Hough Forests for Object Detection, Tracking, and Action Recognition
Hough Forests for Object Detection, Tracking, and Action Recognition
复制标题
DOI：
10.1109/tpami.2011.70
复制
发表时间：
2011-11-01
影响因子：
23.6
通讯作者：
Lempitsky, Victor
中科院分区：
文献类型：
--
作者：
Gall, Juergen;Yao, Angela;Lempitsky, Victor
本文介绍了Hough森林，这是随机森林适应执行广义Hough变换在一个有效的方式。与以前的基于Hough的系统（如隐式形状模型）相比，Hough森林提高了广义Hough变换在分类级别上进行对象检测的性能。同时，它们的灵活性允许将Hough变换扩展到新的领域，例如对象跟踪和动作识别。霍夫森林可以被视为本地外观的任务适应码本，允许在测试时进行快速监督训练和快速匹配。它们实现了高检测精度，因为这样的码本的条目被优化以投下具有小方差的Hough投票，并且因为它们的效率允许在检测期间对局部图像块或视频长方体进行密集采样。Hough森林对一组计算机视觉任务的有效性通过对大量公开可用的基准数据集进行实验并与最先进的进行比较来验证。
The paper introduces Hough forests, which are random forests adapted to perform a generalized Hough transform in an efficient way. Compared to previous Hough-based systems such as implicit shape models, Hough forests improve the performance of the generalized Hough transform for object detection on a categorical level. At the same time, their flexibility permits extensions of the Hough transform to new domains such as object tracking and action recognition. Hough forests can be regarded as task-adapted codebooks of local appearance that allow fast supervised training and fast matching at test time. They achieve high detection accuracy since the entries of such codebooks are optimized to cast Hough votes with small variance and since their efficiency permits dense sampling of local image patches or video cuboids during detection. The efficacy of Hough forests for a set of computer vision tasks is validated through experiments on a large set of publicly available benchmark data sets and comparisons with the state-of-the-art.