基于多算法融合的跌倒行为识别

doi:10.3969/j.issn.1000-1158.2022.01.17

摘要
图/表
参考文献(19)
相关文章 (15)

全文: PDF (4472 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要提出一种多算法融合的跌倒行为识别算法。首先,针对人体目标的特征对YOLOv3 tiny检测算法进行改进,有效框定人体动态目标区域,提取出目标前景;在此基础上利用AlphaPose姿态识别框架识别出人体骨骼关键点,得到人体主要关节图;最后以人体关节图坐标信息为输入,通过时空图卷积神经网络对跌倒等动作进行检测识别,满足对不同场景跌倒的有效检测。实验结果表明:融合算法改善了不同场景下跌倒行为的检测效果,检测的准确率可达到97.4%,并有效降低了误检率。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	程淑红
	谢文锐
	张典范
	徐南

关键词 ：计量学, 跌倒行为识别, YOLOv3 tiny检测算法, 姿态识别, 时空图卷积

Abstract：A fall behavior recognition algorithm based on multi algorithm fusion is proposed. Firstly, Yolov3 tiny detection algorithm is improved to effectively frame the human anchor and extract the target prospect according to the characteristics of human; then alphapose gesture recognition framework is used to identify the key points of human skeleton, and the main joint diagram of human body is obtained; Finally, taking the coordinate information of human joint diagram as input, the spatiotemporal graph convolution neural network is used to detect and identify falls and other actions, which can effectively detect falls in different scenes. The experimental results show that the fusion algorithm can improve the detection effect of fall behavior in different scenes, the detection accuracy can reach 97.4%, and effectively reduce the false detection rate.

Key words： metrology fall action recognition YOLOv3 tiny detection algorithm gesture recognition spatiotemporal graph convolution

收稿日期: 2020-11-24 发布日期: 2022-01-06

PACS:	TB973
	TB96

基金资助:国家自然科学基金(61601400);河北省重点研发计划项目(20371801D)

作者简介: 程淑红1978-,女,河北秦皇岛人,燕山大学教授,博士,主要从事计算机视觉、水质检测方面的研究。Email: shhcheng@ysu.edu.cn

引用本文:

程淑红, 谢文锐, 张典范, 徐南. 基于多算法融合的跌倒行为识别[J]. 计量学报, 2022, 43(1): 107-113.
CHENG Shu-hong, XIE Wen-rui, ZHANG Dian-fan, XU Nan. Fall Action Recognition Based on Computer Vision. Acta Metrologica Sinica, 2022, 43(1): 107-113.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.01.17 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I1/107

［1］王雅磊, 刘腊梅, 张振香. 老年人跌倒评估工具的研究进展［J］. 中国老年学杂志, 2019, 39(9): 2294-2298.
Wang Y L, Liu L M, Zhang Z X. Research progress on fall assessment tools for the elderly［J］. Chinese Journal of Gerontology, 2019, 39(9): 2294-2298.
［2］张烨, 周晓晶, 杨晓童. 基于单目视频的人体运动测量系统［J］. 计量学报, 2019, 40(3): 367-372.
Zhang Y, Zhou X J, Yang X T. Human motion measurement system based on Monocular Video［J］. Acta Metrologica Sinica, 2019, 40 (3): 367-372.
［3］ Alarifi A, Alwadain A. Killer heuristic optimized convolution neural network-based fall detection with wearable IoT sensor devices［J］. Measurement, 2021, 167.
［4］ Jang N, Du X. Design of wearable fall detection system based on inertial sensor［J］. Electronics World, 2016(5): 147-149.
［5］ Min W, Cui H, Rao H, et al. Detection of human falls on furniture using scene analysis based on deep learning and activity characteristics［J］. IEEE Access, 2018, 6: 9324-9335.
［6］ Wang S K, Chen L, Zhou Z X, et al. Human fall detection in surveillance video based on PCANet［J］. Multimedia Tools and Applications, 2016, 75(19):11603-11613..
［7］蔡文郁, 郑雪晨, 郭嘉豪, 等. 基于SVM-MultiCNN模型的视觉感知跌倒检测算法［J］. 杭州电子科技大学学报(自然科学版), 2020, 40(5): 59-66.
Cai W Y, Zheng X C, Guo J H, et al. Visual perception fall detection algorithm based on SVM-MultiCNN model［J］. Journal of Hangzhou University of Electronic Science and Technology (Natural Science Edition), 2020, 40(5): 59-66.
［8］ Liu W, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector［C］//European Conference on Computer Vision, Amsterdam Netherlands, 2016, 2011:21-37.
［9］ Ji S, Xu W, Yang M, et al. 3D convolutional neural networks for human action recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(1): 221-231.
［10］ Zhi Y, Hui H. A Fall Detection Method Based on Two-Stream Convolutional Neural Network［J］. Journal of Henan Normal University(Natural Science Edition), 2017, 45(3): 96-101.
［11］程淑红,程彦龙. 融合批量再标准化和YOLOv3的手势识别研究［J］. 计量学报, 2021, 42 (1): 29-34.
Cheng S H, Cheng Y L. Hand Gesture Recognition Algorithm Combined with Batch Renormalization and YOLOv3［J］. Acta Metrologica Sinic, 2021, 42 (1): 29-34.
［12］谭芳,穆平安,马忠雪. 基于YOLOv3检测和特征点匹配的多目标跟踪算法［J］. 计量学报, 2021, 42 (2): 157-162.
Tan F, Mu P A, Ma Z X. Multi-target Tracking Algorithm Based on YOLOv3 Detection and Feature Point Matching［J］. Acta Metrologica Sinica, 2021, 42 (2): 157-162.
［13］ Redmon J, Farhadi A. Yolov3: An incremental improvement［C］// Computer Vision and Pattern Recognition. Berlin/Heidelberg, Germany, 2018,1804-2767.
［14］ Hu J, Shen L, Samuel A, et al. Squeeze-and-Excitation Networks. ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8):2011-2023..
［15］程淑红, 张仕军, 赵考鹏. 基于卷积神经网络的生物式水质监测方法［J］. 计量学报, 2019, 40(4): 721-727.
Cheng S H, Zhang S J, Zhao K P. Biological water quality monitoring method based on convolutional neural network［J］. Acta Metrologica Sinica, 2019, 40(4): 721-727.
［16］赵彦涛, 何永强, 贾利颖, 等. 基于时间序列单维卷积神经网络的水泥熟料游离钙软测量方法［J］. 计量学报, 2020, 41(9): 1152-1162.
Zhao Y T, He Y Q, Jia L Y, et al. Soft Measurement Method for Cement Clinker fCaO Based on Time Series Single-dimensional Convolutional Neural Network［J］. Acta Metrologica Sinica, 2020, 41(9): 1152-1162.
［17］ Fang H S, Xie S, Tai Y W, et al. RMPE: Regional Multi-person Pose Estimation［C］//IEEE International Conference on Computer Vision (ICCV). Venice, Italy, 2017.
［18］ Gkioxari G, Hariharan B, Girshick R, et al. Using k-Poselets for Detecting People and Localizing Their Keypoints［C］// Computer Vision & Pattern Recognition. IEEE, Columbus,USA, 2014.
［19］ Yan S, Xiong Y, Lin D. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition［C］// The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). Hilton New Orleans Riverside, New Orleans, Louisiana, USA, 2018.