Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (2): 529-535.DOI: 10.11772/j.issn.1001-9081.2022010114
• Multimedia computing and computer simulation • Previous Articles
Ping WANG1,2(), Nan CHEN1, Lei LU1,2
Received:
2022-01-28
Revised:
2022-04-26
Accepted:
2022-04-27
Online:
2022-05-16
Published:
2023-02-10
Contact:
Ping WANG
About author:
CHEN Nan, born in 1997, M. S. candidate. Her research interests include deep learning, object detection and recognition.通讯作者:
王萍
作者简介:
陈楠(1997—),女,陕西榆林人,硕士研究生,主要研究方向:深度学习、目标检测与识别CLC Number:
Ping WANG, Nan CHEN, Lei LU. Fall detection algorithm based on scene prior and attention guidance[J]. Journal of Computer Applications, 2023, 43(2): 529-535.
王萍, 陈楠, 鲁磊. 基于场景先验及注意力引导的跌倒检测算法[J]. 《计算机应用》唯一官方网站, 2023, 43(2): 529-535.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022010114
数据集 | 跌倒样本数 | 非跌倒样本数 |
---|---|---|
训练集 | 1 001 | 4 004 |
测试集 | 777 | 3 108 |
Tab. 1 Distribution of Elevator Fall Detection dataset
数据集 | 跌倒样本数 | 非跌倒样本数 |
---|---|---|
训练集 | 1 001 | 4 004 |
测试集 | 777 | 3 108 |
算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
A | 83.66 | 18.66 | 99.90 |
B | 94.20 | 76.44 | 98.64 |
C | 95.36 | 89.31 | 96.87 |
Tab. 2 Module performance comparison on Elevator Fall Detection dataset
算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
A | 83.66 | 18.66 | 99.90 |
B | 94.20 | 76.44 | 98.64 |
C | 95.36 | 89.31 | 96.87 |
卷积阶段序号 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
2 | 90.68 | 78.12 | 93.82 |
3 | 89.93 | 50.45 | 99.80 |
4 | 94.64 | 85.45 | 96.94 |
5 | 95.36 | 89.31 | 96.87 |
Tab. 3 Comparison of results of scene prior fusion at different convolution stages
卷积阶段序号 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
2 | 90.68 | 78.12 | 93.82 |
3 | 89.93 | 50.45 | 99.80 |
4 | 94.64 | 85.45 | 96.94 |
5 | 95.36 | 89.31 | 96.87 |
注意力算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
ResNet18(baseline) | 83.66 | 18.66 | 99.90 |
baseline+CBAM | 88.08 | 42.72 | 99.42 |
baseline+SAM | 91.71 | 59.20 | 99.83 |
baseline+SENet | 92.15 | 62.67 | 99.51 |
baseline+场景先验注意力 | 94.20 | 76.44 | 98.64 |
Tab. 4 Performance comparison of different attention algorithms
注意力算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
ResNet18(baseline) | 83.66 | 18.66 | 99.90 |
baseline+CBAM | 88.08 | 42.72 | 99.42 |
baseline+SAM | 91.71 | 59.20 | 99.83 |
baseline+SENet | 92.15 | 62.67 | 99.51 |
baseline+场景先验注意力 | 94.20 | 76.44 | 98.64 |
特征融合算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
特征逐元素相加 | 92.97 | 67.82 | 99.25 |
特征拼接 | 94.36 | 83.52 | 97.07 |
自适应特征融合 | 95.36 | 89.31 | 96.87 |
Tab. 5 Performance comparison of different feature fusion algorithms
特征融合算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
特征逐元素相加 | 92.97 | 67.82 | 99.25 |
特征拼接 | 94.36 | 83.52 | 97.07 |
自适应特征融合 | 95.36 | 89.31 | 96.87 |
算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
AlexNet[ | 82.08 | 11.06 | 99.83 |
ResNet34 | 89.32 | 47.87 | 99.67 |
ResNet50 | 91.84 | 61.13 | 99.51 |
本文算法 | 95.36 | 89.31 | 96.87 |
Tab. 6 Performance comparison of different classification networks on Elevator Fall Detection dataset
