Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps

作者：

Highlights：

• A novel effective non-rigid object tracking framework is proposed with the spatial-temporal consistent saliency detection.

• An efficient TFCN is developed to produce the local saliency prior for a given image region.

• A multi-scale multi-region mechanism is presented to generate multiple local saliency maps and then fuse them through a weighted entropy method.

• Extensive experiments on public saliency detection and visual tracking datasets show that our algorithm achieves considerably impressive results in both research fields.

摘要

•A novel effective non-rigid object tracking framework is proposed with the spatial-temporal consistent saliency detection.•An efficient TFCN is developed to produce the local saliency prior for a given image region.•A multi-scale multi-region mechanism is presented to generate multiple local saliency maps and then fuse them through a weighted entropy method.•Extensive experiments on public saliency detection and visual tracking datasets show that our algorithm achieves considerably impressive results in both research fields.

论文关键词：Deep neural network,Non-rigid object tracking,Salient object detection,Spatial-temporal consistency

论文评审过程：Received 5 January 2019, Revised 10 October 2019, Accepted 24 November 2019, Available online 25 November 2019, Version of Record 29 November 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107130