Laser & Optoelectronics Progress, Volume. 57, Issue 10, 101010(2020)
Multi-Target Recognition Method Based on Improved YOLOv2 Model
Figures & Tables(13)
Fig. 2. Test results of different models. (a) Model 1; (b) model 2; (c) model 3; (d) model 4; (e) model 5; (f) model 6
Fig. 5. Loss graphs of different models. (a) YOLOv2; (b) YOLOv2-voc; (c) YOLOv3; (d) YOLOv2-voc_mul
Fig. 6. Verification results of different models. (a) YOLOv2; (b) YOLOv2-voc; (c) YOLOv3; (d) YOLOv2-voc_mul
Fig. 9. Test results of different models. (a) YOLOv2 model; (b) YOLOv2-voc model; (c) YOLOv3 model; (d) YOLOv2-voc_mul model
Table 1. Network framework
View tableTable 1. Network framework
Model Learning rate Layer number of network structure Activation function Convolution layer Maximum pooling layer+ average pooling layer BN layer Model 1 0.001 23 5+0 22 22 leaky+1 linear Model 2 0.0001 23 5+0 20 22 leaky+1 linear Model 3 0.01 23 5+0 22 22 leaky+1 linear Model 4 0.001 20 5+1 22 19 leaky+1 linear Model 5 0.001 20 5+1 22 19 leaky+1 ReLU Model 6 0.001 20 5+0 20 19 leaky+1 linear
Table 2. Test results
View tableTable 2. Test results
Model Ntotal Ccorrect Pproposal Pprecision /% Rrecall /% F1 /% YOLOv2 152 146 151 96.69 96.05 96.36 YOLOv2-voc 152 144 146 98.63 94.74 96.64 YOLOv3 152 85 150 56.67 55.92 69.68 YOLOv2- voc_mul 152 145 146 99.20 95.39 97.26
Table 4. Comparison of mAP value in different models
View tableTable 4. Comparison of mAP value in different models
Model mAP /% Truck Bus Van Car YOLOv2 86.45 84.16 82.37 86.88 YOLOv2-voc 87.61 85.22 83.02 87.31 YOLOv3 83.35 81.83 77.96 83.92 YOLOv2-voc_mul 88.72 88.56 86.64 89.03
Table 5. Average accuracy of vehicle identification in the YOLOv2-voc_mul model
View tableTable 5. Average accuracy of vehicle identification in the YOLOv2-voc_mul model
Type Accuracy /% Average accuracy /% Truck Bus Van Car Simple target 92.14 91.89 90.08 94.72 92.21 Multiple target 89.01 88.76 88.20 91.71 89.44
Tools
Get Citation
Copy Citation Text
Xun Li, Binbin Shi, Yang Liu, Lei Zhang, Xiaohua Wang. Multi-Target Recognition Method Based on Improved YOLOv2 Model[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101010
Paper Information
Category: Image Processing
Received: Aug. 28, 2019
Accepted: Oct. 18, 2019
Published Online: May. 8, 2020
The Author Email: Binbin Shi (734931099@qq.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20