thirdparty/HaWoR/lib/utils/imutils.py

"""
This file contains functions that are used to perform data augmentation.
"""
import torch
import numpy as np
from skimage.transform import rotate, resize
import cv2
from torchvision.transforms import Normalize, ToTensor, Compose

from lib.core import constants

def get_normalization():
    normalize_img = Compose([ToTensor(),
                            Normalize(mean=constants.IMG_NORM_MEAN, 
                                      std=constants.IMG_NORM_STD)
                            ])
    return normalize_img

def get_transform(center, scale, res, rot=0):
    """Generate transformation matrix."""
    h = 200 * scale + 1e-6
    t = np.zeros((3, 3))
    t[0, 0] = float(res[1]) / h
    t[1, 1] = float(res[0]) / h
    t[0, 2] = res[1] * (-float(center[0]) / h + .5)
    t[1, 2] = res[0] * (-float(center[1]) / h + .5)
    t[2, 2] = 1
    if not rot == 0:
        rot = -rot # To match direction of rotation from cropping
        rot_mat = np.zeros((3,3))
        rot_rad = rot * np.pi / 180
        sn,cs = np.sin(rot_rad), np.cos(rot_rad)
        rot_mat[0,:2] = [cs, -sn]
        rot_mat[1,:2] = [sn, cs]
        rot_mat[2,2] = 1
        # Need to rotate around center
        t_mat = np.eye(3)
        t_mat[0,2] = -res[1]/2
        t_mat[1,2] = -res[0]/2
        t_inv = t_mat.copy()
        t_inv[:2,2] *= -1
        t = np.dot(t_inv,np.dot(rot_mat,np.dot(t_mat,t)))
    return t

def transform(pt, center, scale, res, invert=0, rot=0, asint=True):
    """Transform pixel location to different reference."""
    t = get_transform(center, scale, res, rot=rot)
    if invert:
        t = np.linalg.inv(t)
    new_pt = np.array([pt[0]-1, pt[1]-1, 1.]).T
    new_pt = np.dot(t, new_pt)

    if asint:
        return new_pt[:2].astype(int)+1
    else:
        return new_pt[:2]+1

def transform_pts(pts, center, scale, res, invert=0, rot=0, asint=True):
    """Transform pixel location to different reference."""
    t = get_transform(center, scale, res, rot=rot)
    if invert:
        t = np.linalg.inv(t)
    pts = np.concatenate((pts, np.ones_like(pts)[:, [0]]), axis=-1)
    new_pt = pts.T
    new_pt = np.dot(t, new_pt)

    if asint:
        return new_pt[:2, :].T.astype(int)
    else:
        return new_pt[:2, :].T

def crop(img, center, scale, res, rot=0):
    """Crop image according to the supplied bounding box."""
    # Upper left point
    ul = np.array(transform([1, 1], center, scale, res, invert=1))-1
    # Bottom right point
    br = np.array(transform([res[0]+1, 
                             res[1]+1], center, scale, res, invert=1))-1

    # Padding so that when rotated proper amount of context is included
    pad = int(np.linalg.norm(br - ul) / 2 - float(br[1] - ul[1]) / 2)
    if not rot == 0:
        ul -= pad
        br += pad

    new_shape = [br[1] - ul[1], br[0] - ul[0]]
    if len(img.shape) > 2:
        new_shape += [img.shape[2]]
    new_img = np.zeros(new_shape)
    

    # Range to fill new array
    new_x = max(0, -ul[0]), min(br[0], len(img[0])) - ul[0]
    new_y = max(0, -ul[1]), min(br[1], len(img)) - ul[1]
    # Range to sample from original image
    old_x = max(0, ul[0]), min(len(img[0]), br[0])
    old_y = max(0, ul[1]), min(len(img), br[1])
    try:
        new_img[new_y[0]:new_y[1], new_x[0]:new_x[1]] = img[old_y[0]:old_y[1], 
                                                        old_x[0]:old_x[1]]
    except:
        print("invlid bbox, fill with 0")

    if not rot == 0:
        # Remove padding
        new_img = rotate(new_img, rot)
        new_img = new_img[pad:-pad, pad:-pad]

    new_img = resize(new_img, res)
    return new_img

def crop_j2d(j2d, center, scale, res, rot=0):
    """Crop image according to the supplied bounding box."""
    # Upper left point
    # crop_j2d = np.array(transform_pts(j2d, center, scale, res, invert=0))
    b = scale * 200
    points2d = j2d - (center - b/2)
    points2d = points2d * (res[0] / b)
    
    return points2d


def crop_crop(img, center, scale, res, rot=0):
    """Crop image according to the supplied bounding box."""
    # Upper left point
    ul = np.array(transform([1, 1], center, scale, res, invert=1))-1
    # Bottom right point
    br = np.array(transform([res[0]+1, 
                             res[1]+1], center, scale, res, invert=1))-1

    # Padding so that when rotated proper amount of context is included
    pad = int(np.linalg.norm(br - ul) / 2 - float(br[1] - ul[1]) / 2)
    if not rot == 0:
        ul -= pad
        br += pad

    new_shape = [br[1] - ul[1], br[0] - ul[0]]
    if len(img.shape) > 2:
        new_shape += [img.shape[2]]
    new_img = np.zeros(new_shape)
    

    if new_img.shape[0] > img.shape[0]:
        p = (new_img.shape[0] - img.shape[0]) / 2
        p = int(p)
        new_img = cv2.copyMakeBorder(img, p, p, p, p, cv2.BORDER_REPLICATE)

    # Range to fill new array
    new_x = max(0, -ul[0]), min(br[0], len(img[0])) - ul[0]
    new_y = max(0, -ul[1]), min(br[1], len(img)) - ul[1]
    # Range to sample from original image
    old_x = max(0, ul[0]), min(len(img[0]), br[0])
    old_y = max(0, ul[1]), min(len(img), br[1])
    new_img[new_y[0]:new_y[1], new_x[0]:new_x[1]] = img[old_y[0]:old_y[1], 
                                                        old_x[0]:old_x[1]]

    if not rot == 0:
        # Remove padding
        new_img = rotate(new_img, rot)
        new_img = new_img[pad:-pad, pad:-pad]

    new_img = resize(new_img, res)
    return new_img

def uncrop(img, center, scale, orig_shape, rot=0, is_rgb=True):
    """'Undo' the image cropping/resizing.
    This function is used when evaluating mask/part segmentation.
    """
    res = img.shape[:2]
    # Upper left point
    ul = np.array(transform([1, 1], center, scale, res, invert=1))-1
    # Bottom right point
    br = np.array(transform([res[0]+1,res[1]+1], center, scale, res, invert=1))-1
    # size of cropped image
    crop_shape = [br[1] - ul[1], br[0] - ul[0]]

    new_shape = [br[1] - ul[1], br[0] - ul[0]]
    if len(img.shape) > 2:
        new_shape += [img.shape[2]]
    new_img = np.zeros(orig_shape, dtype=np.uint8)
    # Range to fill new array
    new_x = max(0, -ul[0]), min(br[0], orig_shape[1]) - ul[0]
    new_y = max(0, -ul[1]), min(br[1], orig_shape[0]) - ul[1]
    # Range to sample from original image
    old_x = max(0, ul[0]), min(orig_shape[1], br[0])
    old_y = max(0, ul[1]), min(orig_shape[0], br[1])
    img = resize(img, crop_shape, interp='nearest')
    new_img[old_y[0]:old_y[1], old_x[0]:old_x[1]] = img[new_y[0]:new_y[1], new_x[0]:new_x[1]]
    return new_img

def rot_aa(aa, rot):
    """Rotate axis angle parameters."""
    # pose parameters
    R = np.array([[np.cos(np.deg2rad(-rot)), -np.sin(np.deg2rad(-rot)), 0],
                  [np.sin(np.deg2rad(-rot)), np.cos(np.deg2rad(-rot)), 0],
                  [0, 0, 1]])
    # find the rotation of the body in camera frame
    per_rdg, _ = cv2.Rodrigues(aa)
    # apply the global rotation to the global orientation
    resrot, _ = cv2.Rodrigues(np.dot(R,per_rdg))
    aa = (resrot.T)[0]
    return aa

def flip_img(img):
    """Flip rgb images or masks.
    channels come last, e.g. (256,256,3).
    """
    img = np.fliplr(img)
    return img

def flip_kp(kp):
    """Flip keypoints."""
    if len(kp) == 24:
        flipped_parts = constants.J24_FLIP_PERM
    elif len(kp) == 49:
        flipped_parts = constants.J49_FLIP_PERM
    kp = kp[flipped_parts]
    kp[:,0] = - kp[:,0]
    return kp

def flip_pose(pose):
    """Flip pose.
    The flipping is based on SMPL parameters.
    """
    flipped_parts = constants.SMPL_POSE_FLIP_PERM
    pose = pose[flipped_parts]
    # we also negate the second and the third dimension of the axis-angle
    pose[1::3] = -pose[1::3]
    pose[2::3] = -pose[2::3]
    return pose


def crop_img(img, center, scale, res, val=255):
    """Crop image according to the supplied bounding box."""
    # Upper left point
    ul = np.array(transform([1, 1], center, scale, res, invert=1))-1
    # Bottom right point
    br = np.array(transform([res[0]+1, 
                             res[1]+1], center, scale, res, invert=1))-1
    
    new_shape = [br[1] - ul[1], br[0] - ul[0]]
    if len(img.shape) > 2:
        new_shape += [img.shape[2]]
    new_img = np.ones(new_shape) * val

    # Range to fill new array
    new_x = max(0, -ul[0]), min(br[0], len(img[0])) - ul[0]
    new_y = max(0, -ul[1]), min(br[1], len(img)) - ul[1]
    # Range to sample from original image
    old_x = max(0, ul[0]), min(len(img[0]), br[0])
    old_y = max(0, ul[1]), min(len(img), br[1])
    new_img[new_y[0]:new_y[1], new_x[0]:new_x[1]] = img[old_y[0]:old_y[1], 
                                                        old_x[0]:old_x[1]]
    new_img = resize(new_img, res)
    return new_img


def boxes_2_cs(boxes):
    x1, y1, x2, y2 = boxes[:, 0], boxes[:, 1], boxes[:, 2], boxes[:, 3]
    w, h = x2-x1, y2-y1
    cx, cy = x1+w/2, y1+h/2
    size = np.stack([w, h]).max(axis=0)
    
    centers = np.stack([cx, cy], axis=1)
    scales = size / 200
    return centers, scales


def box_2_cs(box):
    x1,y1,x2,y2 = box[:4].int().tolist()

    w, h = x2-x1, y2-y1
    cx, cy = x1+w/2, y1+h/2
    size = max(w, h)

    center = [cx, cy]
    scale = size / 200
    return center, scale


def est_intrinsics(img_shape):
    h, w, c = img_shape
    img_center = torch.tensor([w/2., h/2.]).float()
    img_focal = torch.tensor(np.sqrt(h**2 + w**2)).float()
    return img_center, img_focal