Author Affiliations
1Key Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China2University of Chinese Academy of Sciences, Beijing 100049, Chinashow less
Fig. 1. Framework of Siamese network with channel spatial coordination attention module
Fig. 2. Convolutional blocks of MobileNetV2
Fig. 3. Convolution process abstract graph of MobileNetV2
Fig. 4. Grad-CAM network visualization results. (a) No attention module; (b) with attention module
Fig. 5. Channel spatial coordination attention module
Fig. 6. Success rate comparison of different attention module combinations on OTB-2015
Fig. 7. Precision comparison of different attention module combinations on OTB-2015
Fig. 8. Qualitative results of the nine tracking algorithms on different video sequences. (a) car6_5; (b) car17; (c) person9; (d) person1_s; (e) uav4; (f) wakeboard6
Fig. 9. Results of problem sequence on uav1_1
Fig. 10. Results of the tracking algorithms on OTB-2015. (a) Success plot; (b) precision plot
Fig. 11. Tracking success plots of different attributes videos. (a) Scale variation; (b) aspect ratio change; (c) low resolution; (d) fast motion; (e) full occlusion; (f) partial occlusion; (g) out-of-view; (h) background clutter; (i) illumination variation; (j) viewpoint change; (k) camera motion; (l) similar object
Fig. 12. Tracking precision plots of different attributes videos. (a) Scale variation; (b) aspect ratio change; (c) low resolution; (d) fast motion; (e) full occlusion; (f) partial occlusion; (g) out-of-view; (h) background clutter; (i) illumination variation; (j) viewpoint change; (k) camera motion; (l) similar object
Fig. 13. Quantitative analysis of some video sequences. (a) Scale variation and aspect ratio change; (b) CLE
Layer name | Input | Operator | Expansion factor | Channel | Repeat time | Stride | CSCAM |
---|
Input | 255×255×3 | Conv2d | - | 32 | 1 | 2 | No | Layer1 | 127×127×32 | Bottleneck | 1 | 16 | 1 | 1 | No | Layer 2 | 127×127×16 | Bottleneck | 6 | 24 | 2 | 2 | No | Layer 3 | 63×63×24 | Bottleneck | 6 | 32 | 3 | 2 | Yes | Layer 4 | 31×31×32 | Bottleneck | 6 | 64 | 4 | 1 | No | Layer 5 | 31×31×64 | Bottleneck | 6 | 96 | 3 | 1 | Yes | Layer 6 | 31×31×96 | Bottleneck | 6 | 160 | 3 | 1 | Yes | Layer 7 | 31×31×160 | Bottleneck | 6 | 320 | 1 | 1 | Yes | Output | 31×31×320 | - | - | - | - | - | - |
|
Table 1. Architecture of Siamese network based on MobieleNetV2