基于多重检测的无人机抗遮挡目标跟踪算法

Anti-occlusion target tracking algorithm of UAV based on multiple detection

针对无人机(UAV)目标跟踪过程中遇到目标被障碍物遮挡时跟踪效果不佳的问题,提出一种多重检测的抗遮挡目标跟踪算法。在基于时空正则化相关滤波算法的框架下通过融合多种置信度函数,设计了一种响应置信度判别方法;为了具体了解目标被遮挡情况,将响应差值变化和响应梯度变化结合在一起作为判断是否更新滤波模板参数的依据;设计了一种融合分块思想与金字塔尺度池的尺度估计方法来解决目标在图像中尺度大小变化问题。所提算法在UAV数据集上相较于其他7种算法有不错的表现,在跟踪过程中面对目标遮挡、尺度变化和快速移动问题的跟踪精度和成功率上都有明显的提升。结果表明:所提算法能够更好地应对UAV在目标跟踪过程中出现的目标遮挡和尺度变化的问题,具有良好的快速性、准确性和鲁棒性。

In this research,a multi-detection anti-occlusion target tracking method is suggested to address the issue of poor tracking effect when unmanned aerial vehicle(UAV)targets are occluded by obstacles during the target tracking process.A response confidence discrimination method is designed by fusing various confidence functions under the framework of a spatiotemporal regularization correlation filtering algorithm.In order to understand the occlusion situation,the change of response difference and response gradient are combined together as the basis to judge whether to update the filter template parameters.A scale estimation method combining the block idea and pyramid scale pool is designed to solve the problem of the scale variation of the target in the image.Compared with the other seven algorithms,the proposed algorithm performs well in the UAV data set,and significantly improves the tracking accuracy and success rate in the face of target occlusion,scale change,and fast movement problems in the tracking process.The findings demonstrate that the multi-detection-based anti-occlusion target tracking algorithm has good speed,accuracy,and robustness and can more effectively address the issues of target occlusion and dimension change in the process of UAV target tracking.