What does pixel_std for?

[PaTricksStar]

https://github.com/Microsoft/human-pose-estimation.pytorch/blob/c3a30c0e1f83e73b3038b1a443becf6b4a19cf1f/lib/dataset/JointsDataset.py#L31 I review the code and find the pixel_std represents the std of human bbox area, right? But why we need to normalize the bbox scale and set it to 200?

[rafikg]

@PaTricksStar , I have the same question. Also, what about the scale = scale*1.25 in this function

def _xywh2cs(self, x, y, w, h):
        center = np.zeros((2), dtype=np.float32)
        center[0] = x + w * 0.5
        center[1] = y + h * 0.5

        if w > self.aspect_ratio * h:
            h = w * 1.0 / self.aspect_ratio
        elif w < self.aspect_ratio * h:
            w = h * self.aspect_ratio
        scale = np.array(
            [w * 1.0 / self.pixel_std, h * 1.0 / self.pixel_std],
            dtype=np.float32)
        if center[0] != -1:
            scale = scale * 1.25

return center, scale

[wanghao14]

@Gouiaa This also is what confuse me. @leoxiaobin Could you please answer our questions?

[annopackage]

@PaTricksStar @leoxiaobin @wanghao14 @rafikg Have you solved this? I am confused about it.

[PaTricksStar]

I think It is just a hyper parameter representing the default w/h of the bounding box. Just leave it alone. Or you can try to email the author to verify .

[lqduc]

I think it is just a method they store values of bbox h and w. They divide h/w by 200 and then they get the h and w back in get_affine_transform by multiply scale by 200. It just a hyperparam and you could choose another number.

@rafikg As I say above, scale is just another representation of bbox h and w. I think they multiply scale with 1.25 to expand the bbox, in case the bbox fits the human body too much, which lead to information loss.