Scribd
Upload
9 views3 pages

Experiment 8

Uploaded by

Jeevika D.k
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
9 views3 pages

Experiment 8

Uploaded by

Jeevika D.k
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

8.

Car detection using YOLO

Procedure

1. Open google colabarotary.


2. Import necessary packages like numpy, pandas and CV2.
3. Load the car images dataset from kaggle.(testing, training and training_bounding_boxes).
4. Provide bounding boxes for car image accordingly.
5. Implement data generator to train and test the car images.
6. Display images with grid.
7. Now car object is detected.
.

Program Coding
Data Manipulation
import numpy as np
import pandas as pd

# Visualization/Image Processing
import cv2
import matplotlib.pyplot as plt

# Machine Learning
import tensorflow as tf
from tensorflow.keras.layers import Conv2D, Input, BatchNormalization, Flatten, MaxPool2D,
Dense

# Other
from pathlib import Path
train_path = Path("car_detection/data/training_images")
test_path = Path("car_detection/data/testing_images")

train = pd.read_csv("train_solution_bounding_boxes (1).csv")


train[['xmin', 'ymin', 'xmax', 'ymax']] = train[['xmin', 'ymin', 'xmax', 'ymax']].astype(int)
train.drop_duplicates(subset='image', inplace=True, ignore_index=True)
file = pd.read_csv('train_solution_bounding_boxes (1).csv')
file['label'] = 'car'
print(file)

def display_image(img, bbox_coords=[], pred_coords=[], norm=False):


# if the image has been normalized, scale it up
if norm:
img *= 255.
img = img.astype(np.uint8)
# Draw the bounding boxes
if len(bbox_coords) == 4:
xmin, ymin, xmax, ymax = bbox_coords
img = cv2.rectangle(img, (int(xmin), int(ymin)), (int(xmax), int(ymax)), (0, 255, 0), 3)

if len(pred_coords) == 4:
xmin, ymin, xmax, ymax = pred_coords
img = cv2.rectangle(img, (int(xmin), int(ymin)), (int(xmax), int(ymax)), (255, 0, 0), 3)

plt.imshow(img)
plt.xticks([])
plt.yticks([])

def display_image_from_file(name, bbox_coords=[], path=train_path):


img = cv2.imread(str(path/name))
display_image(img, bbox_coords=bbox_coords)

def display_from_dataframe(row, path=train_path):


display_image_from_file(row['image'], bbox_coords=(row.xmin, row.ymin, row.xmax,
row.ymax), path=path)

def display_grid(df=train, n_items=3):


plt.figure(figsize=(20, 10))

# get 3 random entries and plot them in a 1x3 grid


rand_indices = [np.random.randint(0, df.shape[0]) for _ in range(n_items)]

for pos, index in enumerate(rand_indices):


plt.subplot(1, n_items, pos + 1)
display_from_dataframe(df.loc[index, :])

display_image_from_file("vid_4_10520.jpg")
display_grid()
def data_generator(df=train, batch_size=16, path=train_path):
while True:
images = np.zeros((batch_size, 380, 676, 3))
bounding_box_coords = np.zeros((batch_size, 4))

for i in range(batch_size):
rand_index = np.random.randint(0, train.shape[0])
row = df.loc[rand_index, :]
images[i] = cv2.imread(str(train_path/row.image)) / 255.
bounding_box_coords[i] = np.array([row.xmin, row.ymin, row.xmax, row.ymax])

yield {'image': images}, {'coords': bounding_box_coords}


example, label = next(data_generator(batch_size=1))
img = example['image'][0]
bbox_coords = label['coords'][0]

display_image(img, bbox_coords=bbox_coords, norm=True)

OUTPUT

You might also like