Robust Long-Term Object Tracking via Improved Discriminative Model Prediction
Robust Long-Term Object Tracking via Improved Discriminative Model Prediction
复制标题
通过改进的判别模型预测实现稳健的长期对象跟踪
DOI:
10.1007/978-3-030-68238-5_40
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Hauptmann, A.
中科院分区:
文献类型:
--
作者:
Choi, S.;Lee, J.;Lee, Y.;Hauptmann, A.
We propose an improved discriminative model prediction method for robust long-term tracking based on a pre-trained short-term tracker. The baseline pre-trained short-term tracker is SuperDiMP which combines the bounding-box regressor of PrDiMP with the standard DiMP classifier. Our tracker RLT-DiMP improves SuperDiMP in the following three aspects: (1) Uncertainty reduction using random erasing: To make our model robust, we exploit an agreement from multiple images after erasing random small rectangular areas as a certainty. And then, we correct the tracking state of our model accordingly. (2) Random search with spatio-temporal constraints: we propose a robust random search method with a score penalty applied to prevent the problem of sudden detection at a distance. (3) Background augmentation for more discriminative feature learning: We augment various backgrounds that are not included in the search area to train a more robust model in the background clutter. In experiments on the VOT-LT2020 benchmark dataset, the proposed method achieves comparable performance to the state-of-the-art long-term trackers. The source code is available at: https://github.com/bismex/RLT-DIMP .
DOI:
10.1109/tpami.2016.2577031
发表时间:
2017-06-01
影响因子:
23.6
作者:
Ren, Shaoqing;He, Kaiming;Sun, Jian
通讯作者:
Sun, Jian