Question

我一直在尝试使用tensorflow的对象检测来尝试建立一个体面的存在检测。我正在使用tensorflow的预训练模型和代码示例在网络摄像头上执行对象检测。有什么方法可以从模型中删除对象或从人员类中过滤掉对象？这是我目前拥有的代码。

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image


from utils import label_map_util

from utils import visualization_utils as vis_util


# # Model preparation 
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.  
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.

# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90


# ## Download Model

if not os.path.exists(MODEL_NAME + '/frozen_inference_graph.pb'):
    print ('Downloading the model')
    opener = urllib.request.URLopener()
    opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
    tar_file = tarfile.open(MODEL_FILE)
    for file in tar_file.getmembers():
      file_name = os.path.basename(file.name)
      if 'frozen_inference_graph.pb' in file_name:
        tar_file.extract(file, os.getcwd())
    print ('Download complete')
else:
    print ('Model already exists')

# ## Load a (frozen) Tensorflow model into memory.

detection_graph = tf.Graph()
with detection_graph.as_default():
  od_graph_def = tf.GraphDef()
  with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
    serialized_graph = fid.read()
    od_graph_def.ParseFromString(serialized_graph)
    tf.import_graph_def(od_graph_def, name='')


# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`.  Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

#intializing the web camera device

import cv2
cap = cv2.VideoCapture(0)

# Running the tensorflow session
with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
   ret = True
   while (ret):
      ret,image_np = cap.read()
      image_np = cv2.resize(image_np,(600,400))
      # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
      image_np_expanded = np.expand_dims(image_np, axis=0)
      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.
      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.
      scores = detection_graph.get_tensor_by_name('detection_scores:0')
      classes = detection_graph.get_tensor_by_name('detection_classes:0')
      num_detections = detection_graph.get_tensor_by_name('num_detections:0')

      b = [x for x in classes if x == 1]
      # Actual detection.
      (boxes, scores, classes, num_detections) = sess.run(
          [boxes, scores, 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(b).astype(np.int32),
          np.squeeze(scores),
          category_index,
          use_normalized_coordinates=True,
          line_thickness=8)

      #print (len(boxes.shape))

      #print (classes)

      final_score = np.squeeze(scores)    
      count = 0
      for i in range(100):
          if scores is None or final_score[i] > 0.5:
                  count = count + 1
                  print (count, ' object(s) detected...')

#      plt.figure(figsize=IMAGE_SIZE)
#      plt.imshow(image_np)
      cv2.imshow('image',image_np)
      if cv2.waitKey(200) & 0xFF == ord('q'):
          cv2.destroyAllWindows()
          cap.release()
          break

Answer 1

我看到您在b = [x for x in classes if x == 1]行中使用了一个过滤器来获取所有人员检测信息。（在标签图中，人员的ID恰好是1）。但这没有用，因为您需要相应地更改boxes，scores和classes。试试这个：

首先删除行

b = [x for x in classes if x == 1]

然后在sess.run()函数之后添加以下内容

boxes = np.squeeze(boxes)
scores = np.squeeze(scores)
classes = np.squeeze(classes)

indices = np.argwhere(classes == 1)
boxes = np.squeeze(boxes[indices])
scores = np.squeeze(scores[indices])
classes = np.squeeze(classes[indices])

然后调用可视化功能

vis_util.visualize_boxes_and_labels_on_image_array(
      image_np,
      boxes,
      classes,
      scores,
      category_index,
      use_normalized_coordinates=True,
      line_thickness=8)

想法是该模型可以产生多个类别的检测结果，但是只选择了一个类别人物以在图像上可视化。

Answer 2

当检测到的类别是唯一的类别时，我建议使用这种方法来防止丢失数组。

# Select specific class
boxes = np.squeeze(boxes)
scores = np.squeeze(scores)
classes = np.squeeze(classes).astype(np.int32)

indices = np.argwhere(classes == 1)
boxes = np.squeeze(boxes[indices], axis=1) # to prevent errors made by nd.array of size 1 nd.array
scores = np.squeeze(scores[indices], axis=1)
classes = np.squeeze(classes[indices], axis=1)

我如何使用tensorflow对象检测仅检测人员？

2 个答案: