OpenCV HOGDescriptor return 值
OpenCV HOGDescriptor return value
为什么 HOG 描述符 return 是 float 而不是 int 的向量？假设 return 一个直方图..
我相信@Micka 是对的：直方图可能已标准化（可能不是 1）。在Wikipedia page on HOG Descriptors上写着：
For improved accuracy, the local histograms can be contrast-normalized by calculating a measure of the intensity across a larger region of the image, called a block, and then using this value to normalize all cells within the block. This normalization results in better invariance to changes in illumination and shadowing.
因此需要 vector<float> 而不是 vector<int>。
为了补充我认为正确的先前答案，根据这个HoG note I found clearer than the initial Dalal & Triggs paper，涉及两个规范化步骤：
- 块规范化
Group the cells into overlapping blocks of 2 x 2 cells each, so that
each block has size 2C x 2C pixels. Two horizontally or vertically
consecutive blocks overlap by two cells, that is, the block stride is
C pixels. As a consequence, each internal cell is covered by four
blocks. Concatenate the four cell histograms in each block into a
single block feature b and normalize the block feature by its
Euclidean norm.
- HOG 特征归一化
The final normalization makes the HOG feature independent of overall
image contrast.
两个连续的 bin 之间也应该有双线性插值投票，以防止量化伪影。
此外，它不能是 int，因为您不仅要计算落入 bin 的梯度向量的数量，还要加上梯度幅度。
为什么 HOG 描述符 return 是 float 而不是 int 的向量？假设 return 一个直方图..
我相信@Micka 是对的：直方图可能已标准化（可能不是 1）。在Wikipedia page on HOG Descriptors上写着：
For improved accuracy, the local histograms can be contrast-normalized by calculating a measure of the intensity across a larger region of the image, called a block, and then using this value to normalize all cells within the block. This normalization results in better invariance to changes in illumination and shadowing.
因此需要 vector<float> 而不是 vector<int>。
为了补充我认为正确的先前答案，根据这个HoG note I found clearer than the initial Dalal & Triggs paper，涉及两个规范化步骤：
- 块规范化
Group the cells into overlapping blocks of 2 x 2 cells each, so that each block has size 2C x 2C pixels. Two horizontally or vertically consecutive blocks overlap by two cells, that is, the block stride is C pixels. As a consequence, each internal cell is covered by four blocks. Concatenate the four cell histograms in each block into a single block feature b and normalize the block feature by its Euclidean norm.
- HOG 特征归一化
The final normalization makes the HOG feature independent of overall image contrast.
两个连续的 bin 之间也应该有双线性插值投票，以防止量化伪影。
此外，它不能是 int，因为您不仅要计算落入 bin 的梯度向量的数量，还要加上梯度幅度。