计算机科学
判别式
BitTorrent跟踪器
正规化(语言学)
人工智能
计算机视觉
源代码
眼动
操作系统
作者
Yiming Li,Changhong Fu,Fangqiang Ding,Ziyuan Huang,Geng Lu
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2020-06-01
卷期号:: 11920-11929
被引量:452
标识
DOI:10.1109/cvpr42600.2020.01194
摘要
Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of correlation filters. However, predefined parameters introduce much effort in tuning them and they still fail to adapt to new situations that the designer did not think of. In this work, a novel approach is proposed to online automatically and adaptively learn spatio-temporal regularization term. Spatially local response map variation is introduced as spatial regularization to make DCF focus on the learning of trust-worthy parts of the object, and global response map variation determines the updating rate of the filter. Extensive experiments on four UAV benchmarks have proven the superiority of our method compared to the state-of-the-art CPU- and GPU-based trackers, with a speed of ~60 frames per second running on a single CPU. Our tracker is additionally proposed to be applied in UAV localization. Considerable tests in the indoor practical scenarios have proven the effectiveness and versatility of our localization method. The code is available at https://github.com/vision4robotics/AutoTrack.
科研通智能强力驱动
Strongly Powered by AbleSci AI