基于tensorflow的实时物体识别

2019年5月5日 494次阅读 来源: 斯坦因和他的狗

google开源了基于深度学习的物体识别模型和python API。

  1. API结构微调；
  2. 多线程，读取视频流；
  3. 多进程，加载物体识别模型；

API结构微调

import os
import cv2
import numpy as np
import multiprocessing
from multiprocessing import Queue, Pool

# tensorflow api 接口相关函数
import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

# 模型路径
PATH_TO_CKPT = '../object_detection/ssd_mobilenet_v1_coco_11_06_2017/frozen_inference_graph.pb')

# label字典路径，用于识别出物品后展示类别名
PATH_TO_LABELS = '../object_detection/data/mscoco_label_map.pbtxt'
NUM_CLASSES = 90 # 最大分类数量
label_map = label_map_util.load_labelmap(PATH_TO_LABELS) # 获得类别字典
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)

# 物体识别神经网络，向前传播获得识别结果
def detect_objects(image_np, sess, detection_graph):
    # 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')

    # 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(classes).astype(np.int32),
        np.squeeze(scores),
        category_index,
        use_normalized_coordinates=True,
        line_thickness=3)
    return image_np

多线程，读取视频流

更多资料参考 Increasing webcam FPS with Python and OpenCV

import cv2
from threading import Thread

# 多线程，高效读视频
class WebcamVideoStream:
    def __init__(self, src, width, height):
        # initialize the video camera stream and read the first frame
        # from the stream
        self.stream = cv2.VideoCapture(src)
        self.stream.set(cv2.CAP_PROP_FRAME_WIDTH, width)
        self.stream.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
        (self.grabbed, self.frame) = self.stream.read()

        # initialize the variable used to indicate if the thread should
        # be stopped
        self.stopped = False

    def start(self):
        # start the thread to read frames from the video stream
        Thread(target=self.update, args=()).start()
        return self

    def update(self):
        # keep looping infinitely until the thread is stopped
        while True:
            # if the thread indicator variable is set, stop the thread
            if self.stopped:
                return

            # otherwise, read the next frame from the stream
            (self.grabbed, self.frame) = self.stream.read()

    def read(self):
        # return the frame most recently read
        return self.frame

    def stop(self):
        # indicate that the thread should be stopped
        self.stopped = True

# 使用方法
video_capture = WebcamVideoStream(src=video_source,
                                      width=width,
                                      height=height).start()
frame = video_capture.read()

多进程，加载物体识别模型

  • 配置参数
     class configs(object):
     def __init__(self):
         self.num_workers = 2 # worker数量
         self.queue_size = 5  # 多进程，输入输出，队列长度
         self.video_source = 0 # 0代表从摄像头读取视频流
         self.width = 720 # 图片宽
         self.height = 490 # 图片高
 args = configs()
  • 定义用于多进程执行的函数word，每个进程执行work函数，都会加载一次模型
    def worker(input_q, output_q):
    detection_graph = tf.Graph()
    with detection_graph.as_default(): # 加载模型
        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)

    while True: # 全局变量input_q与output_q定义，请看下文
        frame = input_q.get() # 从多进程输入队列，取值
        output_q.put(detect_objects(frame, sess, detection_graph)) # detect_objects函数 返回一张图片，标记所有被发现的物品
    sess.close()
  • 多进程 Queue 文档 (Exchanging objects between processes)
    import multiprocessing
input_q = Queue(maxsize=args.queue_size) # 多进程输入队列
output_q = Queue(maxsize=args.queue_size) # 多进程输出队列
pool = Pool(args.num_workers, worker, (input_q, output_q)) # 多进程加载模型

video_capture = WebcamVideoStream(src=args.video_source,
                                  width=args.width,
                                  height=args.height).start()

while True: 
    frame = video_capture.read() # video_capture多线程读取视频流
    input_q.put(frame) # 视频帧放入多进程输入队列
    frame = output_q.get() # 多进程输出队列取出标记好物体的图片

    cv2.imshow('Video', frame) # 展示已标记物体的图片
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

pool.terminate() # 关闭多进程
video_capture.stop() # 关闭视频流
cv2.destroyAllWindows() # opencv窗口关闭

《基于tensorflow的实时物体识别》 简单测试

    原文作者：斯坦因和他的狗
    原文地址: https://www.jianshu.com/p/75fc00764d21
    本文转自网络文章，转载此文章仅为分享知识，如有侵权，请联系博主进行删除。
点赞