Dynamic Traffic Management System

# coding: utf-8

# # Object Detection Demo
# Welcome to the object detection inference walkthrough!  This notebook will walk you step by step through the process of using a pre-trained model to detect objects in an image. Make sure to follow the [installation instructions](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md) before you start.

# # Imports
import subprocess
import shutil
import numpy as np
import os
import openpyxl
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
from pathlib import Path
from matplotlib import pyplot as plt


from PIL import Image

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
from object_detection.utils import ops as utils_ops

if tf.__version__ < '1.4.0':
  raise ImportError('Please upgrade your tensorflow installation to v1.4.* or later!')

#import cv2
#cap = cv2.VideoCapture(0)

# ## Env setup

from utils import label_map_util

from utils import visualization_utils as vis_util


# # Model preparation 

# ## Variables
# 
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_FROZEN_GRAPH` to point to a new .pb file.  
# 
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.

single_image_name=sys.argv[1]

# What model to download.
# MODEL_NAME = 'faster_rcnn_nas_coco_2018_01_28'
MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

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

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

NUM_CLASSES = 90


# ## Download Model

# Check the frozen_inference_graph is exists at path.
# If not ssd_mobilenet_v1_coco_2017_11_17 model is downloaded and frozen_inference_graph.pb moved to path.
if os.path.exists(PATH_TO_FROZEN_GRAPH):
  # print("faster_rcnn_nas_coco_2018_01_28/frozen_inference_graph.pb Exists at path. Skipping download... ")
  print("ssd_mobilenet_v1_coco_2017_11_17/frozen_inference_graph.pb Exists at path. Skipping download... ")
  
else:
  opener = urllib.request.URLopener()
  opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
  tar_file = tarfile.open(MODEL_FILE)
  for file in tar_file.getmembers():
    file_name = os.path.basename(file.name)
    if 'frozen_inference_graph.pb' in file_name:
      tar_file.extract(file, os.getcwd())



# ## Load a (frozen) Tensorflow model into memory.

detection_graph = tf.compat.v1.Graph()
with detection_graph.as_default():
  od_graph_def = tf.compat.v1.GraphDef()
  with tf.io.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='')


# ## Loading label map
# Label maps map indices to category names, so that when our 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)


# # Detection
def load_image_into_numpy_array(image):
  (im_width, im_height) = image.size
  return np.array(image.getdata()).reshape(
      (im_height, im_width, 3)).astype(np.uint8)
  
  
def run_inference_for_single_image(image, graph):
  with graph.as_default():
    with tf.compat.v1.Session() as sess:
      # Get handles to input and output tensors
      ops = tf.compat.v1.get_default_graph().get_operations()
      all_tensor_names = {output.name for op in ops for output in op.outputs}
      tensor_dict = {}
      for key in [
          'num_detections', 'detection_boxes', 'detection_scores',
          'detection_classes', 'detection_masks'
      ]:
        tensor_name = key + ':0'
        if tensor_name in all_tensor_names:
          tensor_dict[key] = tf.compat.v1.get_default_graph().get_tensor_by_name(
              tensor_name)
      if 'detection_masks' in tensor_dict:
        # The following processing is only for single image
        detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
        detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
        # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
        real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
        detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
        detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
        detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
            detection_masks, detection_boxes, image.shape[0], image.shape[1])
        detection_masks_reframed = tf.cast(
            tf.greater(detection_masks_reframed, 0.5), tf.uint8)
        # Follow the convention by adding back the batch dimension
        tensor_dict['detection_masks'] = tf.expand_dims(
            detection_masks_reframed, 0)
      image_tensor = tf.compat.v1.get_default_graph().get_tensor_by_name('image_tensor:0')

      # Run inference
      output_dict = sess.run(tensor_dict,
                             feed_dict={image_tensor: np.expand_dims(image, 0)})

      # all outputs are float32 numpy arrays, so convert types as appropriate
      output_dict['num_detections'] = int(output_dict['num_detections'][0])
      output_dict['detection_classes'] = output_dict[
          'detection_classes'][0].astype(np.uint8)
      output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
      output_dict['detection_scores'] = output_dict['detection_scores'][0]
      if 'detection_masks' in output_dict:
        output_dict['detection_masks'] = output_dict['detection_masks'][0]
  return output_dict


PATH_TO_TEST_IMAGES_DIR = 'test_images'

#TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1,8) ]
# entries = Path('test_images/')
# lis = []
# for ent in entries.iterdir():
#   lis.append(os.path.join(PATH_TO_TEST_IMAGES_DIR,ent.name))

