【发布时间】：2020-07-30 03:27:06
【问题描述】：
我找到了这段代码。该程序使用 TensorFlow 分类器来执行对象检测和计数。
它在来自 picamera 的每一帧中围绕感兴趣的对象绘制框和分数。
它还使用一个变量来计算编号。框架中的对象。 如何更改代码以计算相机检测到的目标对象，例如香蕉和苹果？
######## Object counting using tensorflow on picamera #########
# Author: Vineeth Rajendran
# Date: 4/1/19
# Description:
# This program uses a TensorFlow classifier to perform object detection and counting.
# It draws boxes and scores around the objects of interest in each frame from the picamera.
# IT also uses a variable for counting the no. of objects in the frame.
## Some of the code is copied from Evan Juras example at
## https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi/blob/master/Object_detection_picamera.py
# Import packages
import os
import cv2
import numpy as np
from picamera.array import PiRGBArray
from picamera import PiCamera
import tensorflow as tf
import argparse
import sys
# Set up camera constants
IM_WIDTH = 1280
IM_HEIGHT = 720
#IM_WIDTH = 640 Use smaller resolution for
#IM_HEIGHT = 480 slightly faster framerate
# Select camera type (if user enters --usbcam when calling this script,
# a USB webcam will be used)
camera_type = 'picamera'
parser = argparse.ArgumentParser()
parser.add_argument('--usbcam', help='Use a USB webcam instead of picamera',
action='store_true')
args = parser.parse_args()
if args.usbcam:
camera_type = 'usb'
# This is needed since the working directory is 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 = 'ssdlite_mobilenet_v2_coco_2018_05_09'
# 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','mscoco_label_map.pbtxt')
# Number of classes the object detector can identify
NUM_CLASSES = 90
## Load the label map.
# Label maps map indices to category names, so that when the convolution
# network predicts `5`, we know that this corresponds to `airplane`.
# 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')
# creating a fucntion
def object_counting()
# Initialize Picamera and grab reference to the raw capture
camera = PiCamera()
camera.resolution = (IM_WIDTH,IM_HEIGHT)
camera.framerate = 10
rawCapture = PiRGBArray(camera, size=(IM_WIDTH,IM_HEIGHT))
rawCapture.truncate(0)
for frame1 in camera.capture_continuous(rawCapture, format="bgr",use_video_port=True):
totalcount=0
# 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
frame = np.copy(frame1.array)
frame.setflags(write=1)
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})
# Visualizing the results of the detection
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=0.40)
# Updating totalcount
totalcount=totalcount+num
# Displaying the number of objects detected using the totalcount variable
cv2.putText(frame,"Count"+str(totalcount) ,(10, 35),font,0.8,(0, 0xFF, 0xFF),2,cv2.FONT_HERSHEY_SIMPLEX,)
# 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
rawCapture.truncate(0)
camera.close()
cv2.destroyAllWindows()
object_counting()
【问题讨论】：
标签： python opencv tensorflow object-detection counting