Liu Xiangpeng, Han Jianjiao, Peng Yulin, Liang Qiao, An Kang, He Fengqin, Cheng Yuhua
College of Information, Mechanical & Electrical Engineering, Shanghai Normal University, 100 Haisi Road, Shanghai 201418, China.
Shanghai Research Institute of Microelectronics, Peking University, Shanghai 201203, China.
Sensors (Basel). 2024 Dec 21;24(24):8176. doi: 10.3390/s24248176.
Despite the accuracy and robustness attained in the field of object tracking, algorithms based on Siamese neural networks often over-rely on information from the initial frame, neglecting necessary updates to the template; furthermore, in prolonged tracking situations, such methodologies encounter challenges in efficiently addressing issues such as complete occlusion or instances where the target exits the frame. To tackle these issues, this study enhances the SiamRPN algorithm by integrating the convolutional block attention module (CBAM), which enhances spatial channel attention. Additionally, it integrates the kernelized correlation filters (KCFs) for enhanced feature template representation. Building on this, we present DSiam-CnK, a Siamese neural network with dynamic template updating capabilities, facilitating adaptive adjustments in tracking strategy. The proposed algorithm is tailored to elevate the Siamese neural network's accuracy and robustness for prolonged tracking, all the while preserving its tracking velocity. In our research, we assessed the performance on the OTB2015, VOT2018, and LaSOT datasets. Our method, when benchmarked against established trackers, including SiamRPN on OTB2015, achieved a success rate of 92.1% and a precision rate of 90.9%. On the VOT2018 dataset, it excelled, with a VOT-A (accuracy) of 46.7%, a VOT-R (robustness) of 135.3%, and a VOT-EAO (expected average overlap) of 26.4%, leading in all categories. On the LaSOT dataset, it achieved a precision of 35.3%, a normalized precision of 34.4%, and a success rate of 39%. The findings demonstrate enhanced precision in tracking performance and a notable increase in robustness with our method.
尽管在目标跟踪领域已经取得了准确性和鲁棒性，但基于暹罗神经网络的算法往往过度依赖初始帧的信息，而忽略了对模板进行必要的更新；此外，在长时间跟踪的情况下，此类方法在有效解决诸如完全遮挡或目标离开帧的情况等问题时会遇到挑战。为了解决这些问题，本研究通过集成增强空间通道注意力的卷积块注意力模块（CBAM）来增强SiamRPN算法。此外，它还集成了核相关滤波器（KCF）以增强特征模板表示。在此基础上，我们提出了DSiam-CnK，一种具有动态模板更新能力的暹罗神经网络，便于在跟踪策略中进行自适应调整。所提出的算法旨在提高暹罗神经网络在长时间跟踪中的准确性和鲁棒性，同时保持其跟踪速度。在我们的研究中，我们在OTB2015、VOT2018和LaSOT数据集上评估了性能。与包括OTB2015上的SiamRPN在内的既定跟踪器相比，我们的方法成功率达到92.1%，精确率达到90.9%。在VOT2018数据集上，它表现出色，VOT-A（准确率）为46.7%，VOT-R（鲁棒性）为135.3%，VOT-EAO（预期平均重叠率）为26.4%，在所有类别中领先。在LaSOT数据集上，它的精确率为35.3%，归一化精确率为34.4%，成功率为39%。研究结果表明，我们的方法在跟踪性能上提高了精度，在鲁棒性上有显著提升。
