Object Occupancy Probabilistic Field Based Multi-view Moving Object Detection and Correspondence
-
摘要: 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.Abstract: A novel algorithm to detect objects across multiple views at the same instance is proposed based on object probabilistic 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 fusion 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.
-
Key words:
- Object detection /
- object correspondence /
- multi-view /
- occupancy probability
点击查看大图
计量
- 文章访问数: 2264
- HTML全文浏览量: 56
- PDF下载量: 1684
- 被引次数: 0