arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.10211cs.LGstat.ML
收藏

基于加权在线极限学习机的鲁棒跟踪

Robust Tracking via Weighted Online Extreme Learning Machine

Liaoning Normal University(辽宁师范大学);Dalian Maritime University(大连海事大学)

Jing Zhang, Huibing Wang, Yonggong Ren

摘要:

基于极限学习机的跟踪方法是一种高效、有效的方法。ELM在隐层中随机生成输入权值和偏置,然后通过将迭代求解简化为线性方程组问题来计算和计算输出权值。因此,ELM在跟踪中具有令人满意的分类性能和快速的训练时间。然而,原有的ELM方法存在分类分布不均衡的问题,目标对象少导致欠拟合,背景样本多导致过拟合。更糟糕的是,它降低了跟踪的鲁棒性在特殊条件下,包括遮挡,照明等,为了解决上述问题,在本文中,我们提出了一个强大的跟踪算法。首先,在原ELM中引入局部权重矩阵,即根据当前帧的数据分布动态生成局部权重矩阵,以平衡经验风险和结构风险,充分学习目标对象,提高分类性能。其次,我们将其改进为增量学习方法,保证跟踪的实时性和高效性。最后,利用遗忘因子增强了分类分布随时间变化的鲁棒性。同时,我们提出了一种新的优化方法,以获得最佳的样本作为目标对象,这避免了跟踪漂移所造成的噪声样本。因此,我们的跟踪方法可以充分学习目标对象和背景信息,以提高跟踪性能,并在20个具有不同属性(包括光照,遮挡,变形等)的挑战图像序列中进行评估,其在有效性和鲁棒性方面实现了比几种现有技术方法更好的性能。

英文摘要:

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative solution to the problem of linear equations. Therefore, ELM offers the satisfying classification performance and fast training time than other discriminative models in tracking. However, the original ELM method often suffers from the problem of the imbalanced classification distribution, which is caused by few target objects, leading to under-fitting and more background samples leading to over-fitting. Worse still, it reduces the robustness of tracking under special conditions including occlusion, illumination, etc. To address above problems, in this paper, we present a robust tracking algorithm. First, we introduce the local weight matrix that is the dynamic creation from the data distribution at the current frame in the original ELM so as to balance between the empirical and structure risk, and fully learn the target object to enhance the classification performance. Second, we improve it to the incremental learning method ensuring tracking real-time and efficient. Finally, the forgetting factor is used to strengthen the robustness for changing of the classification distribution with time. Meanwhile, we propose a novel optimized method to obtain the optimal sample as the target object, which avoids tracking drift resulting from noisy samples. Therefore, our tracking method can fully learn both of the target object and background information to enhance the tracking performance, and it is evaluated in 20 challenge image sequences with different attributes including illumination, occlusion, deformation, etc., which achieves better performance than several state-of-the-art methods in terms of effectiveness and robustness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