Pattern Recognition
Pattern Recognition
复制标题
DOI：
10.1007/978-3-0348-5495-5_8
复制
发表时间：
2015
期刊：
影响因子：
3.9
通讯作者：
Lorenzo Vaquero;V. Brea;M. Mucientes
中科院分区：
文献类型：
--
作者：
Lorenzo Vaquero;V. Brea;M. Mucientes
在实时视频中保持多个对象的身份是一项具有挑战性的任务，因为在每一帧上运行检测器并不总是可行的。因此，经常使用运动估计系统，这些系统要么不能很好地随目标数量的增加而扩展，要么产生语义信息有限的特征。为了解决上述问题，并允许实时跟踪数十个任意对象，我们提出了SiamMOTION。SiamMOTION包括一个新颖的提议引擎，通过一个注意力机制和一个由惯性模块提供的兴趣区域提取器产生高质量的特征，并由一个特征金字塔网络提供动力。最后，提取的张量进入一个比较头，该比较头有效地匹配成对的样本和搜索区域，通过成对深度区域建议网络和多目标惩罚模块生成高质量的预测。SiamMOTION已在五个公共基准测试中得到验证，与目前最先进的跟踪器相比，实现了领先的性能。代码可在:https://www.github.com/lorenzovaquero/SiamMOTION
Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always feasible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with the number of targets or produce features with limited semantic information. To solve the aforementioned problems and allow the tracking of dozens of arbitrary objects in real-time, we propose SiamMOTION. SiamMOTION includes a novel proposal engine that produces quality features through an attention mechanism and a region-of-interest extractor fed by an inertia module and powered by a feature pyramid network. Finally, the extracted tensors enter a comparison head that efficiently matches pairs of exemplars and search areas, generating quality predictions via a pairwise depthwise region proposal network and a multi-object penalization module. SiamMOTION has been validated on five public benchmarks, achieving leading performance against current state-of-the-art trackers. Code available at: https://www.github.com/lorenzovaquero/SiamMOTION