Uncertain motion tracking based on convolutional net with semantics estimation and region proposals
作者：
Highlights：
• A novel uncertain motion tracking framework with semantics estimation and region proposals is proposed.
• A semantics object proposals generation strategy is proposed.
• The proposed hybrid semantics tracking algorithm combines the full advantages of globally sparse semantics region proposals prediction and correlation filter prediction.
• The proposed semantics-contextual estimation method can generate more credible candidates.
• Experimental results show the state-of-the-art performance of our method.
摘要
•A novel uncertain motion tracking framework with semantics estimation and region proposals is proposed.•A semantics object proposals generation strategy is proposed.•The proposed hybrid semantics tracking algorithm combines the full advantages of globally sparse semantics region proposals prediction and correlation filter prediction.•The proposed semantics-contextual estimation method can generate more credible candidates.•Experimental results show the state-of-the-art performance of our method.
论文关键词：Correlation filter,Semantics estimation,Visual tracking,Region proposals,Contextual information
论文评审过程：Received 31 May 2019, Revised 17 December 2019, Accepted 23 January 2020, Available online 24 January 2020, Version of Record 30 January 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107232