TEST_IMAGE_PATHS = [os.path.join(PATH_TO_TEST_IMAGES_DIR,single_image_name)]

for image_path in TEST_IMAGE_PATHS:
  image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image)
#while True:
  #ret, image_np = cap.read()
  # Actual detection.
  output_dict = run_inference_for_single_image(image_np, detection_graph)
  # Visualization of the results of a detection.
 # print(category_index)
  #print("----------",image_path,"------------")
 # print(output_dict)
  count = 0
  result = {}
  
  for data in output_dict['detection_scores']:
      count+=1
      if data > 0.5:
          #print(data," ",count," ",output_dict['detection_classes'][count-1])
          ans = (category_index[output_dict['detection_classes'][count-1]]['name']).upper()
          if ans in result.keys():
              result[ans]+=1
          else:
              result[ans]=1
    
  vis_util.visualize_boxes_and_labels_on_image_array(
      image_np,
      output_dict['detection_boxes'],
      output_dict['detection_classes'],
      output_dict['detection_scores'],
      category_index,
      instance_masks=output_dict.get('detection_masks'),
      use_normalized_coordinates=True,
      line_thickness=8)
  
  def cellval(sheet_obj,i,j,val):
    sheet_obj.cell(row=i,column=j).value=val

  def updateColumn(clm_lst,sheet_obj):
    mclm=sheet_obj.max_column
    print(mclm)
    for i in range(1,mclm+1):
      clm_name=sheet_obj.cell(row=1,column=i).value
      if clm_name in clm_lst:
        clm_lst.remove(clm_name)
      
    
    for i in range(1,len(clm_lst)+1):
      sheet_obj.cell(row=1,column=mclm+i).value=clm_lst[i-1].upper()

  def exl_write(path,result,time,intensity):
    wb_obj = openpyxl.load_workbook(path)
    sheet_obj = wb_obj.active
    sheet_obj.cell(row=1,column=1).value="NAME"
    sheet_obj.cell(row=1,column=2).value="TIME"
    sheet_obj.cell(row=1,column=3).value="INTENSITY"
    clm_lst=[]
    for key in result.keys():
      clm_lst.append(key)

    updateColumn(clm_lst,sheet_obj)
    # print(clm_lst)
    row_max=sheet_obj.max_row
    clm_with_inx={}
    # print(sheet_obj.max_column)
    for i in range(3,sheet_obj.max_column+1):
      clm_with_inx[sheet_obj.cell(row=1,column=i).value]=i
    
    
    
    sheet_obj.cell(row=1+row_max,column=2).value=time
    sheet_obj.cell(row=1+row_max,column=3).value=intensity
    # for k,v in clm_with_inx.items():
    #   print(k+" "+str(v))
    inx=1+row_max
    cellval(sheet_obj,inx,1,image_path[-10:])
    for key,val in result.items():
      cellval(sheet_obj,inx,clm_with_inx[key],val)
    
    wb_obj.save(path)

  def cal_time(result):
    car=0
    truck=0
    bike=0
    if "CAR" in result.keys():
      car=result["CAR"]
    if "TRUCK" in result.keys():
      truck=result["TRUCK"]
    if "BUS" in result.keys():
      truck=truck+result["BUS"]
    if "MOTORBIKE" in result.keys():
      bike=result["MOTORBIKE"]

    time=((81/14.0)*car+(69/14.0)*truck+(30/7.0)*bike)
    return round(time)

    
  title=""
  for key,val in result.items():
      title+=(key+"-"+str(val)+"\n")
  
    ##plt.figure(figsize=(16, 9))
#   plt.imshow(image_np)
  
  img = Image.fromarray(image_np)
  img.save('output\\output_'+image_path[-10:])
  img.save('C:\\xampp\\htdocs\\output\\output_'+image_path[-10:])
  
  time=cal_time(result)
  intensity=""
  if time<15:
    time=15
    intensity='VERY LOW TRAFFIC (0-15) seconds\n'
  elif time<=60:
    intensity='LOW TRAFFIC (15-60) seconds\n'
  elif time<=120:
    intensity='MEDIUM TRAFFIC (60-120) seconds\n'
  elif time<=180:
    intensity='HIGH TRAFFIC (120-180) seconds\n'    
  elif time<=240:
    intensity='VERY HIGH TRAFFIC (180-240) seconds\n'
  elif time>240:
    time=240
    intensity='IMMENSE TRAFFIC (>240) seconds\n'
  
  log='logs\\log_'+ image_path[-10:-3]+'txt';
  file=open(log,"w")
  file.write(str(time)+"\n"+intensity+"\n"+title)
  file.close()  
  exl_write("G:/Tut/models/research/object_detection/history/data.xlsx",result,time,intensity)
  # subprocess.Popen('G:/Tut/models/research/object_detection/clean_dir.bat')
  # if single_image_name == "image1.jpg":
  #   shutil.copy("cp/log_image1.txt","Logs")
  #   shutil.copy("cp/output_image1.jpg","output")
  #   shutil.copy("cp/output_image1.jpg","C:/xampp/htdocs/output")

  # if single_image_name == "image2.jpg":
  #   shutil.copy("cp/log_image2.txt","Logs")
  #   shutil.copy("cp/output_image2.jpg","output")
  #   shutil.copy("cp/output_image2.jpg","C:/xampp/htdocs/output")


  
  shutil.copy("cp/data.xlsx","history")
  for ent in TEST_IMAGE_PATHS:
    os.remove(ent)
  


  # file=open('history\\data.txt',"a")
  # hist="-------------------"
  # hist+="\nName : " + image_path[-10:]
  # title=title.replace("-","")
  # hist+=title
  # file.write(hist)
  # file.close()     
#  plt.title(title, fontdict = {'fontsize' : 50})
  
      
'''  cv2.imshow('Image Detction', cv2.resize(image_np, (100,200)))
  if cv2.waitKey(25) & 0xFF == ord('q'):
    cv2.destroyAllWindows()
    break
'''