Pedestrian detection in crowded scenes
Pedestrian detection in crowded scenes
复制标题
DOI：
10.1109/cvpr.2005.272
复制
发表时间：
2005-06
期刊：
影响因子：
--
通讯作者：
B. Leibe;Edgar Seemann;B. Schiele
中科院分区：
文献类型：
--
作者：
B. Leibe;Edgar Seemann;B. Schiele
在本文中，我们研究了在拥挤的真实场景中检测严重重叠的行人的问题。我们的基本前提是，这个问题对于任何类型的模型或功能来说都太难了。相反，我们提出了一种算法，该算法在多次迭代中整合了来自不同来源的证据。我们方法的核心部分是通过概率自顶向下分割来结合局部和全局线索。总而言之，这种方法允许以高精度检查和比较对象假设，精确到像素级别。在大量数据集上的定性和定量结果证实，我们的方法能够可靠地检测出拥挤场景中的行人，即使他们相互重叠和部分遮挡。此外，我们方法的灵活性使其能够在非常小的训练集上运行。
In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any type of model or feature alone. Instead, we present an algorithm that integrates evidence in multiple iterations and from different sources. The core part of our method is the combination of local and global cues via probabilistic top-down segmentation. Altogether, this approach allows examining and comparing object hypotheses with high precision down to the pixel level. Qualitative and quantitative results on a large data set confirm that our method is able to reliably detect pedestrians in crowded scenes, even when they overlap and partially occlude each other. In addition, the flexible nature of our approach allows it to operate on very small training sets.