HoG 特征如何以图形方式表示? [英] How are HoG features represented graphically?

问题描述

我正在实现用于人体检测的定向梯度直方图"中的定向梯度直方图特征，我想将结果可视化.所有关于这些特性的论文都使用标准的可视化，但我找不到任何关于这些特性是如何生成的描述.如果您提供解释或有用的链接，我将不胜感激.

I'm implementing the Histogram of Oriented Gradient features from "Histograms of oriented gradients for human detection" and I'd like to visualise the result. All papers on these features use a standard visualisation, but I can't find any description of how these are generated. I'd be grateful for an explanation or helpful link.

推荐答案

你在论文中看到的可视化可以这样解释:

The visualizations you see in papers can be interpreted as follows:

描述符由网格中覆盖图像窗口的 M*N 个单元组成.每个单元由边缘方向的直方图表示，其中离散化边缘方向的数量是一个参数(通常为 9).细胞直方图通过星"显示直方图中边缘方向的强度:特定方向越强，相对于其他方向的时间越长.

The descriptor is made up of M*N cells covering the image window in a grid. Each cell is represented by a histogram of edge orientations, where the number of discretized edge orientations is a parameter (usually 9). The cell histogram is visualized by a 'star' showing the strength of the edge orientations in the histogram: the stronger a specific orientation, the longer it is relative to the others.

请注意，有多种归一化方案:局部方案，其中单元格仅相对于相邻单元格进行归一化(如 Dalal-Triggs 的原始论文中所述)，或全局方案，其中方向长度由下式归一化所有的细胞.另请注意，一些作者对每个单元格使用多个局部归一化(例如我在下面提到的那个)，但可视化只显示一个(或它们的平均值).

Note that there are various normalization schemes: local schemes, in which the cell in normalized with respect to neighboring cells only (as in the original paper by Dalal-Triggs), or global schemes, in which the orientation length is normalized by all the cells. Also note that some authors use multiple local normalizations per cell (e.g. the one I am referring to below), but visualization only shows one (or an average of them).

Felzenszwalb 等人开创性工作的 Matlab 代码.通过在图像上绘制细胞来可视化细胞，其中强度通过边缘的强度而不是长度来可视化.你可以在他们提供的包中找到它(DPM).查找名为 HOGpicture.m 的函数

The Matlab code for the seminal work by Felzenszwalb et al. visualizes the cells by painting them over an image, where the strength is visualized by the intensity of the edge instead of the length. You can find it in the package they give here (DPM). Look for a function named HOGpicture.m

下面的示例显示了一个自行车模型(来自 Felzenszwalb 等人)，其 HoG 由 7*11 个单元组成，每个单元有 8 个方向

The example below shows a model of a bike (from Felzenszwalb et al.) with HoG consisting of 7*11 cells, each with 8 orientations

这篇关于HoG 特征如何以图形方式表示?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！