Survey conducted and the code used

Survey conducted and the code used

The Automatic Trash Bin

Year Two Group Project, University of Liverpool, Electrical and Electronics Engineering Department.

The developments of this project were supervised by Dr. James Bradley

The Group members are

Haoran Cheng, Xuhui Gong, Shekhah Mobarak, A-ro Han

In this section of the blog you will find the survey that was conducted by the group along with the code used for the entire project.
The questions of the survey are written below;
1. Do you think that recycling helps preserve the environment?

- Yes

- No

- If you chose no, please explain why?

2. Do you tend to recycle often?

- Yes

- Sometimes

- No

- If you chose no, please explain why?

3. In your opinion what do you think happens if recycling is not promoted?

4. Do you think the recycling system nowadays (color codes) is straightforward and comprehensible?

- Yes

- No

- If you chose no, please explain why?

5. Do you think an automatic sorting bin may ease the operation of recycling?

- Yes

- No

- If you chose no, please explain why?

6. Would you buy an automatic sorting bin?

- Yes

- No

- If you chose no, please explain why?

7. If you were to design this product what would you include?

- Motion detector for cover

- AI voice to y3ln what object has been thrown into the bin

- Brail instructions of the sides of the bin for the visually impaired

- Screen to show identification of object

- Easy dispensing of the rubbish

- Other

Screenshots of the survey

As for the codes which are used to operate the system.

There were four main codes;

test.py

import keras

import shutil

import tensorflow as tf

import sys

import os

import argparse

import datetime

import time

import cv2

import numpy as np

def sort():

Cans = 0

Paper = 0

Plastic_Bottle = 0

# lists all files to be tested in test_input folder

list_images = os.listdir(image_path)

with tf.compat.v1.Session() as sess:

for igs in list_images:

# load the image data

image_data = tf.compat.v1.gfile.FastGFile(image_path + igs, 'rb').read()

# Feed the image_data as input to the graph and get first prediction

softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')

predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})

# Sort to show labels of first prediction in order of confidence

top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]

# print('\n' + igs + ' :')

human_string = label_lines[0]

score = predictions[0][0]

# print('%s (score = %.5f)' % (human_string, score))

if human_string == "cans" and score >= 0.65:

Cans += 1

elif human_string == "paper" and score >= 0.97:

Paper += 1

elif human_string == "plastic bottle" and score >= 0.65:

Plastic_Bottle += 1

print(Cans)

print(Paper)

print(Plastic_Bottle)

if Cans > Paper and Cans > Plastic_Bottle:

print("can")

elif Paper > Cans and Paper > Plastic_Bottle:

print("paper")

elif Plastic_Bottle > Cans and Plastic_Bottle > Paper:

print("plastic_bottle")

def detect():

# construct the argument parser and parse the arguments

ap = argparse.ArgumentParser()

ap.add_argument("-v", "--video", help="path to the video file")

ap.add_argument("-a", "--min-area", type=int, default=1000, help="minimum area size")

args = vars(ap.parse_args())

# if the video argument is None, then we are reading from webcam

if args.get("video", None) is None:

camera = cv2.VideoCapture(0)

time.sleep(0.25)

# otherwise, we are reading from a video file

else:

camera = cv2.VideoCapture(args["video"])

# initialize the first frame in the video stream

firstFrame = None

# Define the codec

fourcc = cv2.VideoWriter_fourcc('X', 'V', 'I', 'D')

framecount = 0

frame = np.zeros((640, 480))

out = cv2.VideoWriter(

'./videos/' + 'calm_down_video_' + datetime.datetime.now().strftime("%A_%d_%B_%Y_%I_%M_%S%p") + '.avi', fourcc,

5.0, np.shape(frame))

# to begin with, the light is not stable, calm it down

tc = 40

while tc:

ret, frame = camera.read()

out.write(frame)

# cv2.imshow("vw",frame)

cv2.waitKey(10)

tc -= 1

totalc = 2000

tc = totalc

out.release()

# loop over the frames of the video

while True:

# grab the current frame and initialize the occupied/unoccupied

# text

(grabbed, frame) = camera.read()

text = "Unoccupied"

# if the frame could not be grabbed, then we have reached the end

# of the video

if not grabbed:

time.sleep(0.25)

continue

# resize the frame, convert it to grayscale, and blur it

# frame = imutils.resize(frame, width=500)

gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

gray = cv2.GaussianBlur(gray, (21, 21), 0)

# update firstFrame for every while

if tc % totalc == 0:

firstFrame = gray

tc = (tc + 1) % totalc

continue

else:

tc = (tc + 1) % totalc

# print tc

# compute the absolute difference between the current frame and

# first frame

frameDelta = cv2.absdiff(firstFrame, gray)

thresh = cv2.threshold(frameDelta, 25, 255, cv2.THRESH_BINARY)[1]

