dlib系列【3】-目标检测 训练自己的数据

dlib 支持 imglab 生成的数据格式；

imglab 用法见 我的博客 《标注工具》

 

目标检测 标注文件 格式如下 

<?xml version='1.0' encoding='ISO-8859-1'?>
<?xml-stylesheet type='text/xsl' href='image_metadata_stylesheet.xsl'?>
<dataset>
<name>imglab dataset</name>
<comment>Created by imglab tool.</comment>
<images>
  <image file='images\1.jpg' width='400' height='300'>
    <box top='59' left='14' width='377' height='229'/>
  </image>
  <image file='images\10.jpg' width='612' height='459'>
    <box top='38' left='67' width='488' height='361'/>
  </image>
</images>
</dataset>

图片大小无需一致

 

训练自己的数据

import dlib

# 训练的参数，可以根据实际情况进行修改
options = dlib.simple_object_detector_training_options()

options.add_left_right_image_flips = True
options.C = 5
options.num_threads = 4
options.be_verbose = True

current_path = r'D:\Pythoncode\dlib-master\tools\imglab\build\Release'
train_folder = current_path + '/images/'        # 图片地址
train_xml_path = current_path + '/data.xml'      # 标注文件地址

print("start training:")

# 最重要的一个函数，生成 detector.svm 模型
dlib.train_simple_object_detector(train_xml_path, 'detector.svm', options)  # 

print("Training accuracy: {}".format(
    dlib.test_simple_object_detector(train_xml_path, "detector.svm")))

 

测试训练的模型

import dlib
import cv2
import glob

detector = dlib.simple_object_detector("detector.svm")  # 训练好的模型
test_folder = 'img/test/'       # 测试数据地址

for f in glob.glob(test_folder + '*.jpg'):
    print("Processing file: {}".format(f))
    img = cv2.imread(f, cv2.IMREAD_COLOR)
    b, g, r = cv2.split(img)
    img2 = cv2.merge([r, g, b])
    dets = detector(img2)
    print("Number of cars detected: {}".format(len(dets)))
    for index, car in enumerate(dets):
        print('car {}; left {}; top {}; right {}; bottom {}'.format(index, car.left(), car.top(), car.right(),
                                                                    car.bottom()))

        left = car.left()
        top = car.top()
        right = car.right()
        bottom = car.bottom()
        cv2.rectangle(img, (left, top), (right, bottom), (0, 255, 0), 3)
        cv2.namedWindow(f, cv2.WINDOW_AUTOSIZE)
        cv2.imshow(f, img)

k = cv2.waitKey(0)
cv2.destroyAllWindows()

 

 

 

参考资料：

https://blog.csdn.net/wyd1520/article/details/81585293　　基于dlib的物体检测(转)

https://blog.csdn.net/djstavaV/article/details/86743600　　基于dlib的物体检测(转)

https://www.jianshu.com/p/96eaa6a6ec22　　人脸识别(dlib)——用imglab制作样本与测试