Object Tracking Algorithm Based on and L2-regularization Least Square and Convolutional Networks
首发时间:2018-04-16
Abstract:Object tracking is a hot and difficult research topic in computer vision. In this paper, we propose a object tracking algorithm based on L2 regularization least squares method and convolution network under the particle filter framework. Firstly, the extent of occlusion can be evaluated by L2 tracker. Secondly, convolutional networks is used to locate the target object if the extent of occlusion satisfies two inequality constraints. In order to make convolutional networks suitable for tracking tasks with high real-time requirements, this thesis uses a simple two-layer convolutional networks to represent the targets robustly. Finally, most of the insignificant samples are removed before applying convolutional networks, which reduces the complexity of the algorithm. The experimental results on numerous challenging image sequences show that the proposed method is more robust and stable than L2 tracker when the target object undergoes dramatic appearance changes such as pose variation or rotation and is superior in accuracy to other classical tracking algorithms.
keywords: Object tracking Particle filter L2-regularization Convolution network
点击查看论文中文信息
基于L2正则化最小二乘法与卷机网络的目标跟踪算法
摘要:目标跟踪是计算机视觉领域中的一个热门而又困难的研究课题,本文在粒子滤波框架下提出基于L2正则化最小二乘法和卷机网络的目标跟踪算法。首先,每一帧的遮挡率由L2跟踪算法来评估;其次,如果遮挡率满足两个不等式约束,则用卷机网络来对跟踪目标进行修正。为了使卷机网络适用于实时性较高的跟踪任务,本文采用简单的两层卷积网络来对目标进行稳健性表示。最后,在应用卷机网络求取样本的特征图时,大部分不重要的样本被去除,这使得算法的复杂度降低。在许多具有挑战性的测试视频上的测试结果表明,当目标发生旋转或姿态变化等剧烈的外观变化时,所提出的算法比L2跟踪算法鲁棒性更强,并且在精度方面优于其他经典跟踪算法。
引用
No.****
同行评议
共计0人参与
勘误表
基于L2正则化最小二乘法与卷机网络的目标跟踪算法
评论
全部评论0/1000