Fig. 1. Process of obtaining initial frame saliency awareness reference weight for Soccer video sequence. (a) First frame image; (b) saliency detection result; (c) result of saliency detection after treatment; (d) saliency image; (e) saliency awareness reference weight for initial frame
Fig. 2. Visualization of four different spatial regularization weights. (a) W1; (b) W2; (c) W3; (d) W4
Fig. 3. Response of object in different cases for Box video sequence. (a) Object for 130th frame; (b) response for 130th frame; (c) object for 460th frame; (d) response for 460th frame
Fig. 4. Distance precision and success rate on OTB-2015 dataset. (a) Distance precision curve; (b) success rate curve
Fig. 5. Success rate of 4 different attribute video sequences on OTB-2015 dataset. (a) Deformation; (b) out-of-plane rotation; (c) occlusion; (d) out of view
Fig. 6. Tracking results of our algorithm and comparison algorithms on 4 video sequences. (a) Box; (b) dragonbaby; (c) shaking; (d) soccer
ADMM | Relevant parameter |
---|
Solving filtering function and temporal regularization parameter | γ(0)=1,γmax=10,α=0.1,NI=2 | Solving spatial regularization weight | ζ(0)=1,ζmax=100,β=10,N'I=2 |
|
Table 1. Relevant parameters setting of ADMM in the process of algorithm optimization
Parameter setting | DP | SR |
---|
ζ(0)=1,ζmax=1000,β=10,N'I=2 | 86.2 | 65.1 | ζ(0)=1,ζmax=10000,β=10,N'I=2 | 84.1 | 63.8 | ζ(0)=1,ζmax=100,β=10,N'I=2 | 86.4 | 65.6 | ζ(0)=1,ζmax=100,β=10,N'I=3 | 84.9 | 64.3 |
|
Table 2. Comparison of tracking performance of algorithm in different parameter settingsunit: %
Algorithm | DSST | BACF | SRDCF | STRCF | CNN-SVM | Ours |
---|
Average tracking speed /(frame·s-1) | 31.8 | 22.1 | 3.3 | 13.7 | N | 12.1 |
|
Table 3. Comparison of average tracking speeds on OTB-2015 dataset