基于目标存在概率场的多视角运动目标检测与对应算法

提出了一种多视角运动目标检测与对应算法---基于目标存在概率场的运动目标检测和对应算法. 目标存在概率场是算法的核心, 其融合各视角的信息, 并依据融合结果在空间中检测目标. 目标窗结构是快速计算目标存在概率场的关键, 并给出了一种同时实现目标检测和对应的框架. 实验结果表明该算法具有遮挡处理能力强, 计算复杂度低的优点.

Object Occupancy Probabilistic Field Based Multi-view Moving Object Detection and Correspondence

A novel algorithm to detect objects across multiple views at the same instance is proposed based on object proba- bilistic random field(OOPF).OOPF is the core of our algorithm and it integrates all the information of individual views into the fusion space.Then object detection is implemented in the fu- sion space.An object window structure is designed in order to compute OOPF fast,which also provides a scheme to detect objects and the correspondence simultaneously.The experiment results demonstrate that the algorithm has a better performance against occlusion while the computational complexity is low.