算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
AlexNet[ | 82.08 | 11.06 | 99.83 |
ResNet34 | 89.32 | 47.87 | 99.67 |
ResNet50 | 91.84 | 61.13 | 99.51 |
本文算法 | 95.36 | 89.31 | 96.87 |
算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
AlexNet[ | 88.20 | 34.30 | 99.60 |
ResNet34 | 96.80 | 82.10 | 100.00 |
ResNet50 | 98.40 | 90.90 | 100.00 |
AR-FD[ | 94.00 | 98.00 | 89.40 |
MEWMA-FD[ | 96.60 | 100.00 | 94.90 |
Mask RCNN-LSTM[ | 96.70 | 91.80 | 100.00 |
DCFI-FD[ | 97.33 | 97.78 | 96.67 |
本文算法 | 99.01 | 100.00 | 98.72 |
Tab. 7 Performance comparison of different algorithms on UR Fall Detection dataset
算法 | 准确率 | 灵敏度 | 特异度 |
---|---|---|---|
AlexNet[ | 88.20 | 34.30 | 99.60 |
ResNet34 | 96.80 | 82.10 | 100.00 |
ResNet50 | 98.40 | 90.90 | 100.00 |
AR-FD[ | 94.00 | 98.00 | 89.40 |
MEWMA-FD[ | 96.60 | 100.00 | 94.90 |
Mask RCNN-LSTM[ | 96.70 | 91.80 | 100.00 |
DCFI-FD[ | 97.33 | 97.78 | 96.67 |
本文算法 | 99.01 | 100.00 | 98.72 |
算法 | 参数量/MB | 速度/FPS | 准确率/% | |
---|---|---|---|---|
CPU | GPU | |||
ResNet18 | 11.18 | 51 | 359 | 83.66 |
ResNet34 | 21.29 | 33 | 225 | 89.32 |
ResNet50 | 23.51 | 20 | 166 | 91.84 |
本文算法 | 11.19 | 48 | 354 | 95.36 |
Tab. 8 Comparison results of different models on parameters, detection frame rate and accuracy
算法 | 参数量/MB | 速度/FPS | 准确率/% | |
---|---|---|---|---|
CPU | GPU | |||
ResNet18 | 11.18 | 51 | 359 | 83.66 |
ResNet34 | 21.29 | 33 | 225 | 89.32 |
ResNet50 | 23.51 | 20 | 166 | 91.84 |
本文算法 | 11.19 | 48 | 354 | 95.36 |
1 | MATHIE M J, COSTER A C F, LOVELL N H, et al. Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement[J]. Physiological Measurement, 2004, 25(2): No.R1. 10.1088/0967-3334/25/2/r01 |
2 | LAI C F, CHANG S Y, CHAO H C, et al. Detection of cognitive injured body region using multiple triaxial accelerometers for elderly falling[J]. IEEE Sensors Journal, 2011, 11(3): 763-770. 10.1109/jsen.2010.2062501 |
3 | CHAITEP T, CHAWACHAT J. A 3-phase threshold algorithm for smartphone-based fall detection[C]// Proceedings of the 14th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology. Piscataway: IEEE, 2017: 183-186. 10.1109/ecticon.2017.8096203 |
4 | ALWAN M, RAJENDRAN P J, KELL S, et al. A smart and passive floor-vibration based fall detector for elderly[C]// Proceedings of the 2nd International Conference on Information and Communication Technologies. Piscataway: IEEE, 2006: 1003-1007. |
5 | LI Y, HO K C, POPESCU M. A microphone array system for automatic fall detection[J]. IEEE Transactions on Biomedical Engineering, 2012, 59(5): 1291-1301. 10.1109/tbme.2012.2186449 |
6 | WANG Y X, WU K S, NI L M. WiFall: device-free fall detection by wireless networks[J]. IEEE Transactions on Mobile Computing, 2017, 16(2): 581-594. 10.1109/tmc.2016.2557792 |
7 | CHARFI I, MITERAN J, DUBOIS J, et al. Definition and performance evaluation of a robust SVM based fall detection solution[C]// Proceedings of the 8th International Conference on Signal Image Technology and Internet Based Systems. Piscataway: IEEE, 2012: 218-224. 10.1109/sitis.2012.155 |
