play_video.py

### 讀取影片 ###

# Import packages
import os
import cv2
import numpy as np
import tensorflow as tf
import sys

# Import utilites
from utils import label_map_util
from utils import visualization_utils1 as vis_util

# Name of the directory containing the object detection module we're using
MODEL_NAME = 'inference_graph'
#IMAGE_NAME = '21.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,'training','labelmap.pbtxt')

# Path to image
#PATH_TO_IMAGE = os.path.join(CWD_PATH,'images/test/',IMAGE_NAME)

# Number of classes the object detector can identify
NUM_CLASSES = 10

# 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')


# 開啟影片檔案
cap = cv2.VideoCapture('my_video.avi')
# 設定擷取影像的尺寸大小
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 960)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 540)

# 使用 MJPG 編碼
fourcc = cv2.VideoWriter_fourcc(*'MJPG')

# 建立 VideoWriter 物件，輸出影片至 output.avi
# FPS 值為 20.0，解析度為 640x360
fps = cap.get(cv2.CAP_PROP_FPS)
#out = cv2.VideoWriter('output1.avi', fourcc, fps, (960, 540))
total_frames = cap.get(cv2.CAP_PROP_FRAME_COUNT)
count = 0

# 以迴圈從影片檔案讀取影格，並顯示出來
while(cap.isOpened()):
    ret, frame = cap.read()

    #break if nothing read
    if not ret:
        break

    count += 1
    if count % 3 == 1:
        # 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(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: image_expanded})


        # Draw the results of the detection (aka 'visulaize the results')
        vis_util.visualize_boxes_and_labels_on_image_array(
            frame,
            np.squeeze(boxes),
            np.squeeze(classes).astype(np.int32),
            np.squeeze(scores),
            category_index,
            use_normalized_coordinates=True,
            line_thickness=8,
            min_score_thresh=0.60)

        #out.write(frame)
        cv2.imshow('frame',frame)
        
        #if count % (total_frames / 10) == 0:
        #    print('progress: ' + str(count * 100 / total_frames) + '%')

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

cap.release()
#out.release()
cv2.destroyAllWindows()