论文信息 - Online multicamera tracking with a switching state-space model

Online multicamera tracking with a switching state-space model

The paper presents a novel method for online tracking of multiple objects with non-overlapping cameras. The method is based on a generative model defining probabilistic dependencies between observations, the underlying color properties of objects and their dynamics. It allows for a full Bayesian inference of trajectories. We developed an online algorithm for efficient, approximate inference and we demonstrate it to be accurate in an office environment.

[1] Stuart J. Russell,et al. Dynamic bayesian networks: representation, inference and learning , 2002 .

[2] Yaakov Bar-Shalom,et al. Estimation and Tracking: Principles, Techniques, and Software , 1993 .

[3] B. Kröse,et al. A Hybrid Graphical Model for Online Multi-camera Tracking , 2022 .

[4] Xavier Boyen,et al. Tractable Inference for Complex Stochastic Processes , 1998, UAI.

[5] Yaacov Ritov,et al. Tracking Many Objects with Many Sensors , 1999, IJCAI.

[6] Thomas M. Cover,et al. Elements of Information Theory , 2005 .

[7] Takeo Kanade,et al. Algorithms for cooperative multisensor surveillance , 2001, Proc. IEEE.

[8] David B. Dunson,et al. Bayesian Data Analysis , 2010 .

[9] Stuart J. Russell,et al. Object Identification: A Bayesian Analysis with Application to Traffic Surveillance , 1998, Artif. Intell..

[10] Jie Wei,et al. Illumination-invariant color object recognition via compressed chromaticity histograms of color-channel-normalized images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).