8 | YUN Y X, GU I Y H. Human fall detection via shape analysis on Riemannian manifolds with applications to elderly care[C]// Proceedings of the 2015 IEEE International Conference on Image Processing. Piscataway: IEEE, 2015: 3280-3284. 10.1109/icip.2015.7351410 |
9 | 张舒雅,吴科艳,黄炎子,等. 基于SVM_KNN的老人跌倒检测算法[J]. 计算机与现代化, 2017(12):49-55. 10.3969/j.issn.1006-2475.2017.12.010 |
ZHANG S Y, WU K Y, HUANG Y Z, et al. Fall detection algorithm based on SVM_KNN[J]. Computer and Modernization, 2017(12):49-55. 10.3969/j.issn.1006-2475.2017.12.010 | |
10 | LU L, HUANG H. A hierarchical scheme for vehicle make and model recognition from frontal images of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(5): 1774-1786. 10.1109/tits.2018.2835471 |
11 | LU L, HUANG H. Component-based feature extraction and representation schemes for vehicle make and model recognition[J]. Neurocomputing, 2020, 372: 92-99. 10.1016/j.neucom.2019.09.049 |
12 | FAN Y X, LEVINE M D, WEN G J, et al. A deep neural network for real-time detection of falling humans in naturally occurring scenes[J]. Neurocomputing, 2017, 260: 43-58. 10.1016/j.neucom.2017.02.082 |
13 | MIN W D, 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. 10.1109/access.2018.2795239 |
14 | FENG Q, GAO C Q, WANG L, et al. Spatio-temporal fall event detection in complex scenes using attention guided LSTM[J]. Pattern Recognition Letters, 2020, 130: 242-249. 10.1016/j.patrec.2018.08.031 |
15 | LIE W N, LE A T, LIN G H. Human fall-down event detection based on 2D skeletons and deep learning approach[C]// Proceedings of the 2018 International Workshop on Advanced Image Technology. Piscataway: IEEE, 2018: 1-4. 10.1109/iwait.2018.8369778 |
16 | 伏娜娜,刘大铭,程晓婷,等. 基于轻量级OpenPose模型的跌倒检测算法[J]. 传感器与微系统, 2021, 40(11):131-134, 138. 10.13873/J.1000-9787(2021)11-0131-04 |
FU N N, LIU D M, CHENG X T, et al. Fall detection algorithm based on lightweight OpenPose model[J]. Transducer and Microsystem Technologies, 2021, 40(11):131-134, 138. 10.13873/J.1000-9787(2021)11-0131-04 | |
17 | HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. 10.1109/cvpr.2016.90 |
18 | HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. 10.1109/cvpr.2018.00745 |
19 | KWOLEK B, KEPSKI M. Human fall detection on embedded platform using depth maps and wireless accelerometer[J]. Computer Methods and Programs in Biomedicine, 2014, 117(3): 489-501. 10.1016/j.cmpb.2014.09.005 |
20 | WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11211. Cham: Springer, 2018: 3-19. |
21 | LI X G, PANG T T, LIU W X, et al. Fall detection for elderly person care using convolutional neural networks[C]// Proceedings of the 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics. Piscataway: IEEE, 2017: 1-6. 10.1109/cisp-bmei.2017.8302004 |
22 | HARROU F, ZERROUKI N, SUN Y, et al. Vision-based fall detection system for improving safety of elderly people[J]. IEEE Instrumentation and Measurement Magazine, 2017, 20(6): 49-55. 10.1109/mim.2017.8121952 |
23 | CHEN Y, LI W T, WANG L, et al. Vision-based fall event detection in complex background using attention guided bi-directional LSTM[J]. IEEE Access, 2020, 8: 161337-161348. 10.1109/access.2020.3021795 |
