tailieunhanh - Báo cáo toán học: " Real-time reliability measure-driven multihypothesis tracking using 2D and 3D features"

Tuyển tập các báo cáo nghiên cứu khoa học ngành toán học được đăng trên tạp chí toán học quốc tế đề tài: Real-time reliability measure-driven multihypothesis tracking using 2D and 3D features | Zuniga et al. EURASIP Journal on Advances in Signal Processing 2011 2011 142 http content 2011 1 142 o EURASIP Journal on Advances in Signal Processing a SpringerOpen Journal RESEARCH Open Access Real-time reliability measure-driven multihypothesis tracking using 2D and 3D features Marcos D Zuniga1 Frangois Brémond2 and Monique Thonnat2 Abstract We propose a new multi-target tracking approach which is able to reliably track multiple objects even with poor segmentation results due to noisy environments. The approach takes advantage of a new dual object model combining 2D and 3D features through reliability measures. In order to obtain these 3D features a new classifier associates an object class label to each moving region . person vehicle a parallelepiped model and visual reliability measures of its attributes. These reliability measures allow to properly weight the contribution of noisy erroneous or false data in order to better maintain the integrity of the object dynamics model. Then a new multitarget tracking algorithm uses these object descriptions to generate tracking hypotheses about the objects moving in the scene. This tracking approach is able to manage many-to-many visual target correspondences. For achieving this characteristic the algorithm takes advantage of 3D models for merging dissociated visual evidence moving regions potentially corresponding to the same real object according to previously obtained information. The tracking approach has been validated using video surveillance benchmarks publicly accessible. The obtained performance is real time and the results are competitive compared with other tracking algorithms with minimal or null reconfiguration effort between different videos. Keywords multi-hypothesis tracking reliability measures object models 1 Introduction Multi-target tracking is one of the most challenging problems in the domain of computer vision. It can be utilised in interesting applications with high .