He Haiyu, Chen Zhen, Li Zhen, Liu Xiangdong, Liu Haikuo
School of Automation, Beijing Institute of Technology, Beijing 100010, China.
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100010, China.
Sensors (Basel). 2023 Aug 30;23(17):7516. doi: 10.3390/s23177516.
Visual object tracking is a fundamental task in computer vision that requires estimating the position and scale of a target object in a video sequence. However, scale variation is a difficult challenge that affects the performance and robustness of many trackers, especially those based on the discriminative correlation filter (DCF). Existing scale estimation methods based on multi-scale features are computationally expensive and degrade the real-time performance of the DCF-based tracker, especially in scenarios with restricted computing power. In this paper, we propose a practical and efficient solution that can handle scale changes without using multi-scale features and can be combined with any DCF-based tracker as a plug-in module. We use color name (CN) features and a salient feature to reduce the target appearance model's dimensionality. We then estimate the target scale based on a Gaussian distribution model and introduce global and local scale consistency assumptions to restore the target's scale. We fuse the tracking results with the DCF-based tracker to obtain the new position and scale of the target. We evaluate our method on the benchmark dataset Temple Color 128 and compare it with some popular trackers. Our method achieves competitive accuracy and robustness while significantly reducing the computational cost.
视觉目标跟踪是计算机视觉中的一项基本任务，它需要估计视频序列中目标物体的位置和尺度。然而，尺度变化是一个难题，会影响许多跟踪器的性能和鲁棒性，尤其是那些基于判别相关滤波器（DCF）的跟踪器。现有的基于多尺度特征的尺度估计方法计算成本高，会降低基于DCF的跟踪器的实时性能，特别是在计算能力受限的场景中。在本文中，我们提出了一种实用且高效的解决方案，该方案无需使用多尺度特征就能处理尺度变化，并且可以作为插件模块与任何基于DCF的跟踪器相结合。我们使用颜色名称（CN）特征和一个显著特征来降低目标外观模型的维度。然后，我们基于高斯分布模型估计目标尺度，并引入全局和局部尺度一致性假设来恢复目标的尺度。我们将跟踪结果与基于DCF的跟踪器进行融合，以获得目标的新位置和尺度。我们在基准数据集Temple Color 128上评估我们的方法，并将其与一些流行的跟踪器进行比较。我们的方法在显著降低计算成本的同时，实现了具有竞争力的准确性和鲁棒性。