# dilate the thresholded image to fill in holes, then find contours

# on thresholded image

thresh = cv2.dilate(thresh, None, iterations=2)

# _, cnts, _ = cv2.findContours(thresh.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)

contours, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2:]

# _, contours, _ = cv2.findContours(skin_ycrcb, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# loop over the contours

for c in contours:

print(framecount)

# if the contour is too small, ignore it

if cv2.contourArea(c) < args["min_area"]:

continue

# compute the bounding box for the contour, draw it on the frame,

# and update the text

(x, y, w, h) = cv2.boundingRect(c)

cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)

text = "Occupied"

# draw the text and timestamp on the frame

cv2.putText(frame, "Monitoring Area Status: {}".format(text), (10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5,

(0, 0, 255), 2)

cv2.putText(frame, datetime.datetime.now().strftime("%A %d %B %Y %I:%M:%S%p"), (10, frame.shape[0] - 10),

cv2.FONT_HERSHEY_SIMPLEX, 0.35, (0, 0, 255), 1)

# show the frame and record if the user presses a key

cv2.imshow("Security Feed", frame)

cv2.imshow("Thresh", thresh)

cv2.imshow("Frame Delta", frameDelta)

# save the detection result

if text == "Occupied":

if framecount == 0:

# # create VideoWriter object

# out = cv2.VideoWriter('./videos/' + datetime.datetime.now().strftime("%A_%d_%B_%Y_%I_%M_%S%p") + '.avi',

# fourcc, 10.0, np.shape(gray)[::-1])

# cv2.imwrite('./images/' + datetime.datetime.now().strftime("%A_%d_%B_%Y_%I_%M_%S%p") + '.jpg', frame)

# # write the flipped frame

# out.write(frame)

framecount += 1

elif framecount > 200:

break

else:

# write the flipped frame

out.write(frame)

if framecount % 10 == 0:

cv2.imwrite('./images/' + datetime.datetime.now().strftime("%A_%d_%B_%Y_%I_%M_%S%p") + '.jpg',

frame)

framecount += 1

elif framecount < 200 and framecount > 1:

# write the flipped frame

out.write(frame)

# if framecount%10 == 0:

cv2.imwrite('./images/'+datetime.datetime.now().strftime("%A_%d_%B_%Y_%I_%M_%S%p")+'.jpg',frame)

framecount += 1

key = cv2.waitKey(1) & 0xFF

# if the `ESC` key is pressed, break from the lop

if key == 27:

break

# cleanup the camera and close any open windows

camera.release()

cv2.destroyAllWindows()

def clear():

shutil.rmtree("/Users/xg/Desktop/DL-wastesort-master-2/images")

os.mkdir("/Users/xg/Desktop/DL-wastesort-master-2/images")

def loop():

while True:

detect()

sort()

clear()

if __name__ == '__main__':

# Disable tensorflow compilation warnings

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

image_path = '/Users/xg/Desktop/DL-wastesort-master-2/images/'

# Loads label file, strips off carriage return

label_lines = [line.rstrip() for line

in tf.compat.v1.io.gfile.GFile("tf_files/retrained_labels.txt")]

# Unpersists graph from file

with tf.compat.v1.gfile.FastGFile("tf_files/retrained_graph.pb", 'rb') as f:

graph_def = tf.compat.v1.GraphDef()

graph_def.ParseFromString(f.read())

_ = tf.import_graph_def(graph_def, name='')

try:

loop()

except KeyboardInterrupt:

sys.exit()

train.sh

python3 retrain.py \

--bottleneck_dir=tf_files/bottlenecks \

--how_many_training_steps=6000 \

--model_dir=inception \

--summaries_dir=tf_files/training_summaries/basic \

--output_graph=tf_files/retrained_graph.pb \

--output_labels=tf_files/retrained_labels.txt \

--image_dir=training_dataset

wastesort.py

import keras

import tensorflow as tf

import sys

import os

# Disable tensorflow compilation warnings

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

image_path = '/Users/xg/Desktop/DL-wastesort-master-2/test_input/'

# Loads label file, strips off carriage return

label_lines = [line.rstrip() for line

in tf.compat.v1.io.gfile.GFile("tf_files/retrained_labels.txt")]

# Unpersists graph from file

with tf.compat.v1.gfile.FastGFile("tf_files/retrained_graph.pb", 'rb') as f:

graph_def = tf.compat.v1.GraphDef()

graph_def.ParseFromString(f.read())

_ = tf.import_graph_def(graph_def, name='')

# lists all files to be tested in test_input folder

list_images = os.listdir(image_path)

with tf.compat.v1.Session() as sess:

for igs in list_images:

