使用亚马逊的Rekognition,我使用以下方法从JSON响应中提取了感兴趣的边界框:
def __init__(self, image):
self.shape = image.shape
def bounding_box_convert(self, bounding_box):
xmin = int(bounding_box['Left'] * self.shape[1])
xmax = xmin + int(bounding_box['Width'] * self.shape[1])
ymin = int(bounding_box['Top'] * self.shape[0])
ymax = ymin + int(bounding_box['Height'] * self.shape[0])
return (xmin,ymin,xmax,ymax)
def polygon_convert(self, polygon):
pts = []
for p in polygon:
x = int(p['X'] * self.shape[1])
y = int(p['Y'] * self.shape[0])
pts.append( [x,y] )
return pts
def get_bounding_boxes(jsondata):
objectnames = ('Helmet','Hardhat')
bboxes = []
a = jsondata
if('Labels' in a):
for label in a['Labels']:
#-- skip over anything that isn't hardhat,helmet
if(label['Name'] in objectnames):
print('extracting {}'.format(label['Name']))
lbl = "{}: {:0.1f}%".format(label['Name'], label['Confidence'])
print(lbl)
for instance in label['Instances']:
coords = tmp.bounding_box_convert(instance['BoundingBox'])
bboxes.append(coords)
return bboxes
if __name__=='__main__':
imagefile = 'image011.jpg'
bgr_image = cv2.imread(imagefile)
tmp = Tmp(bgr_image)
jsonname = 'json_000'
fin = open(jsonname, 'r')
jsondata = json.load(fin)
bb = get_bounding_boxes(jsondata)
print(bb)
输出是边界框的列表:
[(865, 731, 1077, 906), (1874, 646, 2117, 824)]
我能够轻松地从列表中提取一个位置,并使用以下方式另存为新图像:
from PIL import Image
img = Image.open("image011.jpg")
area = (865, 731, 1077, 906)
cropped_img = img.crop(area)
cropped_img.save("cropped.jpg")
但是,我还没有找到一个好的解决方案,可以使用'bb'列表输出来裁剪并保存图像中的多个边界框。
我确实找到了一种从csv中提取信息的解决方案:Most efficient/quickest way to crop multiple bounding boxes in 1 image, over thousands of images?。
但是,我相信有一种比将边界框数据保存到csv并读回的更有效的方法。
我不太擅长编写自己的函数-非常感谢所有建议!
x,y,w,h
的形式,则可以进行ROI = image[y:y+h,x:x+w]
裁剪。使用此输入图像:使用how to get ROI Bounding Box Coordinates without Guess & Check中的脚本来获取x,y,w,h
边界框坐标以裁剪出这些ROI:
我们只是简单地遍历边界框列表,然后使用Numpy切片对其进行裁剪。提取的投资回报率:
这是最小的示例:
import cv2
import numpy as np
image = cv2.imread('1.png')
bounding_boxes = [(17, 24, 47, 47),
(74, 28, 47, 50),
(125, 15, 51, 61),
(184, 18, 53, 53),
(247, 25, 44, 46),
(296, 6, 65, 66)
]
num = 0
for box in bounding_boxes:
x,y,w,h = box
ROI = image[y:y+h, x:x+w]
cv2.imwrite('ROI_{}.png'.format(num), ROI)
num += 1
cv2.imshow('ROI', ROI)
cv2.waitKey()