体感游戏 | 手势识别玩飞机大战游戏(四) 使用深度学习实现手势识别玩飞机大战游戏

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

from utils import label_map_util
from utils import visualization_utils as vis_util

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_FROZEN_GRAPH = './export/frozen_inference_graph_ssd.pb'

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

NUM_CLASSES = 3
   
detection_graph = tf.Graph()
with detection_graph.as_default():
  od_graph_def = tf.GraphDef()
  with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
    serialized_graph = fid.read()
    od_graph_def.ParseFromString(serialized_graph)
    tf.import_graph_def(od_graph_def, name='')

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categorys = label_map_util.convert_label_map_to_categories(label_map,max_num_classes=NUM_CLASSES,use_display_name=True)
categorys_index = label_map_util.create_category_index(categorys)

config = tf.ConfigProto()
config.gpu_options.allow_growth = True

cap = cv2.VideoCapture(0)
#cap = cv2.VideoCapture("xxx.mp4")

with detection_graph.as_default():
  with tf.Session(graph=detection_graph,config=config) as sess:
    #image = cv2.imread("./VOC2012/JPEGImages/700.jpg")
    while True:
      start = cv2.getTickCount()
      ret,image = cap.read()
      image_np_expanded = np.expand_dims(image,axis = 0)
      image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
      boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
      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')
      (boxes,scores,classes,num_detections) = sess.run([boxes,scores,classes,\
                                num_detections],feed_dict={image_tensor:image_np_expanded})
      vis_util.visualize_boxes_and_labels_on_image_array(
        image,
        np.squeeze(boxes),
        np.squeeze(classes).astype(np.int32),
        np.squeeze(scores),
        categorys_index,
        min_score_thresh = 0.5,
        use_normalized_coordinates = True,
        line_thickness = 5  
        )
    
      end = cv2.getTickCount()
      use_time = (end - start) / cv2.getTickFrequency()
      print("use_time:%0.3fs" % use_time)
      strText = ("SSD one frame use_time: %0.3fs" % use_time)
      cv2.putText(image,strText,(5,30),cv2.FONT_HERSHEY_SIMPLEX,0.7,(0,255,0),2)
      cv2.imshow("object_detection", image)
      if cv2.waitKey(1)&0xFF ==27:
        break
cv2.destroyAllWindows()