Img process

获取图像尺寸

img = cv2.imread(pic)
height, width, channel = img.shape  

从原图中随机裁剪12×12的图像

size = npr.randint(12, min(width, height) / 2)
#top_left coordinate
nx = npr.randint(0, width - size)
ny = npr.randint(0, height - size)
#random crop
crop_box = np.array([nx, ny, nx + size, ny + size])
#calculate iou
Iou = IoU(crop_box, boxes)

#crop a part from inital image
cropped_im = img[ny : ny + size, nx : nx + size, :]
#resize the cropped image to size 12*12
resized_im = cv2.resize(cropped_im, (12, 12), interpolation=cv2.INTER_LINEAR)

计算IoU

def IoU(box, boxes):
    """Compute IoU between detect box and gt boxes

    Parameters:
    ----------
    box: numpy array , shape (5, ): x1, y1, x2, y2, score
        predicted boxes
    boxes: numpy array, shape (n, 4): x1, y1, x2, y2
        input ground truth boxes

    Returns:
    -------
    ovr: numpy.array, shape (n, )
        IoU
    """
    box_area = (box[2] - box[0] + 1) * (box[3] - box[1] + 1)
    area = (boxes[:, 2] - boxes[:, 0] + 1) * (boxes[:, 3] - boxes[:, 1] + 1)
    xx1 = np.maximum(box[0], boxes[:, 0])
    yy1 = np.maximum(box[1], boxes[:, 1])
    xx2 = np.minimum(box[2], boxes[:, 2])
    yy2 = np.minimum(box[3], boxes[:, 3])

    # compute the width and height of the bounding box
    w = np.maximum(0, xx2 - xx1 + 1)
    h = np.maximum(0, yy2 - yy1 + 1)

    inter = w * h
    ovr = inter / (box_area + area - inter)
    return ovr