Tracking-Learning-Detection
Tracking-Learning-Detection
复制标题
DOI：
10.1109/tpami.2011.239
复制
发表时间：
2012-07-01
影响因子：
23.6
通讯作者：
Matas, Jiri
中科院分区：
文献类型：
--
作者：
Kalal, Zdenek;Mikolajczyk, Krystian;Matas, Jiri
本文研究了视频流中未知对象的长期跟踪问题。对象由其在单个帧中的位置和范围定义。在接下来的每一帧中，任务是确定对象的位置和范围，或者指示对象不存在。我们提出了一种新的跟踪框架（STIM），明确地将长期跟踪任务分解为跟踪，学习和检测。跟踪器从一帧到另一帧跟踪对象。探测器定位到目前为止已经观察到的所有外观，并在必要时校正跟踪器。学习估计检测器的错误并更新它以避免将来出现这些错误。我们研究了如何识别检测器的错误并从中学习。我们开发了一种新的学习方法（P-N学习），它通过一对“专家”来估计错误：1）P-expert估计漏检测，2）N-expert估计虚警。学习过程被建模为一个离散的动态系统和条件下，学习保证improved. We描述了我们的实时实现的框架和P-N学习。我们进行了广泛的定量评估，显示出显着的改善，国家的最先进的方法。
This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object's location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detector's errors and updates it to avoid these errors in the future. We study how to identify the detector's errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of "experts": 1) P-expert estimates missed detections, and 2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the conditions under which the learning guarantees improvement are found. We describe our real-time implementation of the TLD framework and the P-N learning. We carry out an extensive quantitative evaluation which shows a significant improvement over state-of-the-art approaches.