# load the image data

image_data = tf.compat.v1.gfile.FastGFile(image_path + igs, 'rb').read()

# Feed the image_data as input to the graph and get first prediction

softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')

predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})

# Sort to show labels of first prediction in order of confidence

top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]

print('\n' + igs + ' :')

for node_id in top_k:

human_string = label_lines[node_id]

score = predictions[0][node_id]

print('%s (score = %.5f)' % (human_string, score))

# if __name__ == '__main__':

#

ImageAugmenter.py

# import imgaug as ia

# from imgaug import augmenters as iaa

# import numpy as np

# import imageio

# import cv2

# from skimage.io import imread_collection

# ia.seed(1)

#

# # path= '/Volumes/MDisk/dataset/test_data/*.jpg'

# # img=imread_collection(path)

# img = imageio.imread("/Volumes/MDisk/dataset/test_data/test.jpg") #read you image

#

# print(img)

# images = np.array(

# [img for _ in range(32)], dtype=np.uint8) # 32 means creat 32 enhanced images using following methods.

#

# seq = iaa.Sequential(

# [

# iaa.Fliplr(0.5),

# iaa.Crop(percent=(0, 0.1)),

# iaa.Sometimes(0.5, iaa.GaussianBlur(sigma=(0, 0.5))),

# iaa.ContrastNormalization((0.75, 1.5)),

# iaa.AdditiveGaussianNoise(

# loc=0, scale=(0.0, 0.05 * 255), per_channel=0.5),

# iaa.Multiply((0.8, 1.2), per_channel=0.2),

# iaa.Affine(

# scale={

# "x": (0.8, 1.2),

# "y": (0.8, 1.2)

# },

# translate_percent={

# "x": (-0.2, 0.2),

# "y": (-0.2, 0.2)

# },

# rotate=(-25, 25),

# shear=(-8, 8))

# ],

# random_order=True) # apply augmenters in random order

#

# images_aug = seq.augment_images(images)

#

# for i in range(32):

# imageio.imwrite(str(i)+'new.jpg', images_aug[i]) #write all changed images

#

import matplotlib

from imgaug import augmenters as iaa

import numpy as np

import imageio

import cv2

from pasta.augment import inline

from skimage.io import imread_collection

import imgaug as ia

from imgaug import augmenters as iaa

import numpy as np

import imageio

from glob import glob

import matplotlib.pyplot as plt

import cv2

import scipy.misc

def get_img(img_paths, img_size):

X = np.zeros((len(img_paths), img_size, img_size, 3), dtype=np.uint8)

i = 0

for img_path in img_paths:

img = cv2.imread(img_path)

img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

img = cv2.resize(img, (img_size, img_size), interpolation=cv2.INTER_AREA)

X[i, :, :, :] = img

i += 1

return X

def get_X_batch(X_path, batch_size, img_size):

while 1:

for i in range(0, len(X_path), batch_size):

X = get_img(X_path[i:i + batch_size], img_size)

yield X

if __name__ == '__main__':

img_paths = glob('/Volumes/MDisk/dataset/test_data/*.jpg') # 得到所有图片的路径列表

print(img_paths)

images = get_X_batch(img_paths, 16, 300) # 得到一个batch的图片，形式为generator

images = next(images) # next(generator)，得到一个batch的ndarray

ia.seed(1)

seq = iaa.Sequential([

iaa.Fliplr(0.5), # 0.5的概率水平翻转

iaa.Crop(percent=(0, 0.1)), # random crops

# sigma在0~0.5间随机高斯模糊，且每张图纸生效的概率是0.5

iaa.Sometimes(0.5,

iaa.GaussianBlur(sigma=(0, 0.5))

),

# 增大或减小每张图像的对比度

iaa.ContrastNormalization((0.75, 1.5)),

# 高斯噪点

iaa.AdditiveGaussianNoise(loc=0, scale=(0.0, 0.05 * 255), per_channel=0.5),

# 给每个像素乘上0.8-1.2之间的数来使图片变暗或变亮

# 20%的图片在每个channel上乘以不同的因子

iaa.Multiply((0.8, 1.2), per_channel=0.2),

# 对每张图片进行仿射变换，包括缩放、平移、旋转、修剪等

iaa.Affine(

scale={"x": (0.8, 1.2), "y": (0.8, 1.2)},

translate_percent={"x": (-0.2, 0.2), "y": (-0.2, 0.2)},

rotate=(-90, 90),

shear=(-8, 8)

)

], random_order=True) # 随机应用以上的图片增强方法

images_aug = seq.augment_images(images) # 得到增强后的图片ndarray

print((len(images_aug)))

for i in range(len(images_aug)):

imageio.imwrite(str(i)+'new.jpg', images_aug[i]) #write all changed images

Comments