Letter Box目标检测

前言

深度学习模型输入图片的尺寸为正方形，而数据集中的图片一般为长方形，粗暴的resize会使得图片失真，采用letterbox可以较好的解决这个问题。该方法可以保持图片的长宽比例，剩下的部分采用灰色填充

import cv2
import numpy as np
import xml.etree.ElementTree as ET


class_dict = {'aircraft': 1}

def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
    # Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
    shape = img.shape[:2]  # current shape [height, width]
    if isinstance(new_shape, int):
        new_shape = (new_shape, new_shape)

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    if not scaleup:  # only scale down, do not scale up (for better test mAP)
        r = min(r, 1.0)

    # Compute padding
    ratio = r, r  # width, height ratios
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
    if auto:  # minimum rectangle
        dw, dh = np.mod(dw, 64), np.mod(dh, 64)  # wh padding
    elif scaleFill:  # stretch
        dw, dh = 0.0, 0.0
        new_unpad = (new_shape[1], new_shape[0])
        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios

    dw /= 2  # divide padding into 2 sides
    dh /= 2

    if shape[::-1] != new_unpad:  # resize
        img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return img, ratio, (dw, dh)

def parse_xml(path):
    tree = ET.parse(path)
    root = tree.findall('object')
    class_list = []
    boxes_list = []
    difficult_list = []
    for sub in root:
        xmin = float(sub.find('bndbox').find('xmin').text)
        xmax = float(sub.find('bndbox').find('xmax').text)
        ymin = float(sub.find('bndbox').find('ymin').text)
        ymax = float(sub.find('bndbox').find('ymax').text)
        boxes_list.append([xmin, ymin, xmax, ymax])
        class_list.append(class_dict[sub.find('name').text])
        difficult_list.append(int(sub.find('difficult').text))
    return np.array(class_list), np.array(boxes_list).astype(np.int32)

if __name__=="__main__":
    import glob
    import matplotlib.pyplot as plt
    imglist = glob.glob(f'./JPEGImages/*.jpg')
    shape = (512, 512)
    imgPath = imglist[0]
    xmlPath = imgPath[:-3] + 'xml'
    img = cv2.imread(imgPath)
    labels, boxes = parse_xml(xmlPath.replace('JPEGImages', 'Annotation/xml'))
    img2, ratio, pad = letterbox(img.copy(), shape, auto=False, scaleup=False)
    new_boxes = np.zeros_like(boxes)
    new_boxes[:, 0] = ratio[0] * boxes[:, 0] + pad[0]  # pad width
    new_boxes[:, 1] = ratio[1] * boxes[:, 1] + pad[1]  # pad height
    new_boxes[:, 2] = ratio[0] * boxes[:, 2] + pad[0]
    new_boxes[:, 3] = ratio[1] * boxes[:, 3] + pad[1]

    sample1 = img.copy()
    for box in boxes:
        cv2.rectangle(sample1, (box[0], box[1]), (box[2], box[3]), (1, 0, 0), 1)

    sample2 = img2.copy()
    for box in new_boxes:
        cv2.rectangle(sample2, (box[0], box[1]), (box[2], box[3]), (1, 0, 0), 1)

    plt.subplot(121)
    plt.imshow(sample1)
    plt.subplot(122)
    plt.imshow(sample2)
    plt.show()