YOLO算法中mosaic数据增强中常用到的图像变换的方法

1.YOLOV5中使用了mosaic，具体代码如下：

def load_mosaic(self, index):
    # loads images in a mosaic

    labels4 = []
    s = self.img_size
    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border]  # mosaic center x, y
    indices = [index] + [self.indices[random.randint(0, self.n - 1)] for _ in range(3)]  # 3 additional image indices
    for i, index in enumerate(indices):
        # Load image
        img, _, (h, w) = load_image(self, index)
        关键点：
        # place img in img4
        if i == 0:  # top left
            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image) # mosaic后区域: 
            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image) # 原图的区域
        elif i == 1:  # top right
            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
        elif i == 2:  # bottom left
            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
        elif i == 3:  # bottom right
            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)

        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
        padw = x1a - x1b
        padh = y1a - y1b
        这个是测试用的代码
        cv2.imshow('test_image',img4)
        cv2.waitKey(0)
        # Labels
        x = self.labels[index]
        labels = x.copy()
        if x.size > 0:  # Normalized xywh to pixel xyxy format
            labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw
            labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh
            labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw
            labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh
        labels4.append(labels)

    # Concat/clip labels
    if len(labels4):
        labels4 = np.concatenate(labels4, 0)
        np.clip(labels4[:, 1:], 0, 2 * s, out=labels4[:, 1:])  # use with random_perspective
        # img4, labels4 = replicate(img4, labels4)  # replicate

    # Augment
    img4, labels4 = random_perspective(img4, labels4,
                                       degrees=self.hyp['degrees'],
                                       translate=self.hyp['translate'],
                                       scale=self.hyp['scale'],
                                       shear=self.hyp['shear'],
                                       perspective=self.hyp['perspective'],
                                       border=self.mosaic_border)  # border to remove
    cv2.imshow('test_image', img4)
    cv2.waitKey(0)
    return img4, labels4

下面重点介绍random_perspective这个函数，这个函数主要是对构造好的图片进行变换。数学推导公式公式

def random_perspective(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, border=(0, 0)):
    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
    # targets = [cls, xyxy]

    height = img.shape[0] + border[0] * 2  # shape(h,w,c)  #计算输出的图片的大小
    width = img.shape[1] + border[1] * 2

    # Center
    C = np.eye(3)#构造了一个对角线为1的矩阵
    C[0, 2] = -img.shape[1] / 2  # x translation (pixels)
    C[1, 2] = -img.shape[0] / 2  # y translation (pixels)

    # Perspective
    P = np.eye(3)
    P[2, 0] = random.uniform(-perspective, perspective)  # x perspective (about y)
    P[2, 1] = random.uniform(-perspective, perspective)  # y perspective (about x)

    # Rotation and Scale #该变换为旋转和尺度变化
    R = np.eye(3)
    a = random.uniform(-degrees, degrees)
    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
    s = random.uniform(1 - scale, 1 + scale)
    # s = 2 ** random.uniform(-scale, scale)
    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) #图像旋转

    # Shear 剪切变换
    S = np.eye(3)
    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)

    # Translation  欧拉变换
    T = np.eye(3)
    T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width  # x translation (pixels)
    T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height  # y translation (pixels)

    # Combined rotation matrix
    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT #此处的用法为简单的矩阵之间相乘
    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed  图像透视变换 cv2.warpPerspective
        if perspective:
            img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114))
        else:  # affine
            img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) #仿射变换函数

    # Visualize
    # import matplotlib.pyplot as plt
    # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
    # ax[0].imshow(img[:, :, ::-1])  # base
    # ax[1].imshow(img2[:, :, ::-1])  # warped

    # Transform label coordinates
    n = len(targets)
    if n:
        # warp points
        xy = np.ones((n * 4, 3))
        xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
        xy = xy @ M.T  # transform
        if perspective:
            xy = (xy[:, :2] / xy[:, 2:3]).reshape(n, 8)  # rescale
        else:  # affine
            xy = xy[:, :2].reshape(n, 8)

        # create new boxes
        x = xy[:, [0, 2, 4, 6]]
        y = xy[:, [1, 3, 5, 7]]
        xy = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T

        # # apply angle-based reduction of bounding boxes
        # radians = a * math.pi / 180
        # reduction = max(abs(math.sin(radians)), abs(math.cos(radians))) ** 0.5
        # x = (xy[:, 2] + xy[:, 0]) / 2
        # y = (xy[:, 3] + xy[:, 1]) / 2
        # w = (xy[:, 2] - xy[:, 0]) * reduction
        # h = (xy[:, 3] - xy[:, 1]) * reduction
        # xy = np.concatenate((x - w / 2, y - h / 2, x + w / 2, y + h / 2)).reshape(4, n).T

        # clip boxes 将数组中的元素限制在一定的范围内
        xy[:, [0, 2]] = xy[:, [0, 2]].clip(0, width)
        xy[:, [1, 3]] = xy[:, [1, 3]].clip(0, height)

        # filter candidates 计算候选框
        i = box_candidates(box1=targets[:, 1:5].T * s, box2=xy.T)
        targets = targets[i]
        targets[:, 1:5] = xy[i]

    return img, targets