#Import packages
import math
import os
import cv2
import numpy as np
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

# Variables
total_humans = 0  # using it to count humans

# 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 = 1

## 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)

total_humans = 0

# 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')
#print('Num detections : ', num_detections)

# Initialize frame rate calculation
frame_rate_calc = 1
freq = cv2.getTickFrequency()
font = cv2.FONT_HERSHEY_SIMPLEX

# Initialize camera and perform object detection.
# The camera has to be set up and used differently depending on if it's a
# Picamera or USB webcam.

# I know this is ugly, but I basically copy+pasted the code for the object
# detection loop twice, and made one work for Picamera and the other work
# for USB.

### Picamera ###
if camera_type == 'picamera':
    # Initialize Picamera and grab reference to the raw capture
    camera = PiCamera()
    camera.resolution = (IM_WIDTH,IM_HEIGHT)
    camera.framerate = 100
    rawCapture = PiRGBArray(camera, size=(IM_WIDTH,IM_HEIGHT))
    rawCapture.truncate(0)

    for frame1 in camera.capture_continuous(rawCapture, format="bgr",use_video_port=True):

        t1 = cv2.getTickCount()

        # 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 = 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})

        #print('Boxes = ', boxes)
      #  if not np.all(boxes==0):
          #  print(boxes.shape)
        x=np.count_nonzero(boxes)
        print(x/8)
        # 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=0.70)

         #total_humans = total_humans + counter

        cv2.putText(frame,"FPS: {0:.2f}".format(frame_rate_calc),(30,50),font,1,(255,255,0),2,cv2.LINE_AA)

        # All the results have been drawn on the frame, so it's time to display it.
        cv2.imshow('Object detector', frame)

        t2 = cv2.getTickCount()
        time1 = (t2-t1)/freq
        frame_rate_calc = 1/time1

        # Press 'q' to quit
        if cv2.waitKey(1) == ord('q'):
            break

        rawCapture.truncate(0)

    camera.close()

### USB webcam ###
elif camera_type == 'usb':
    # Initialize USB webcam feed
    camera = cv2.VideoCapture(0)
    ret = camera.set(3,IM_WIDTH)
    ret = camera.set(4,IM_HEIGHT)
    c1=0
    c2=0
    while(True):

        t1 = cv2.getTickCount()

        # 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
        ret, frame = camera.read()
        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})
        if((int)(classes[0][0]) == 1):
        #print(boxes)
            s=(int)(boxes[:,[0]])*IM_HEIGHT

            if np.all(s == (int)(IM_HEIGHT/1.5)):
                c1=c1+1
            if np.all(s >= (int)(IM_HEIGHT/3.75)):
                if np.all(s == (int)(IM_HEIGHT/3.8)):
                    c1=c1-1
                    c2=c2+1
            elif np.all(s <= (int)(IM_HEIGHT/3.8)):
                if np.all(s == (int)(IM_HEIGHT/3.75)):
                    c2=c2-1
                    c1=c1+1
            print(s)
            print(c1)
            print(c2)
        #if not np.all(boxes==0):
         #   print(boxes.shape)
            x=np.count_nonzero(boxes)
            a=(x/4)
            c=math.floor(a)
        #print("No. of persons:")
        #print(c)
        # 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,
            )

        #print(counter)
        cv2.line(frame,(0,(IM_HEIGHT/3.75)),(650,(IM_HEIGHT/3.75)),(0,0,255),1)
        cv2.line(frame,(0,(IM_HEIGHT/3.8)),(650,(IM_HEIGHT/3.8)),(0,0,255),1)
        cv2.line(frame,(0,(IM_HEIGHT/1.5)),(650,(IM_HEIGHT/1.5)),(0,0,255),1)
        #cv2.line(frame,(325,0),(325,625),(0,0,255),2)
        cv2.putText(frame,"FPS: {0:.2f}".format(frame_rate_calc),(30,50),font,1,(255,255,0),2,cv2.LINE_AA)
        cv2.putText(frame,"Number of Persons: {0:.2f}".format(c),(30,90),font,1,(255,255,0),2,cv2.LINE_AA)

       # font = cv2.FONT_HERSHEY_SIMPLEX
        #        cv2.putText(
         ##          'Detected Humans: ' + str(total_humans),
           #         (10, 35),
            #        font,
             #       (0, 0xFF, 0xFF),
              #      2,
               ##    )

        # All the results have been drawn on the frame, so it's time to display it.
        cv2.imshow('Object detector', frame)

        t2 = cv2.getTickCount()
        time1 = (t2-t1)/freq
        frame_rate_calc = 1/time1

        # Press 'q' to quit
        if cv2.waitKey(1) == ord('q'):
            break

    camera.release()

cv2.destroyAllWindows()