Laser & Optoelectronics Progress, Volume. 56, Issue 13, 131101(2019)
Method of Detecting Abnormal Behavior in Video Sequences Based on Deep Network Models
Figures & Tables(15)
Table 1. Convolutional neural network parameters
View tableTable 1. Convolutional neural network parameters
Layer Size /(pixel×pixel) Number of layers Input 28×28 1 Convolution kernel 5 ×5 3 Pooling layer 2 ×2 3 Fully connected layer 192 ×1 2 Output 10 ×1 1
Table 2. Comparison of misidentification rates of six optimization algorithms[21]
View tableTable 2. Comparison of misidentification rates of six optimization algorithms[21]
Algorithm SGD AdaDelta NAG AdaGrad Adam RMSProp False rate /% 16.15 19.56 28.68 18.97 12.33 17.37
Table 3. Misrecognition rate comparison
View tableTable 3. Misrecognition rate comparison
Number of iterations Old misrecognition rate /% New misrecognition rate /% Reduction rate /% 100 50.44 19.18 61.97 1200 27.15 12.69 53.26 2200 20.26 10.27 49.31 3400 15.34 8.43 45.05 4000 12.33 8.01 35.04
Table 4. Recognition effect of different algorithms
View tableTable 4. Recognition effect of different algorithms
Algorithm Two- stream TSN iDT TRN This paper False rate /% 9.37 7.93 8.54 7.26 8.01 Reduction rate /% 14.5 -1.0 6.2 -10.3 -
Table 5. Recognition effect on UT-interaction database
View tableTable 5. Recognition effect on UT-interaction database
Algorithm Two- stream TSN iDT TRN This paper False rate /% 12.62 9.49 10.44 8.92 9.53 Reduction rate /% 24.5 -0.4 8.7 -6.8 -
Tools
Get Citation
Copy Citation Text
Peiji Wu, Xue Mei, Yi He, Shenqiang Yuan. Method of Detecting Abnormal Behavior in Video Sequences Based on Deep Network Models[J]. Laser & Optoelectronics Progress, 2019, 56(13): 131101
Paper Information
Category: Imaging Systems
Received: Dec. 13, 2018
Accepted: Jan. 22, 2019
Published Online: Jul. 11, 2019
The Author Email: Wu Peiji (1434519290@qq.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20