Bayesian Tracking of Video Graphs Using Joint Kalman Smoothing and Registration
Bayesian Tracking of Video Graphs Using Joint Kalman Smoothing and Registration
复制标题
DOI：
10.1007/978-3-031-19833-5_26
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
A. Bal;R. Mounir;Sathyanarayanan N. Aakur;Sudeep Sarkar;Anuj Srivastava
中科院分区：
文献类型：
--
作者：
A. Bal;R. Mounir;Sathyanarayanan N. Aakur;Sudeep Sarkar;Anuj Srivastava
基于图的表示在表示和分析视频数据方面变得越来越流行，特别是在对象跟踪和场景理解应用中。因此，这种方法中的一个重要工具是为与视频相关联的图形时间序列生成统计推断。本文提出了一种卡尔曼平滑方法，用于从噪声、杂乱和不完整的数据中估计图形。这里的主要挑战是，当数据由于错误和缺失节点而具有噪声和杂波时，在时间帧上找到并保留节点（显着检测到的对象）的注册。首先，我们引入了一个虚拟空间表示的图形，结合时间登记的节点，我们使用的度量结构施加一个动态模型图的演变。然后，我们推导出一个卡尔曼平滑，适应商空间几何，估计密集，光滑的轨迹图。我们使用模拟数据和从多视图扩展视频与活动（MEVA）数据集提取的实际视频图形来演示这个框架。该框架成功地估计了图，尽管噪声，杂波和错过的检测。
Graph-based representations are becoming increasingly popular for representing and analyzing video data, especially in object tracking and scene understanding applications. Accordingly, an essential tool in this approach is to generate statistical inferences for graphical time series associated with videos. This paper develops a Kalman-smoothing method for estimating graphs from noisy, cluttered, and incomplete data. The main challenge here is to find and preserve the registration of nodes (salient detected objects) across time frames when the data has noise and clutter due to false and missing nodes. First, we introduce a quotient-space representation of graphs that incorporates temporal registration of nodes, and we use that metric structure to impose a dynamical model on graph evolution. Then, we derive a Kalman smoother, adapted to the quotient space geometry, to estimate dense, smooth trajectories of graphs. We demonstrate this framework using simulated data and actual video graphs extracted from the Multiview Extended Video with Activities (MEVA) dataset. This framework successfully estimates graphs despite the noise, clutter, and missed detections.