Individual Cow Recognition Based on Convolution Neural Network and Transfer Learning

Fig. 11. Detection effect of SSD algorithm with different training methods. (a) Transfer learning trains only the classification layer; (b) new study; (c) transfer learning trains all layers

Download full size

Fig. 12. Detection effect of improved SSD algorithm under different training methods. (a) Transfer learning trains all layers; (b) new study; (c) transfer learning trains only classification layer

Download full size

Table 1. Candidate box parameter setting of SSD algorithm
View table
Table 1. Candidate box parameter setting of SSD algorithm
Feature map M×N K Aspect ration Number of candidate frames
Conv4_3 38×38 4 1,2 5776
FC7 19×19 6 1,2,3 2166
Conv8_2 10×10 6 1,2,3 600
Conv9_2 5×5 6 1,2,3 150
Conv10_2 3×3 4 1,2 36
Conv11_2 1×1 4 1,2 4

Table 2. Parameter setting of upper sampling layer under different fusion modes
View table
Table 2. Parameter setting of upper sampling layer under different fusion modes
Upper sampling layer Number of output channels Kernel_size Stride Padding
concat add
Conv11_2 256 256 3 3 Same
Conv10_2 256 256 3 1 Valid
Conv9_2 512 512 3 2 Same
Conv8_2 512 1024 10 1 Valid

Table 3. Parameter setting of candidate frame of improved SSD algorithm
View table
Table 3. Parameter setting of candidate frame of improved SSD algorithm
Feature map M×N K Aspect_ration Number of candidate frames Total number of candidate frames
FC7 19×19 8 1,2,3,4 2888 3948
Conv8_2 10×10 8 1,2,3,4 800
Conv9_2 5×5 8 1,2,3,4 200
Conv10_2 3×3 6 1,2,3 54
Conv11_2 1×1 6 1,2,3 6

Table 4. Experimental results on test sets of different fusion methods
View table
Table 4. Experimental results on test sets of different fusion methods
Experimental algorithm Feature fusion Fusion method P_AP /% Average detection time /ms
SSD 88.23 46.23
SSD √ Add 88.11 51.52
SSD √ Concat 90.58 54.04

Table 5. Experimental results of SSD algorithm and improved SSD algorithm on test set
View table
Table 5. Experimental results of SSD algorithm and improved SSD algorithm on test set
Experimental algorithm N_TP/N_FP/N_FN P /% R /% P_AP/% Average detection time /ms
SSD 454/12/60 97.42 88.32 88.23 46.23
Improved SSD 476/7/38 98.55 92.60 92.55 54.16

Table 6. Experimental results of different training methods on test set

View table

Table 6. Experimental results of different training methods on test set

Experimental algorithm	Training method	N_TP/N_FP/N_FN	P /%	R /%	P_AP/%
SSD	New training	454/12/60	97.42	88.32	88.23
SSD	Transfer learning only trains classification layer	368/3/146	99.19	71.59	71.56
SSD	Transfer all levels of learning and training	477/8/37	98.35	92.80	92.69
Improved SSD	New training	476/7/38	98.55	92.60	92.55
Improved SSD	Transfer learning only trains classification layer	388/11/126	97.24	75.48	75.24
Improved SSD	Transfer all levels of learning and training	496/7/18	98.60	96.49	96.40

Table 7. Influence of training set size of target domain on recognition accuracy after transfer learning
View table
Table 7. Influence of training set size of target domain on recognition accuracy after transfer learning
Algorithm 20% of the training set 50% of the training set 80% of the training set All training set
SSD 87.24 92.94 93.13 92.69
ImprovedSSD 91.73 95.10 95.66 96.40

Table 8. Average accuracy of different algorithms
View table
Table 8. Average accuracy of different algorithms
Algorithm P_AP /% Average detection time /ms
SSD 88.23 46.23
YOLOV2 85.26 20.49
YOLOV3 90.80 53.24
Method in Ref. [13] 85.46 19.64
Method in Ref. [14] 93.21 55.01
Method in this paper 96.40 54.16

Tools

Get Citation

Copy Citation Text

Yongxin Xing, Biqiao Wu, Songping Wu, Tianyi Wang. Individual Cow Recognition Based on Convolution Neural Network and Transfer Learning[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1628002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites