【24h】

Multi-object Tracking with Pre-classified Detection

机译:具有预分类检测的多对象跟踪

获取原文

摘要

Tracking-by-detection is a popular tracking framework nowadays. The paradigm determines that detections will bring huge impact on the final tracking result. Based on the idea, to improve the tracking precision, we propose a novel algorithm which will first divide the detections into false ones, high uncertainty and low uncertainty ones. After that, we first penalize the false detection boundingboxes and then we construct low and high uncertainty tree for different types of detections. For low uncertainty detections, we construct their tracking trees once, for high uncertainty detections, we adopt an improved MHT to delay the data association decision till the end of the sliding windows and make the decision with all the information in the sliding window. Experiments demonstrate that our algorithm can achieved competitive results with state-of-the-art trackers on some challenging datasets such as MOTChallenge2016 [11].
机译:逐个检测现在是一个流行的跟踪框架。 范例确定检测将对最终跟踪结果带来巨大影响。 基于该思想,为了提高跟踪精度,我们提出了一种新颖的算法,首先将检测分为错误的算法,高不确定性和低不确定性。 之后,我们首先惩罚假检测边界箱,然后为不同类型的检测构建低和高不确定性树。 对于低不确定性检测,我们构建其跟踪树一次,对于高不确定性检测,我们采用改进的MHT来延迟数据关联决策直到滑动窗口的末端,并在滑动窗口中的所有信息做出决定。 实验表明,我们的算法可以在一些具有挑战性的数据集上实现竞争结果,如Motchallene2016 [11]。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号