Question

对于我的项目，我想将“对象检测API”找到的边界框另存为.jpg，以输入另一个CNN进行进一步分类。

这是我的代码（来自EdjeElectronics GitHub）：

import os
import cv2
import numpy as np
import tensorflow as tf
import sys

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")

# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util

# Name of the directory containing the object detection module we're using
MODEL_NAME = '_model_ssd_v2'
IMAGE_NAME = 'image.jpg'

# Grab path to current working directory
CWD_PATH = os.getcwd()

# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')

# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'_data','label_map.pbtxt')

# Path to image
PATH_TO_IMAGE = os.path.join(CWD_PATH,"_images",IMAGE_NAME)

# Number of classes the object detector can identify
NUM_CLASSES = 6

# Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# 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)

# Load the 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='')

    sess = tf.Session(graph=detection_graph)

# Define input and output tensors (i.e. data) for the object detection classifier

# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

# Output tensors are the detection boxes, scores, and classes
# 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 represents level of confidence for each of the objects.
# The 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')

# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')

# Load image using OpenCV and
# expand image dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
image = cv2.imread(PATH_TO_IMAGE)
image_expanded = np.expand_dims(image, axis=0)

# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) = sess.run(
    [detection_boxes, detection_scores, detection_classes, num_detections],
    feed_dict={image_tensor: image_expanded})

# Draw the results of the detection (aka 'visulaize the results')

vis_util.visualize_boxes_and_labels_on_image_array(
    image,
    np.squeeze(boxes),
    np.squeeze(classes).astype(np.int32),
    np.squeeze(scores),
    category_index,
    use_normalized_coordinates=True,
    line_thickness=8,
    min_score_thresh=0.3)

# All the results have been drawn on image. Now display the image.
# cv2.imshow('Object detector', cv2.resize(image, (int(2592/2),int(1944/2))))

# # Press any key to close the image
# cv2.waitKey(0)

# # Clean up
# cv2.destroyAllWindows()
cv2.imwrite("C:/tensorflow/models/research/object_detection/_images/test1.jpg", image)

有人问了类似的问题here，但我不知道如何将其与Tensorflow对象检测API结合使用。

谢谢！

Answer 1

我在draw_bounding_boxes_on_image中找到了函数vis_util。试试这个：

#create a white back ground image with the same shape as image
white_bg_img = 255*np.ones(image.shape, np.uint8)
vis_util.draw_bounding_boxes_on_image(
    white_bg_img ,
    np.squeeze(boxes),
    color='red',
    thickness=4)
cv2.imwrite("bounding_boxes.jpg", white_bg_img )

在边框内绘制图像。

boxes = np.squeeze(boxes)
for i in range(len(boxes)):
    ymin = box[i,0]
    xmin = box[i,1]
    ymax = box[i,2]
    xmax = box[i,3]
    roi = image[ymin:ymax,xmin:xmax].copy()
    cv2.imwrite("box_{}.jpg".format(str(i)), roi)

保存文件将类似于box_1.jpg，box_2.jpg ...

Answer 2

这将起作用

enter code here
box = np.squeeze(boxes)
for i in range(len(boxes)):
    ymin = (int(box[i,0]*height))
    xmin = (int(box[i,1]*width))
    ymax = (int(box[i,2]*height))
    xmax = (int(box[i,3]*width))
    print(ymin,xmin,ymax,xmax)
    roi =image[ymin:ymax,xmin:xmax].copy()

Answer 3

我遵循了这个link并成功了。添加以下代码：

min_score_thresh=0.60
true_boxes = boxes[0][scores[0] > min_score_thresh]
for i in range(true_boxes.shape[0]):
    ymin = int(true_boxes[i,0]*height)
    xmin = int(true_boxes[i,1]*width)
    ymax = int(true_boxes[i,2]*height)
    xmax = int(true_boxes[i,3]*width)

    roi = image[ymin:ymax,xmin:xmax].copy()
    cv2.imwrite("box_{}.jpg".format(str(i)), roi)

确保定义图像的真实高度和宽度。

如何将边界框导出为.jpg

3 个答案: