Motion blur caused by the moving of the object or camera during the exposure can be a key challenge for visual object tracking, affecting tracking accuracy significantly. In this work, we explore the robustness of visual object trackers against motion blur from a new angle, i.e., adversarial blur attack (ABA). Our main objective is to online transfer input frames to their natural motion-blurred counterparts while misleading the state-of-the-art trackers during the tracking process. To this end, we first design the motion blur synthesizing method for visual tracking based on the generation principle of motion blur, considering the motion information and the light accumulation process. With this synthetic method, we propose optimization-based ABA (OP-ABA) by iteratively optimizing an adversarial objective function against the tracking w.r.t. the motion and light accumulation parameters. The OP-ABA is able to produce natural adversarial examples but the iteration can cause heavy time cost, making it unsuitable for attacking real-time trackers. To alleviate this issue, we further propose one-step ABA (OS-ABA) where we design and train a joint adversarial motion and accumulation predictive network (JAMANet) with the guidance of OP-ABA, which is able to efficiently estimate the adversarial motion and accumulation parameters in a one-step way. The experiments on four popular datasets (e.g., OTB100, VOT2018, UAV123, and LaSOT) demonstrate that our methods are able to cause significant accuracy drops on four state-of-the-art trackers with high transferability. Please find the source code at \url{https://github.com/tsingqguo/ABA}.
翻译:在接触过程中,由物体或相机移动引起的运动模糊不清可能是视觉物体跟踪的关键挑战,这极大地影响了跟踪准确性。在这项工作中,我们探索视觉物体跟踪器的稳健性,防止从一个新角度(即对抗性模糊攻击(ABA))运动模糊不清。我们的主要目标是将输入框架在线传输到自然运动模糊的对等方,同时误导跟踪过程中的状态对等方。为此,我们首先设计了运动模糊的视觉跟踪合成方法,该方法基于运动生成原则模糊,考虑到运动信息和光累积过程。在这种合成方法下,我们提议以优化为基础的ABA(OP-ABA)(OP-ABA)为主,通过迭接优化对运动和光累积参数的对抗性目标功能。OP-ABA(O)能够生成自然对抗性实例,但循环会带来沉重的时间成本,因此不适于攻击实时跟踪者。为了缓解这一问题,我们进一步提议在ABA(OS-ABA)一阶梯段(OS-ABA)上,我们设计和训练一个联合的对磁性动作-A(OD-A-A)的动力动力定位和预估测测测能的轨道)网络,可以找到一个高的轨道-AUAL-A(OD-A-A-ROGIL-A-L-IL-L-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I)的动力的动力的动力的动力的动力的动力的动力的动力的动力的动力的动力的动力的动力的动力的模型,在四种方法可以找到到一个在4的动力观测到高的动力观测-I-I-L-IL-IL-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-L-L-L-L-I-IL-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-I-L-I-I-I-I-I-I-I-I-I-I-I