24 | WANG B H, YU J, WANG K, et al. Fall detection based on dual-channel feature integration[J]. IEEE Access, 2020, 8: 103443-103453. 10.1109/access.2020.2999503 |
[1] | Ranyan NI, Yi ZHANG. Action recognition method based on video spatio-temporal features [J]. Journal of Computer Applications, 2023, 43(2): 521-528. |
[2] | Cong LIU, Genshun WAN, Jianqing GAO, Zhonghua FU. End-to-end speech recognition method based on prosodic features [J]. Journal of Computer Applications, 2023, 43(2): 380-384. |
[3] | Ming XU, Linhao LI, Qiaoling QI, Liqin WANG. Abductive reasoning model based on attention balance list [J]. Journal of Computer Applications, 2023, 43(2): 349-355. |
[4] | Xiaomeng SHAO, Meng ZHANG. Temporal convolutional knowledge tracing model with attention mechanism [J]. Journal of Computer Applications, 2023, 43(2): 343-348. |
[5] | Yangping LIN, Jia LIU, Pei CHEN, Mingshu ZHANG, Xiaoyuan YANG. Semi-generative video steganography scheme based on deep convolutional generative adversarial net [J]. Journal of Computer Applications, 2023, 43(1): 169-175. |
[6] | Zeqiang SUN, Bingcai CHEN, Xiaobo CUI, Lei WANG, Yanuo LU. Strip steel surface defect detection by YOLOv5 algorithm fusing frequency domain attention mechanism and decoupled head [J]. Journal of Computer Applications, 2023, 43(1): 242-249. |
[7] | Honggang YANG, Jiejie CHEN, Mengfei XU. Bilinear involution neural network for image classification of fundus diseases [J]. Journal of Computer Applications, 2023, 43(1): 259-264. |
[8] | Jianzhuang LIN, Wenzhong YANG, Sixiang TAN, Lexin ZHOU, Danni CHEN. Fusing filter enhancement and reverse attention network for polyp segmentation [J]. Journal of Computer Applications, 2023, 43(1): 265-272. |
[9] | Yuchao LYU, Xi JIANG, Yinghao XU, Xijun ZHU. Improved brachial plexus nerve segmentation method based on multi-scale feature fusion [J]. Journal of Computer Applications, 2023, 43(1): 273-279. |
[10] | Jun ZHANG, Pengli WU, Lukui SHI, Jin SHI, Bin PAN. Deep learning model for multi-station temperature prediction combined with MOD11A1 and surface meteorological station data [J]. Journal of Computer Applications, 2023, 43(1): 321-328. |
[11] | Bin ZOU, Cong ZHANG. Dense crowd detection algorithm based on Faster R-CNN [J]. Journal of Computer Applications, 2023, 43(1): 61-66. |
[12] | Zihao GUO, Lele DONG, Zhijian QU. Arthropod object detection method based on improved Faster RCNN [J]. Journal of Computer Applications, 2023, 43(1): 88-97. |
[13] | Youxin WANG, Bin CHEN. Print defect detection method based on deep comparison network [J]. Journal of Computer Applications, 2023, 43(1): 250-258. |
[14] | Hui LIU, Xiang MA, Linyu ZHANG, Rujin HE. Aspect-based sentiment analysis model integrating match-LSTM network and grammatical distance [J]. Journal of Computer Applications, 2023, 43(1): 45-50. |
[15] | Zhijun SHEN, Lina MU, Jing GAO, Yuanhang SHI, Zhiqiang LIU. Review of fine-grained image categorization [J]. Journal of Computer Applications, 2023, 43(1): 51-60. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||