• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE Global Conference on Signal and Information Processing >THE CROWD CONGESTION LEVEL - A NEW MEASURE FOR RISK ASSESSMENT IN VIDEO-BASED CROWD MONITORING
【24h】

THE CROWD CONGESTION LEVEL - A NEW MEASURE FOR RISK ASSESSMENT IN VIDEO-BASED CROWD MONITORING

机译：人群拥堵水平 - 基于视频的人群监测中的风险评估的新措施

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose a new characteristic measure relative people density and motion dynamics for the purpose of long-term crowd monitoring. While many related works focus on direct people counting and absolute density estimation, we will show that relative densities provide reliable information on crowd behaviour. Furthermore, we will discuss the derivation of a so-called Congestion Level of local areas in the crowd, which takes the current dynamics and density within a certain image region into account. Our density estimation approach is based on a well-known KLT feature tracking algorithm, combined with a post-processing for motion vector association. The resulting feature tracks (tracklets) represent movements of detected objects in the scene. These trajectories are used as basic features for later estimation of track density and relative inertia (changes in motion dynamics), which together are combined to a joint Congestion Level. We show the results of our approach by comparing the characteristic measures of track density and Congestion Level with manually annotated Ground truth data of both artificial and real scenes.
机译：在本文中，我们提出了一种新的特征测量相对人物密度和运动动力学，以便长期人群监测。虽然许多相关的作品专注于直接人数计数和绝对密度估计，但我们将表明相对密度提供有关人群行为的可靠信息。此外，我们将讨论人群中所谓的本地区域的所谓拥塞水平的推导，这将考虑某些图像区域内的当前动态和密度。我们的密度估计方法基于众所周知的KLT特征跟踪算法，结合运动矢量关联的后处理。得到的特征曲目（Tracklet）表示场景中检测到的对象的移动。这些轨迹用作后来估计轨道密度和相对惯性（运动动态变化）的基本特征，它们在一起与联合拥塞水平组合。我们通过比较了轨道密度和拥塞水平的特征测量与人工和真实场景的手动注释的地面真实数据进行了比较了我们的方法的结果。

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