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。
中圖分類號： TP391
文獻標識碼： A
DOI：10.16157/j.issn.0258-7998.201100
中文引用格式： 祁星晨，卓旭升. 基于改進MTCNN算法的低功耗邊緣人臉檢測跟蹤系統[J].電子技術應用，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.
文獻標識碼： A
DOI：10.16157/j.issn.0258-7998.201100
中文引用格式： 祁星晨，卓旭升. 基于改進MTCNN算法的低功耗邊緣人臉檢測跟蹤系統[J].電子技術應用，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
近年來，邊緣設備等爆炸式增長，百億數量級的邊緣設備接入互聯網。傳統的AI計算架構主要是依靠云計算，雖然云計算能夠提供足夠的計算能力和可靠的計算結果，但其不斷地消耗大量電力，且邊緣設備也需要消耗能量收集數據并傳輸到云端，傳輸過程存在著延遲。而邊緣設備與AI的結合能夠降低能源的消耗以及降低延遲，使得原本在云端完成的任務可在邊緣設備完成，降低了云端的負擔，發掘了邊緣設備的計算能力[1-3]。
本文詳細內容請下載:http://www.tom3567.com/resource/share/2000003519
作者信息:
祁星晨，卓旭升
(武漢工程大學 電氣信息學院，湖北 武漢430205)
此內容為AET網站原創，未經授權禁止轉載。