代码之家 › 专栏 › 技术社区 › Ajinkya

以CSV格式存储Tensorflow对象检测API图像输出和方框

object-detection deep-learning computer-vision tensorflow python-3.x

Ajinkya · 技术社区 · 8 年前

我指的是谷歌的Tensor Flow对象检测API。我已经成功地对物体进行了训练和测试。我的问题是,在测试后,我得到了一个对象周围绘制的框的输出图像,如何获得这些框的csv坐标?测试代码可在上找到( https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb )

如果我看到助手代码,它会将图像加载到numpy数组中:

def load_image_into_numpy_array(image):
  (im_width, im_height) = image.size
  return np.array(image.getdata()).reshape(
      (im_height, im_width, 3)).astype(np.uint8)

在检测过程中,它获取这个图像数组,并用如下绘制的方框输出

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    # Definite input and output Tensors for detection_graph
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
    # Each box represents a part of the image where a particular object was detected.
    detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
    # Each score represent how level of confidence for each of the objects.
    # Score is shown on the result image, together with the class label.
    detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
    detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')
    for image_path in TEST_IMAGE_PATHS:
      image = Image.open(image_path)
      # the array based representation of the image will be used later in order to prepare the
      # result image with boxes and labels on it.
      image_np = load_image_into_numpy_array(image)
      # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
      image_np_expanded = np.expand_dims(image_np, axis=0)
      # Actual detection.
      (boxes, scores, classes, num) = sess.run(
          [detection_boxes, detection_scores, detection_classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})
      # Visualization of the results of a detection.
      vis_util.visualize_boxes_and_labels_on_image_array(
          image_np,
          np.squeeze(boxes),
          np.squeeze(classes).astype(np.int32),
          np.squeeze(scores),
          category_index,
          use_normalized_coordinates=True,
          line_thickness=8)
      plt.figure(figsize=IMAGE_SIZE)
      plt.imshow(image_np)

我想将这些绿色框的坐标存储在csv文件中。有什么方法可以做到这一点?

1 回复 | 直到 8 年前

ITiger KleinYuan 8 年前

boxes 阵列( [ymin, xmin, ymax, xmax] )已规范化。因此,必须将它们与图像宽度/高度相乘,才能获得原始值。

要实现这一点,可以执行以下操作:

for box in np.squeeze(boxes):
    box[0] = box[0] * heigh
    box[1] = box[1] * width
    box[2] = box[2] * height
    box[3] = box[3] * width

然后,您可以使用numpy将框保存到csv。savetxt()方法:

import numpy as np
np.savetxt('yourfile.csv', boxes, delimiter=',')

编辑:

正如评论中所指出的,上述方法给出了框坐标列表。这是因为boxes张量保持每个检测区域的坐标。假设您使用默认的置信度接受阈值0.5,我的一个快速修复方法如下:

  for i, box in enumerate(np.squeeze(boxes)):
      if(np.squeeze(scores)[i] > 0.5):
          print("ymin={}, xmin={}, ymax={}, xmax{}".format(box[0]*height,box[1]*width,box[2]*height,box[3]*width))

这应该打印四个值,而不是四个框。每个值表示边界框的一个角。

如果使用另一个置信度接受阈值,则必须调整该值。也许您可以解析此参数的模型配置。

要将坐标存储为CSV,可以执行以下操作:

new_boxes = []
for i, box in enumerate(np.squeeze(boxes)):
    if(np.squeeze(scores)[i] > 0.5):
        new_boxes.append(box)
np.savetxt('yourfile.csv', new_boxes, delimiter=',')