Feature Fusion Video Target Tracking Method Based on Convolutional Neural Network

Meiju Liu; Yongzhan Cao; Shuyun Zhu; Shangkui Yang

doi:10.3788/LOP57.041502

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 4 >Page 041502 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 4, 041502 (2020)

Feature Fusion Video Target Tracking Method Based on Convolutional Neural Network

Meiju Liu¹, Yongzhan Cao^1、*, Shuyun Zhu², and Shangkui Yang³

Author Affiliations

¹Information & Control Engineering Faculty, Shenyang Jianzhu University, Shenyang, Liaoning 110168, China;

²School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang, Liaoning 110168, China

³School of Mechanical Engineering and Automation, Northeastern University, Shenyang, Liaoning 110168, China

show less

DOI: 10.3788/LOP57.041502 Cite this Article Set citation alerts

Meiju Liu, Yongzhan Cao, Shuyun Zhu, Shangkui Yang. Feature Fusion Video Target Tracking Method Based on Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041502 Copy Citation Text

show less

Fig. 1. VGG16 network architecture

Download full size

Fig. 2. Precision plot

Download full size

Fig. 3. Success rate plot

Download full size

Fig. 4. Comparison of center position error (pixel level) . (a) Car4; (b) David; (c) Dudek; (d) Singer1; (e) Soccer; (f) Sylvester

Download full size

Fig. 5. Comparison of overlap rate. (a) Car4; (b) David; (c) Dudek; (d) Singer1; (e) Soccer; (f) Sylvester

Download full size

Fig. 6. Comparison of tracking results of various algorithms

Meiju Liu, Yongzhan Cao, Shuyun Zhu, Shangkui Yang. Feature Fusion Video Target Tracking Method Based on Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041502

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information