Visual tracking is a vital component of autonomous driving perception system. Siamese networks have achieved great success in both accuracy and speed for visual tracking tasks. These Siamese trackers share a similar framework in which each tracker consists of two network branches for exploring semantic information. However, the performance of Siamese trackers is limited by an insufficient semantic template and an unsatisfactory updating strategy. To tackle these problems, we propose a manifold Siamese network for visual tracking that can simultaneously utilize semantic and geometric information. A manifold sample pool is constructed to exploit the manifold structure of image object sequences. This sample pool is dynamically learned via a fast Gaussian mixture model (GMM). After obtaining a manifold sample template, we design a deep architecture based on a correlation filter (CF) network and append a novel manifold feature branch. The network remains fully convolutional and can train a template to discriminate exemplar image and arbitrarily size search image. Then, a triplet occlusion score function cooperates with an effective update method that is established to prevent model drift. Extensive experiments show that the proposed tracking algorithm performs favorably compared with the state-of-the-art methods on three standard benchmark datasets at a high framerate, which is very suitable for autonomous driving.

中文翻译：

---

流形连体网络：一种用于自动驾驶汽车的新型视觉跟踪卷积网络

视觉跟踪是自动驾驶感知系统的重要组成部分。Siamese 网络在视觉跟踪任务的准确性和速度方面都取得了巨大的成功。这些 Siamese 跟踪器共享一个类似的框架，其中每个跟踪器由两个网络分支组成，用于探索语义信息。然而，Siamese 跟踪器的性能受到语义模板不足和更新策略不理想的限制。为了解决这些问题，我们提出了一种用于视觉跟踪的流形连体网络，可以同时利用语义和几何信息。构造一个流形样本池以利用图​​像对象序列的流形结构。该样本池是通过快速高斯混合模型 (GMM) 动态学习的。获得流形样本模板后，我们设计了一个基于相关滤波器 (CF) 网络的深度架构，并附加了一个新的流形特征分支。网络保持完全卷积，可以训练模板来区分示例图像和任意大小的搜索图像。然后，三元组遮挡评分函数与建立的有效更新方法相配合，以防止模型漂移。大量实验表明，所提出的跟踪算法在高帧率的三个标准基准数据集上与最先进的方法相比表现良好，非常适合自动驾驶。三元组遮挡评分函数与有效的更新方法相配合，该方法可以防止模型漂移。大量实验表明，所提出的跟踪算法在高帧率的三个标准基准数据集上与最先进的方法相比表现良好，非常适合自动驾驶。三元组遮挡得分函数与建立的有效更新方法相配合，以防止模型漂移。大量实验表明，所提出的跟踪算法在高帧率的三个标准基准数据集上与最先进的方法相比表现良好，非常适合自动驾驶。