Abstract:

In the target tracking algorithm, the feature model’s ability to quickly learn image features and the ability to adapt to changes in target features during tracking has always been one of the main research directions of target tracking algorithms. Especially for discriminative target trackers based on image block learning, these two points have become decisive factors affecting the efficiency and robustness of the tracker. However, the performance of most existing similar algorithms on these two abilities cannot achieve satisfactory results. To solve this problem, an efficient and robust feature model is proposed. The feature model first uses extreme learning machine autoencoder (ELM-AE) to quickly perform random feature mapping on complex image features of the target and background image blocks, and then uses the transfer learning ability of transfer representation learning (TRL) to improve the adaptability of random feature space. The feature model is named transfer representation learning with ELM-AE (TRL-ELM-AE). Compared with original complex image features, this model can provide the classifier with more compact and expressive shared features, so that the classifier can learn and classify more quickly and efficiently. In addition, in the target tracking process, the target and background usually change continuously over time. Although the feature migration capability of TRL can already adapt to this, in order to further improve the robustness of the tracker, a strategy of dynamically updating training samples is adopted. Through a large number of experimental and analysis results on the 11 target tracking challenge scenarios proposed by OTB, it is proven that the proposed target tracker has significant advantages over the existing target tracker.

Key words: extreme learning machine (ELM), extreme learning machine autoencoder (ELM-AE), transfer represen-tation learning (TRL), feature adaptation, Gaussian naive Bayes classifier (GNBC), object tracking

摘要：

在目标跟踪算法中,特征模型对图像特征的快速学习能力和对跟踪过程中目标特征变化的自适应能力一直是目标跟踪算法的主要研究方向之一。特别是对于基于图像块学习的判别式目标跟踪器而言,这两点已然成为影响跟踪器效率和鲁棒性的决定性因素。然而,现有的大多数同类算法在这两个能力上的性能并不能达到令人满意的效果。为了解决这一问题,提出了一种高效且鲁棒的特征模型。该特征模型首先利用基于极限学习机的自编码器（ELM-AE）对目标和背景图像块的复杂图像特征快速地进行随机特征映射,再利用迁移表征学习（TRL）的迁移学习能力提高随机特征空间的自适应性。将该特征模型命名为基于ELM自编码器和迁移表征学习的特征模型（TRL-ELM-AE）。与原复杂图像特征相比,通过该模型可以获得更加紧凑且具有表达能力的共享特征。从而使得分类器可以快速高效地学习和分类。此外,在目标跟踪过程中,目标与背景通常会随着时间不停地变化。虽然TRL的特征迁移能力已经可以很好地适应这一点,但是为了进一步提高跟踪器的鲁棒性,还采用了一种动态更新训练样本的策略。通过对OTB提出的11项目标跟踪挑战场景进行大量实验和分析,证明了所提的目标跟踪器较现有的目标跟踪器具有显著优势。

关键词: 极限学习机（ELM）, 极限学习机自编码器（ELM-AE）, 迁移表征学习（TRL）, 特征自适应, 高斯朴素贝叶斯分类器（GNBC）, 目标跟踪