人脸识别准备 -- 基于raspberry pi 3b + movidius

#! /usr/bin/env python3

import sys
sys.path.insert(0, "../../ncapi2_shim")
import mvnc_simple_api as mvnc

import numpy
import cv2
import sys
import os

from picamera.array import PiRGBArray
from picamera import PiCamera
import time


# initialize the camera and grab a reference to the raw camera capture
camera = PiCamera()

camera.resolution = (280, 280)
camera.framerate = 32
rawCapture = PiRGBArray(camera, size=(280, 280))

frame_name=''
EXAMPLES_BASE_DIR='../../'
IMAGES_DIR = './'

VALIDATED_IMAGES_DIR = IMAGES_DIR + 'validated_images/'
validated_image_filename = VALIDATED_IMAGES_DIR + 'my1.png'

GRAPH_FILENAME = "facenet_celeb_ncs.graph"

# name of the opencv window
CV_WINDOW_NAME = "FaceNet"



# the same face will return 0.0
# different faces return higher numbers
# this is NOT between 0.0 and 1.0
FACE_MATCH_THRESHOLD = 1.2


# Run an inference on the passed image
# image_to_classify is the image on which an inference will be performed
#    upon successful return this image will be overlayed with boxes
#    and labels identifying the found objects within the image.
# ssd_mobilenet_graph is the Graph object from the NCAPI which will
#    be used to peform the inference.
def run_inference(image_to_classify, facenet_graph):

    # get a resized version of the image that is the dimensions
    # SSD Mobile net expects
    resized_image = preprocess_image(image_to_classify)

    # ***************************************************************
    # Send the image to the NCS
    # ***************************************************************
    facenet_graph.LoadTensor(resized_image.astype(numpy.float16), None)

    # ***************************************************************
    # Get the result from the NCS
    # ***************************************************************
    output, userobj = facenet_graph.GetResult()

    return output


# overlays the boxes and labels onto the display image.
# display_image is the image on which to overlay to
# image info is a text string to overlay onto the image.
# matching is a Boolean specifying if the image was a match.
# returns None
def overlay_on_image(display_image, image_info, matching):
    rect_width = 10
    offset = int(rect_width/2)
    if (image_info != None):
        cv2.putText(display_image, image_info, (30, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 1)
    if (matching):
        # match, green rectangle
        cv2.rectangle(display_image, (0+offset, 0+offset),
                      (display_image.shape[1]-offset-1, display_image.shape[0]-offset-1),
                      (0, 255, 0), 10)
    else:
        # not a match, red rectangle
        cv2.rectangle(display_image, (0+offset, 0+offset),
                      (display_image.shape[1]-offset-1, display_image.shape[0]-offset-1),
                      (0, 0, 255), 10)


# whiten an image
def whiten_image(source_image):
    source_mean = numpy.mean(source_image)
    source_standard_deviation = numpy.std(source_image)
    std_adjusted = numpy.maximum(source_standard_deviation, 1.0 / numpy.sqrt(source_image.size))
    whitened_image = numpy.multiply(numpy.subtract(source_image, source_mean), 1 / std_adjusted)
    return whitened_image

# create a preprocessed image from the source image that matches the
# network expectations and return it
def preprocess_image(src):
    # scale the image
    NETWORK_WIDTH = 160
    NETWORK_HEIGHT = 160
    preprocessed_image = cv2.resize(src, (NETWORK_WIDTH, NETWORK_HEIGHT))

    #convert to RGB
    preprocessed_image = cv2.cvtColor(preprocessed_image, cv2.COLOR_BGR2RGB)

    #whiten
    preprocessed_image = whiten_image(preprocessed_image)

    # return the preprocessed image
    return preprocessed_image

# determine if two images are of matching faces based on the
# the network output for both images.
def face_match(face1_output, face2_output):
    if (len(face1_output) != len(face2_output)):
        print('length mismatch in face_match')
        return False
    total_diff = 0
    for output_index in range(0, len(face1_output)):
        this_diff = numpy.square(face1_output[output_index] - face2_output[output_index])
        total_diff += this_diff
    print('Total Difference is: ' + str(total_diff))

    if (total_diff < FACE_MATCH_THRESHOLD):
        # the total difference between the two is under the threshold so
        # the faces match.
        return True

    # differences between faces was over the threshold above so
    # they didn't match.
    return False

# handles key presses
# raw_key is the return value from cv2.waitkey
# returns False if program should end, or True if should continue
def handle_keys(raw_key):
    ascii_code = raw_key & 0xFF
    if ((ascii_code == ord('q')) or (ascii_code == ord('Q'))):
        return False

    return True


# start the opencv webcam streaming and pass each frame
# from the camera to the facenet network for an inference
# Continue looping until the result of the camera frame inference
# matches the valid face output and then return.
# valid_output is inference result for the valid image
# validated image filename is the name of the valid image file
# graph is the ncsdk Graph object initialized with the facenet graph file
#   which we will run the inference on.
# returns None
def run_camera(valid_output, validated_image_filename, graph):

    frame_count = 0

    cv2.namedWindow(CV_WINDOW_NAME)

    found_match = False

    for frame in camera.capture_continuous(rawCapture, format="bgr", use_video_port=True):
        # grab the raw NumPy array representing the image, then initialize the timestamp
        # and occupied/unoccupied text
        vid_image = frame.array

        test_output = run_inference(vid_image, graph)


        if (face_match(valid_output, test_output)):
                print('PASS!  File ' + frame_name + ' matches ' + validated_image_filename)
                found_match = True
        else:
            found_match = False
            print('FAIL!  File ' + frame_name + ' does not match ' + validated_image_filename)

        overlay_on_image(vid_image, frame_name, found_match)

        # check if the window is visible, this means the user hasn't closed
        # the window via the X button
        prop_val = cv2.getWindowProperty(CV_WINDOW_NAME, cv2.WND_PROP_ASPECT_RATIO)
        if (prop_val < 0.0):
            print('window closed')
            break

        # display the results and wait for user to hit a key
        cv2.imshow(CV_WINDOW_NAME, vid_image)
        raw_key = cv2.waitKey(1)
        if (raw_key != -1):
            if (handle_keys(raw_key) == False):
                print('user pressed Q')
                break
        # show the frame
        #cv2.imshow("Frame", image)


        key = cv2.waitKey(1) & 0xFF

        # clear the stream in preparation for the next frame
        rawCapture.truncate(0)

        # if the `q` key was pressed, break from the loop
        if key == ord("q"):
            break


# This function is called from the entry point to do
# all the work of the program
def main():

    # Get a list of ALL the sticks that are plugged in
    # we need at least one
    devices = mvnc.EnumerateDevices()
    if len(devices) == 0:
        print('No NCS devices found')
        quit()

    # Pick the first stick to run the network
    device = mvnc.Device(devices[0])

    # Open the NCS
    device.OpenDevice()

    # The graph file that was created with the ncsdk compiler
    graph_file_name = GRAPH_FILENAME

    # read in the graph file to memory buffer
    with open(graph_file_name, mode='rb') as f:
        graph_in_memory = f.read()

    # create the NCAPI graph instance from the memory buffer containing the graph file.
    graph = device.AllocateGraph(graph_in_memory)

    validated_image = cv2.imread(validated_image_filename)
    valid_output = run_inference(validated_image, graph)

    run_camera(valid_output, validated_image_filename, graph)

    # Clean up the graph and the device
    graph.DeallocateGraph()
    device.CloseDevice()


# main entry point for program. we'll call main() to do what needs to be done.
if __name__ == "__main__":
    sys.exit(main())