Long-term Correlation Tracking using Multi-layer Hybrid Features in Dense Environments
Long-term Correlation Tracking using Multi-layer Hybrid Features in Dense Environments
复制标题
DOI：
10.5220/0006117301920203
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Nathanael L. Baisa;Deepayan Bhowmik;A. Wallace
中科院分区：
文献类型：
--
作者：
Nathanael L. Baisa;Deepayan Bhowmik;A. Wallace
在拥挤的环境中跟踪感兴趣的目标是一个具有挑战性的问题，在文献中尚未成功解决。在本文中，我们提出了一种新的长期算法，即学习判别相关滤波器并使用在线分类器来跟踪密集视频序列中的感兴趣目标。首先，我们使用卷积神经网络(CNN)和传统手工特征的多层混合来学习平移相关滤波器。我们结合了较低的卷积层和较高的卷积层的优点，前者保留了更好的空间细节用于精确定位，后者编码了用于处理外观变化的语义信息。这与由定向梯度直方图(HOG)和颜色命名形成的传统特征相结合。其次，我们包括一个重新检测模块，用于通过使用手工设计的特征在最有信心的帧上训练增量(在线)支持向量机来克服长期遮挡导致的跟踪失败。仅当对象的相关响应低于某个预定义阈值时才激活该重新检测模块，以生成高分数检测建议。最后，结合高斯混合概率假设密度(GM-PHD)滤波器对学习的在线支持向量机产生的高分检测方案进行时间过滤，通过去除杂波，找到权值最大的检测方案作为目标位置估计。在密集数据集上的大量实验表明，我们的方法明显优于最先进的方法。
Tracking a target of interest in crowded environments is a challenging problem, not yet successfully addressed in the literature. In this paper, we propose a new long-term algorithm, learning a discriminative correlation filter and using an online classifier, to track a target of interest in dense video sequences. First, we learn a translational correlation filter using a multi-layer hybrid of convolutional neural networks (CNN) and traditional hand-crafted features. We combine the advantages of both the lower convolutional layer which retains better spatial detail for precise localization, and the higher convolutional layer which encodes semantic information for handling appearance variations. This is integrated with traditional features formed from a histogram of oriented gradients (HOG) and color-naming. Second, we include a re-detection module for overcoming tracking failures due to long-term occlusions by training an incremental (online) SVM on the most confident frames using hand-engineered features. This re-detection module is activated only when the correlation response of the object is below some pre-defined threshold to generate high score detection proposals. Finally, we incorporate a Gaussian mixture probability hypothesis density (GM-PHD) filter to temporally filter high score detection proposals generated from the learned online SVM to find the detection proposal with the maximum weight as the target position estimate by removing the other detection proposals as clutter. Extensive experiments on dense data sets show that our method significantly outperforms state-of-the-art methods.