Abstract

Visual object tracking is one of the most fundamental tasks in the field of computer vision, and it has numerous applications in many realms such as public surveillance, human-computer interaction, robotics, etc. Recently, discriminative correlation filter (DCF)-based trackers have achieved promising results in short-term tracking problems. Most of them focus on extracting reliable features from the foreground of input images to construct a robust and informative description of the target. However, it is often ignored that the image background which contains the surrounding context of the target is often similar across consecutive frames and thus can be beneficial to locating the target. In this paper, we propose a background perception regulation term to additionally exploit useful background information of the target. Specifically, invalid description of the target can be avoided when either background or foreground information becomes unreliable by assigning similar importance to both of them. Moreover, a novel model update strategy is further proposed. Instead of updating the model by frame, we introduce an output evaluation score, which serves to supervise the tracking process and select high-confidence results for model update, thus paving a new way to avoid model corruption. Extensive experiments on OTB-100 dataset well demonstrate the effectiveness of the proposed method BPCF, which gets an AUC score of 0.689 and outperforms most of the state-of-the-art.

中文翻译：

---

相关滤波器跟踪器的背景感知

摘要

视觉对象跟踪是计算机视觉领域中最基本的任务之一，并且在公共监视，人机交互，机器人等许多领域中都有大量应用。最近，基于判别相关过滤器（DCF）的跟踪器在短期跟踪问题上取得了可喜的成果。他们中的大多数专注于从输入图像的前景中提取可靠的特征，以构建对目标的可靠且信息丰富的描述。然而，常常被忽略的是，包含目标周围环境的图像背景在连续帧中通常是相似的，因此对于定位目标可能是有益的。在本文中，我们提出了一种背景感知调节术语来额外利用目标的有用背景信息。特别，通过为背景或前景信息分配相似的重要性，可以避免对目标的无效描述。此外，还提出了一种新颖的模型更新策略。我们引入了输出评估分数，而不是逐帧更新模型，该输出评估分数用于监督跟踪过程并选择高可信度结果进行模型更新，从而为避免模型损坏提供了新方法。在OTB-100数据集上进行的大量实验很好地证明了所提出方法BPCF的有效性，该方法的AUC得分为0.689，优于大多数最新技术。我们引入了输出评估分数，而不是逐帧更新模型，该输出评估分数用于监督跟踪过程并选择高可信度结果进行模型更新，从而为避免模型损坏提供了新方法。在OTB-100数据集上进行的大量实验很好地证明了所提出的方法BPCF的有效性，该方法的AUC得分为0.689，优于大多数最新技术。我们引入了输出评估分数，而不是逐帧更新模型，该输出评估分数用于监督跟踪过程并选择高可信度结果进行模型更新，从而为避免模型损坏铺平了新道路。在OTB-100数据集上进行的大量实验很好地证明了所提出方法BPCF的有效性，该方法的AUC得分为0.689，优于大多数最新技术。