successfully detected,and the face candidate boundingbox is drawn, it has face tracking function combined with the servo.
Key words : low-power edge devices；object detection；face detection and tracking；cascaded convolutional neural network
0 引言
近年来，边缘设备等爆炸式增长，百亿数量级的边缘设备接入互联网。传统的AI计算架构主要是依靠云计算，虽然云计算能够提供足够的计算能力和可靠的计算结果，但其不断地消耗大量电力，且边缘设备也需要消耗能量收集数据并传输到云端，传输过程存在着延迟。而边缘设备与AI的结合能够降低能源的消耗以及降低延迟，使得原本在云端完成的任务可在边缘设备完成，降低了云端的负担，发掘了边缘设备的计算能力[1-3]。
本文详细内容请下载:http://www.chinaaet.com/resource/share/2000003519
作者信息:
祁星晨，卓旭升
(武汉工程大学 电气信息学院，湖北 武汉430205)
