Robust object tracking via integration of particle filtering with deep detection

We propose a video object tracker (IDPF-RP) which is built upon the variable-rate color particle filtering with two innovations: (i) A deep region proposal network guided candidate BB selection scheme based on the dynamic prediction model of particle filtering is proposed to accurately generate the qualified object BBs. The introduced region proposal alignment scheme significantly improves the localization accuracy of tracking. (ii) A decision level fusion scheme that integrates the particle filter tracker and a deep detector resulting in an improved object tracking accuracy is formulated. This enables us to adaptively update the target model that improves robustness to appearance changes arising from high motion and occlusion. Performance evaluation reported on challenging VOT2018/2017/2016 and OTB-50 data sets demonstrates that IDPF-RP outperforms state-of-the-art trackers especially under size, appearance and illumination changes. Our tracker achieves comparable mean accuracy on VOT2018 while it respectively provides about 8%, 15%, and 30% higher success rates on VOT2016, VOT2017 and OTB-50 when IoU threshold is 0.5.