Author Affiliations
School of Electrical Engineering and Automation, Anhui University, Hefei 230601, Anhui , Chinashow less
Fig. 1. Framework of proposed algorithm
Fig. 2. Architecture of the SK attention network
Fig. 3. Architecture of the MSI module
Fig. 4. Visualization results of originalimage and features from corresponding layer.(a) Original image centered on the target; (b) low level features; (c) high level features; (d) fused version generated by MFB
Fig. 5. Architecture of the multi-scale channel attention network
Fig. 6. Comparison of success rate and precision on OTB100 dataset. (a) Success rate; (b) precision
Fig. 7. EAO performance on VOT2018 dataset
Fig. 8. EAO under different visual attributes on VOT2018
Fig. 9. Comparison of success rate and accuracy on LaSOT dataset.(a) Success rate; (b) normalized precision
Fig. 10. Comparison of speed and performance of different algorithms on LaSOT dataset
Fig. 11. Tracking results of five algorithms
Parameter | DLST | SASiamR | CPT | DRT | RCO | MFT | LADCF | ATOM | Ours |
---|
| 0.325 | 0.337 | 0.339 | 0.356 | 0.376 | 0.385 | 0.389 | 0.401 | 0.426 | | 0.543 | 0.566 | 0.507 | 0.519 | 0.507 | 0.505 | 0.503 | 0.590 | 0.597 | | 0.224 | 0.258 | 0.239 | 0.201 | 0.155 | 0.140 | 0.159 | 0.204 | 0.183 |
|
Table 1. Comparison of experimental results on the VOT2018 dataset
Parameter | ECO | SiamFC | SPM | MDNet | SiamMask | ATOM | D3S | Ours |
---|
| 55.4 | 57.1 | 71.2 | 60.6 | 72.5 | 70.3 | 72.8 | 72.8 | | 49.2 | 53.3 | 66.1 | 56.5 | 66.4 | 64.8 | 66.4 | 67.2 | | 61.8 | 66.6 | 44.8 | 70.5 | 77.8 | 77.1 | 76.8 | 78.9 |
|
Table 2. Comparison of experimental results on the TrackingNet dataset
Parameter | ECO | SiamFC | SPM | MDNet | SiamMask | ATOM | D3S | Ours |
---|
| 31.5 | 34.8 | 51.3 | 29.9 | 51.4 | 55.6 | 59.7 | 58.2 | | 11.1 | 9.8 | 35.9 | 9.9 | 36.6 | 40.2 | 46.2 | 45.4 | | 30.9 | 35.3 | 59.3 | 30.3 | 58.7 | 63.5 | 67.6 | 66.7 |
|
Table 3. Comparison of experimental results on the GOT10k dataset
No. | SK | | MSI | | PMB | VOT2018 EAO | GOT10k AO |
---|
SFB | MFB-MCAM | MFB |
---|
① | | | | | | 0.401 | 0.556 | ② | √ | | | | | 0.412 | 0.564 | ③ | √ | √ | | | | 0.416 | 0.571 | ④ | √ | √ | √ | | | 0.413 | 0569 | ⑤ | √ | √ | | √ | | 0.421 | 0.575 | ⑥ | √ | √ | | √ | √ | 0.426 | 0.582 |
|
Table 4. Tracking results of the proposed algorithm after adding various components