Dawei Yang, Xinfei Gong, Lin Mao, Rubo Zhang. Multi-Domain Convolutional Neural Network Tracking Algorithm Based on Reconstructed Feature Combination[J]. Laser & Optoelectronics Progress, 2019, 56(19): 191501
- Laser & Optoelectronics Progress
- Vol. 56, Issue 19, 191501 (2019)
Fig. 1. MDNet network structure diagram
Fig. 2. Feature visualization results (taking some features as examples). (a) Input image; (b) features of Conv3 layer
Fig. 3. Deconvolution implementation process
Fig. 4. Visualization results of reconstructed features (taking some features as examples). (a) Input image; (b) features of Conv3 layer; (c) reconstructed features
Fig. 5. Feature combination
Fig. 6. RCNet network structure (?? indicates feature combination)
Fig. 7. Feature combination analysis. (a) Input image; (b) features of Conv3 layer; (c) features of Conv5 layer; (d) combination features
Fig. 8. OTB50 experimental results. (a) Tracking precision score; (b) tracking success score
Fig. 9. Maps of tracking success rate attributes. (a) Low resolution; (b) background clutter; (c) deformation; (d) occlusion; (e) scale variation; (f) out-of-plane rotation; (g) motion blur; (h) illumination varition
Fig. 10. VOT2015 testing results
|
Table 1. Average tracking speed of various deep learning traking algorithms based on OTB50
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20