Scribd
Upload
3 views4 pages

CV Lab 9

jdggggggggggggjys

Uploaded by

faisalansari91919
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
3 views4 pages

CV Lab 9

jdggggggggggggjys

Uploaded by

faisalansari91919
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 4

DEPARTMENT OF INFORMATION TECHNOLOGY, QUEST NAWABSHAH

Computer Vision, 21 BS(AI) BATCH

Name: _____________________________ Roll No: __________________________________

Signature of Lab Tutor: ____________________ Date: ________________________________

LAB 9: Object Detection using Deep Learning

OBJECTIVES

After completion of this lab, students will be familiar with:


 Object Detection
 KerasCV a Deep Neural Network
 YOLO model
 Object Detection using a Pre-trained Model
 Training a Deep Neural Network for Object Detection

Introduction to Object Detection

Object detection is a technique that uses deep neural networks to localize and classify objects in
images. This computer vision task has a wide range of applications, from medical imaging to
self-driving cars. An object detection system will return the coordinates of the objects in an
image that it has been trained to recognize. The system will also return a confidence level, which
shows how confident the system is that a prediction is accurate. Object detection algorithms are
broadly classified into two categories based on how many times the same input image is passed
through a network.

KerasCV a Deep Neural Network

KerasCV is an extension of Keras for computer vision tasks. KerasCV includes pre-trained
models for popular computer vision datasets, such as ImageNet, COCO, and Pascal VOC, which

1
DEPARTMENT OF INFORMATION TECHNOLOGY, QUEST NAWABSHAH
Computer Vision, 21 BS(AI) BATCH
can be used for transfer learning. KerasCV also provides a range of visualization tools for
inspecting the intermediate representations learned by the model and for visualizing the results of
object detection and segmentation tasks.

YOLO model

YOLO (You Only Look Once) is a popular object detection model known for its speed and
accuracy. It was first introduced by Joseph Redmon et al. in 2016. It uses an end-to-end neural
network that makes predictions of bounding boxes and class probabilities all at once. Methods
that use Region Proposal Networks perform multiple iterations for the same image, while YOLO
gets away with a single iteration. Several new versions of the same model have been proposed
since the initial release of YOLO in 2015. The current version of YOLO is YOLOv10 released
on May 23, 2024.

The YOLO algorithm takes an image as input and then uses a simple deep convolutional neural
network to detect objects in the image. The architecture of the CNN model that forms the
backbone of YOLO is shown below.

Object Detection using a Pre-trained Model

KerasCV's object detection API

!pip install -q --upgrade keras-cv


!pip install -q --upgrade keras # Upgrade to Keras 3.

import os
os.environ["KERAS_BACKEND"] = "jax"

from tensorflow import data as tf_data


import tensorflow_datasets as tfds
import keras
import keras_cv
import numpy as np
from keras_cv import bounding_box
2
DEPARTMENT OF INFORMATION TECHNOLOGY, QUEST NAWABSHAH
Computer Vision, 21 BS(AI) BATCH
import os
from keras_cv import visualization
import tqdm

pretrained_model = keras_cv.models.YOLOV8Detector.from_preset(
"yolo_v8_m_pascalvoc", bounding_box_format="xywh")

#filepath = keras.utils.get_file('E:\\edges.jpg')
image = keras.utils.load_img('E:\\object_detection.png')
image = np.array(image)

visualization.plot_image_gallery(
np.array([image]),
value_range=(0, 255),
rows=1,
cols=1,
scale=5,
)

inference_resizing = keras_cv.layers.Resizing(
640, 640, pad_to_aspect_ratio=True, bounding_box_format="xywh"
)

image_batch = inference_resizing([image])

class_ids = [
"Aeroplane",
"Bicycle",
"Bird",
"Boat",
"Bottle",
"Bus",
"Car",
"Cat",
"Chair",
"Cow",
"Dining Table",
"Dog",
"Horse",
"Motorbike",
"Person",
"Potted Plant",
"Sheep",
"Sofa",
"Train",
"Tvmonitor",
"Total",
]

3
DEPARTMENT OF INFORMATION TECHNOLOGY, QUEST NAWABSHAH
Computer Vision, 21 BS(AI) BATCH
class_mapping = dict(zip(range(len(class_ids)), class_ids))

y_pred = pretrained_model.predict(image_batch)
# y_pred is a bounding box Tensor:
# {"classes": ..., boxes": ...}
visualization.plot_bounding_box_gallery(
image_batch,
value_range=(0, 255),
rows=1,
cols=1,
y_pred=y_pred,
scale=5,
font_scale=0.7,
bounding_box_format="xywh",
class_mapping=class_mapping,
)

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy