Fig. 2
From: Object state optimization algorithm based on Bayesian random sampling for visual object tracking

Tracking results on representative sequences from the OTB-100 dataset59, including Soccer, Bolt, Coupon, Ironman, and Subway. All images are from this public benchmark. The SuperDiMP tracker is used as the baseline tracker, and BRSO optimization is introduced to enhance the object tracking results. Red indicates the baseline results, while green represents the tracking results after integrating SuperDiMP+BRSO.