NoisyOTNet: A Robust Real-Time Vehicle Tracking Model for Traffic Surveillance
NoisyOTNet: A Robust Real-Time Vehicle Tracking Model for Traffic Surveillance
复制标题
NoisyOTNet：用于交通监控的鲁棒实时车辆跟踪模型
DOI：
10.1109/tcsvt.2021.3086104
复制
发表时间：
2022-04
影响因子：
8.4
通讯作者：
Liqiang Wang
中科院分区：
文献类型：
--
作者：
Weiwei Xing;Yuxiang Yang;Shunli Zhang;Qi Yu;Liqiang Wang
随着智能交通的快速发展，自动交通监控被认为是一个重要的组成部分。在交通监控领域，实现复杂场景下对车辆的鲁棒实时跟踪显得尤为重要。本文提出了一种鲁棒实时车辆跟踪模型NoisyOTNet，该模型将跟踪描述为带有参数空间噪声的强化学习。在该公式中，增强了模型的探索能力，提高了跟踪的鲁棒性。具体而言，我们开发了一种基于参数噪声的深度确定性策略梯度（deep deterministic policy gradients, ddpg）的噪声网络实现，可以更好地处理跟踪任务并直接预测跟踪结果。为了提高车辆在快速运动和大变形等复杂条件下的跟踪精度，提出了一种基于上置信度（UCB）算法的车辆时空信息自适应更新策略。此外，对于丢失目标的恢复，提出了一种基于增量学习的定位算法。大量的实验结果表明，与最先进的方法相比，所提出的NoisyOTNet可以有效地跟踪复杂场景中的车辆，并取得具有竞争力的性能。
With the rapid development of intelligent transportation, automated traffic surveillance is considered as an important component. In the field of traffic surveillance, it is particularly important to achieve robust and real-time tracking of vehicles in complex scenes. In this paper, a robust real-time vehicle tracking model named NoisyOTNet is proposed, which formulates tracking as reinforcement learning with parameter space noise. In this formulation, the exploration ability of the model is enhanced to improve the robustness of tracking. Specifically, we develop a new implementation for noisy network based on deep deterministic policy gradients (DDPGs) with parameter noise, which can better cope with the tracking task and directly predict the tracking result. To improve the tracking accuracy in complex conditions, e.g. fast motion and large deformation, this paper presents an adaptive update strategy that can exploit the vehicle spatial-temporal information based on Upper Confidence Bound (UCB) algorithm by exploiting. Moreover, as for the recovery of the lost target, a relocation algorithm based on incremental learning is developed. The results of extensive experiments demonstrate that the proposed NoisyOTNet can effectively track vehicles in complex scenes and achieve competitive performance compared to the state-of-the-art methods.