Laser & Optoelectronics Progress, Volume. 59, Issue 22, 2215001(2022)
Human Behavior Recognition for Embedded System
Figures & Tables(15)
Fig. 3. Depthwise separable convolution decomposition process. (a) Standard convolution; (b) depthwise convolution; (c) pointwise convolution
Fig. 7. Human behavior recognition test device. (a) Test device; (b) Jetson Xavier NX development board
Table 1. Adjusted feature extraction network structure
View tableTable 1. Adjusted feature extraction network structure
Convolution type Convolution kernel size Stride Dilation Padding conv 3×3×32 2 1 0 conv dw_1 3×3×64 1 1 0 conv dw_2 3×3×128 2 1 0 conv dw_3 3×3×128 1 1 0 conv dw_4 3×3×256 2 1 0 conv dw_5 3×3×256 1 1 0 conv dw_6 3×3×512 1 1 0 conv dw_7 3×3×512 1 2 2 conv dw_8 3×3×512 1 1 0 conv dw_9 3×3×512 1 1 0 conv dw_10 3×3×512 1 1 0 conv dw_11 3×3×512 1 1 0
Table 2. Number of samples of various behaviors in dataset
View tableTable 2. Number of samples of various behaviors in dataset
Category 11 types of human behavior data set （17454） Number of samples Number of samples in training set Number of samples in validation set Stand 1644 13963 3491 Squat 1288 Run 1608 Bend 1428 Fall 1008 Operate the PC 2001 Leg press 2060 Walk 1389 Wave 782 Kick 2300 Hug 1946
Table 3. Software and hardware used in experiment
View tableTable 3. Software and hardware used in experiment
Software and hardware platform Parameter Embedded development board NVIDIA Jetson Xavier NX Operating system Ubuntu 18.04 Deep learning framework Tensorflow CPU 6-core NVIDIA Carmel ARM®v8.2 64-bit CPU GPU NVIDIA Volta™ Architecture 384 NVIDIA® CUDA® cores and 48 Tensor cores CUDA 10.2 cuDNN 8.0 Programming language Python 3.6
Table 4. Experimental parameter description
View tableTable 4. Experimental parameter description
Parameter name Parameter value Input_size 224×224 Epoch 160 Batch_size 64 Learning_rate 0.0001 Loss function Cross entropy loss Optimizer Adam
Table 5. Recognition confusion matrix of 11 types of human behavior
View tableTable 5. Recognition confusion matrix of 11 types of human behavior
Category Stand Squat Run Bend Fall Operate the PC Leg press Walk Wave Kick Hug Stand 100 0 0 0 0 0 0 0 0 0 0 Squat 0 100 0 0 0 0 0 0 0 0 0 Run 1.3 0 94.5 0 0 0 0 4.2 0 0 0 Bend 0 16.7 0 83.3 0 0 0 0 0 0 0 Fall 0 2.5 0 0 97.5 0 0 0 0 0 0 Operate the PC 0 0 0 0 0 100 0 0 0 0 0 Leg press 0 3.3 0 0 5.7 0 91.0 0 0 0 0 Walk 1.5 0 1.2 0 0 0 0 97.3 0 0 0 Wave 0 0 0 0 0 0 0 0 100 0 0 Kick 0 0 0 0 0 0 0 0 100 0 Hug 0 0 0 0 0 0 0 0 6.7 0 93.3
Table 6. Comparison of different models
View tableTable 6. Comparison of different models
Model Feature extraction network File size /MB Recognition accuracy /% Detection speed /（frame·s-1） OpenPose VGG19 200 96.24 3.98 Lightweight OpenPose MobileNet 7.5 96.08 11.04
Table 7. Related research comparison
View tableTable 7. Related research comparison
Method Type of behavior Recognition rate /% Reference［ 4 ］clap， walk， dribble， play golf 86.25 Reference［ 13 ］walk， jog， go up and down， sit， stand 91.60 Reference［ 14 ］walk， run， go up and down， stand still， sit-stand， stand-sit， stand-squat， squat-stand 95.05 Reference［ 15 ］walk， run， jump， go up and down stairs 85.00 Proposed method stand， walk， run， squat， bend， kick， hug， fall， wave， side press， computer the PC 96.08
Tools
Get Citation
Copy Citation Text
Nana Fu, Daming Liu, Hengbo Zhang, Xuandong Li. Human Behavior Recognition for Embedded System[J]. Laser & Optoelectronics Progress, 2022, 59(22): 2215001
Paper Information
Category: Machine Vision
Received: Aug. 10, 2021
Accepted: Sep. 24, 2021
Published Online: Sep. 23, 2022
The Author Email: Liu Daming (nxldm@126.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20