我正在使用TensorFlow对象检测API来检测视频帧中的人物。我想将检测坐标提供给质心跟踪器,为每个检测到的对象分配一个ID,并避免将每个帧作为新对象检测到。
这是我用于检测和获取边界框的代码
# Import packages
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.
from pandas._libs import json
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 = 'inference_graph'
VIDEO_NAME = 'test.mp4'
# direction for out put file
FILE_OUTPUT = 'C:/Mohammad/tensorflow1/models/research/object_detection/savedframes/out.avi'
# 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,'training','label_map.pbtxt')
# Path to video
PATH_TO_VIDEO = os.path.join(CWD_PATH,VIDEO_NAME)
# Number of classes the object detector can identify
NUM_CLASSES = 2
# 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')
# Open video file
video = cv2.VideoCapture('C:/Mohammad/tensorflow1/models/research/object_detection/test.mp4')
frame_width = int(video.get(3))
frame_height = int(video.get(4))
out = cv2.VideoWriter(FILE_OUTPUT, cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'),
10, (frame_width, frame_height))
frame_index = 0
while(video.isOpened()):
# Acquire frame and expand frame 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
ret, frame = video.read()
frame_expanded = np.expand_dims(frame, 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: frame_expanded})
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
frame,
frame_index,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.80)
#frame_index +=1
if ret == True:
out.write(frame)
# writing coordinates
coordinates = vis_util.return_coordinates(
frame,
frame_index,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.80)
for coordinate in coordinates:
(ymin, ymax, xmin, xmax, acc, classification) = coordinate
height = ymax - ymin
width = xmax -xmin
crop = frame[ymin:ymin+height, xmin:xmin+width]
path = 'C:/Mohammad/A_Mohammad laptop/Tensorflow From C Drive/tensorflow1/models/research/object_detection/savecroped'
cv2.imwrite(os.path.join(path,'crop%d.jpg' %frame_index), frame)
textfile = open('filename_string' + ".json", "a")
textfile.write(json.dumps(coordinates))
textfile.write("\n")
frame_index =frame_index+1
# txt file
#textfile = open('filename_string' + ".txt", "w")
#textfile.write(str(coordinates))
#textfile.write("\n")
# All the results have been drawn on the frame, so it's time to display it.
cv2.imshow('Object detector', frame)
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
# Clean up
video.release()
cv2.destroyAllWindows()
所以最好的方法是定义一个空列表并存储所有检测结果(边界框的坐标),并使用质心类中的更新功能来跟踪对象。同样不要忘记每次检测后清空列表,否则,您将为一个对象获得如此多的ID!