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:
Computer Vision – ECCV 2020 Workshops
影响因子:
--
通讯作者:
Hauptmann, A.
Hauptmann, A.
中科院分区:
--
文献类型:
--
作者:
Choi, S.;Lee, J.;Lee, Y.;Hauptmann, A.

文献摘要

参考文献

被引文献

相似文献

我们提出了一种改进的判别模型预测方法,用于基于预训练的短期跟踪器的鲁棒长期跟踪。基线预训练短期跟踪器是 SuperDiMP,它将 PrDiMP 的边界框回归器与标准 DiMP 分类器相结合。我们的跟踪器 RLT-DiMP 在以下三个方面改进了 SuperDiMP:(1)使用随机擦除来减少不确定性:为了使我们的模型具有鲁棒性,我们在擦除随机小矩形区域后利用多个图像的一致性作为确定性。然后,我们相应地纠正模型的跟踪状态。 (2)具有时空约束的随机搜索:我们提出了一种鲁棒的随机搜索方法,并应用分数惩罚来防止远距离突然检测的问题。 (3)背景增强以实现更具辨别力的特征学习:我们增强了搜索区域中未包含的各种背景,以在背景杂乱中训练更鲁棒的模型。在 VOT-LT2020 基准数据集的实验中,所提出的方法实现了与最先进的长期跟踪器相当的性能。源代码位于:https://github.com/bismex/RLT-DIMP。
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