杜 闯,何赟泽,邓海平,常 珊,王耀南.基于百度飞桨的面向黑暗环境人员行为检测与身份识别[J].电子测量与仪器学报,2023,37(8):21-29 |
基于百度飞桨的面向黑暗环境人员行为检测与身份识别 |
Human behavior detection and identification in dark environment based on Baidu Paddle |
|
DOI: |
中文关键词: 黑暗环境 红外热成像 行为检测 跨模态人脸识别 |
英文关键词:dark environment infrared thermal imaging behavior detection cross-modal face recognition |
基金项目:2022 年 CCF-百度松果基金( CCF-BAIDU OF2022010)、湖南省重点研发计划( 2022GK2012)、湖南省自然科学基金重大项目
(2021JC0004)资助 |
|
|
摘要点击次数: 610 |
全文下载次数: 603 |
中文摘要: |
针对传统可见光在黑暗环境中难以实现人员行为检测与身份识别的问题,本文结合红外热成像技术基于百度飞桨深度
学习框架研究了一种面向黑暗环境的人员行为检测与身份识别算法。 首先经过实地采集,自主构建红外热成像人员行为数据
集总计 10 900 张 9 种行为类别以及双光人脸数据集总计 3 000 张 30 位人员。 针对行为检测方面,基于轻量化网络 PP-LCNet
改进 YOLOv5 骨干网络进行人员行为检测,大幅度减少模型参数并提高检测精度与推理速度。 针对人脸识别方面,引入
CycleGAN 算法改进 InsightFace 实现将红外人脸转化为可见光人脸进行身份识别,提高在黑暗环境下人脸识别准确率。 最后实
现红外人员行为检测网络与人脸识别网络的级联工作,在黑暗环境下可以实时行为检测与身份识别,具有很好的应用效果。 实
验结果表明,基于 PPLCNet 轻量化改进的 YOLOv5 相对于原网络模型参数减少 56. 4%,平均精度 mAP 由 89. 1%提高至 94. 7%,
推理速度由 68 提高至 101 fps;基于 CycleGAN 算法改进 InsightFace 相对于原网络黑暗环境下识别准确率由 84%提高至 99%。 |
英文摘要: |
Aiming at the problem that traditional visible light is difficult to realize personnel behavior detection and identity recognition in
dark environment, this paper combined with infrared thermal imaging technology to study an algorithm for personnel behavior detection
and identity recognition in dark environment based on Baidu Paddle deep learning framework. First, after field collection, the behavioral
dataset of infrared thermal imaging personnel totaled 10 900 pieces of 9 behavior categories and the double-light face dataset totaled 3 000
pieces of 30 personnel. In terms of behavior detection, the lightweight network PP-LCNet is used to improve the YOLOv5 backbone
network for personnel behavior detection, reducing model parameters greatly and improving detection accuracy and reasoning speed. In
terms of face recognition, CycleGAN algorithm is introduced to improve InsightFace to transform infrared faces into visible faces for
identity recognition and improve face recognition accuracy in dark environments. Finally, the cascade of infrared human behavior
detection network and face recognition network is realized, and real-time behavior detection and identity recognition can be achieved in
the dark environment, which has a good application effect. The experimental results show that compared with the original network model,
the parameters of YOLOv5 based on PPLCNet are reduced by 56. 4%, the average precision mAP is increased from 89. 1% to 94. 7%,
and the reasoning speed is increased from 68 to 101 fps. Based on CycleGAN algorithm, the recognition accuracy of InsightFace is
improved from 84% to 99% in the dark environment of the original network. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|