Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
561 views

Object Detection Using TensorFlow

This document provides an overview of object detection with TensorFlow. It begins by defining object detection as identifying objects in images and localizing them with bounding boxes. Classical and deep learning approaches to object detection are discussed, including R-CNN, Fast R-CNN, YOLO, and Faster R-CNN. The TensorFlow Object Detection API is introduced for preparing data, training and evaluating models. CIFAR-10 is used as an example dataset. Key steps include creating TFRecords from annotated images and using the train.py and eval.py scripts. Applications of object detection discussed include facial recognition, self-driving cars, and security.

Uploaded by

Hari Vamshi
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
561 views

Object Detection Using TensorFlow

This document provides an overview of object detection with TensorFlow. It begins by defining object detection as identifying objects in images and localizing them with bounding boxes. Classical and deep learning approaches to object detection are discussed, including R-CNN, Fast R-CNN, YOLO, and Faster R-CNN. The TensorFlow Object Detection API is introduced for preparing data, training and evaluating models. CIFAR-10 is used as an example dataset. Key steps include creating TFRecords from annotated images and using the train.py and eval.py scripts. Applications of object detection discussed include facial recognition, self-driving cars, and security.

Uploaded by

Hari Vamshi
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

Object Detection with

Tensorflow

o D. HARI VAMSHI
o V. RAJU
o U. LAXMAN
Agenda

Ø Intro
Ø What  is  Object  Detection
Ø State of   Object  Detection
Ø Tensorflow Object Detection API
Ø Preparing Data
Ø Training & Evaluating Models
Ø Links
What is Object
Detection
Object detection is the
task of
identifying objects in an
image and drawing
bounding boxes around
them, i.e. localizing them.
It's a very important
problem in computer vision
due its numerous
applications from self-
driving cars to security and
tracking.
Object detection =
Object Classification + Object
Localization
Approache
s

▪ Classical approach (Haar features) -
first OD real time framework (Viola-Jones)
▪ Deep  learning  approach is a subset of machine
learning in artificial intelligence (AI) that has networks
capable of learning unsupervised from data that is
unstructured or unlabeled. Also known
as deep neural learning or deep neural network. Few of
the approaches used are: 
▪ OverFeat
▪ R-CNN
▪ Fast R-CNN
▪ YOLO
▪ Faster R-CNN
▪ SSD andR-FCN
Deep learning
approach
OverFeat -published in 2013, multi-scale
sliding window algorithm using Convolutional
Neural Networks (CNNs).

N.N - Regions with CNN features. Three


stage approach:
- Extract possible objects using a region
proposal method (the most popular one
being Selective Search).
- Extract features from each region using a
CNN.
- Classify each region with SVMs.
Deep learning
approach
Fast R-CNN - Similar to R-CNN, it used Selective 
Search to generate object proposals, but instead
of  extracting all of them independently and
using SVM  classifiers, it applies the CNN on the
complete image  and then used both Region of
Interest (RoI) Pooling  on the feature mapwith a
final feed forward network  for classification and
regression.

YOLO - You Only Look Once:


a simple convolutional neural
network approach which has
both great results and high
speed,allowing for the first
time real time object
detection.
Deep learning
approach
Faster R-CNN - Faster R-CNN added what
they called a Region Proposal Network
(RPN), in an attempt to get rid of the
Selective Search algorithm and make the
model completely trainable end-to-end.

SSD andR-FCN
Finally, there are two notable papers, Single Shot
Detector (SSD)which takes on YOLO by using
multiple sized convolutional feature maps
achieving better results and speed, and Region-
based Fully Convolutional Networks (R-FCN)
which takes the architecture of Faster R-CNN but
with only convolutionalnetworks.
Introduction
TensorFlow is a free and open-
source software library for
dataflow and differentiable
programming across a range of
tasks. It is a symbolic math
library, and is also used for
machine learning applications
such as neural networks. We
train and process the data
based on the help of
TensorFlow Object Detection
API.
Creating a
dataset
 We can either create a dataset of
our own or we can also consider
a predefined dataset and work on
the basis of TensorFlow package.

 The dataset being considered in


CIFAR 10
this project is CIFAR-10 which
consists of numerous pictures
used in detection classified in 10
classes.
Dataset

Ø Tensorflow  Object  Detection  API  uses 
 the  TFRecord  file format
Ø There    is   available  third-party    scripts 
 to  convert  PASCAL VOC and   Oxford   
 Pet Format
Ø In  other cases   explanation   of   format is 
    available in  git repo.
Ø Input data to create TFRecord - annotated
Image

The dataset being considered in this module is


CIFAR 10.
Creating
TFRecord
 TensorFlow object detection API report contains  folder dataset_tools 
with scripts to covert  common  structures  of  data  into TFRecord.

 The considered images can be formed into a TFrecord once the input file are
either an image or a jpg or png file which s stored in the form of records in
TensorFlow. 
Max-norm The maximum norm, also called max-norm or max-norm, is a popular constraint
because it is less aggressive than other norms such as the unit norm, simply setting an upper bound.

TRAINING DATA
One model for two
tasks?

Po - is object
exists
bx1
- bounding
bx2 box
Object detection -output is the one number (index) of coordinates
aclass by1

by2
c1

c2 - object’s
variables
c3
…
Object localization -output is the four
numbers - coordinates of bounding box. cn
Selecting a
model
Tensorflow OD API provides a
collection of  detection models pre-
trained on the COCO  dataset, the Kitti dataset, 
 and the Open Images  dataset.

- model name corresponds to a config file that
was used to train this model.
- speed -
running time in msper 600x600  image
- mAP stands for mean average precision,
which indicates how well the model
performed on the COCO dataset.
- Outputs types (Boxes, and Masks if  ap
plicable)
Training &
Evaluating
# From the tensorflow/models/research directory
python object_detection/train.py
--logtostderr
--
pipeline_config_path=/tensorflow/models/object_detection/samples/configs/ssd_mobilenet_v1_p
ets.config
--train_dir=${PATH_TO_ROOT_TRAIN_FOLDER}

# From the tensorflow/models/research directory


python object_detection/eval.py \
--logtostderr \
--pipeline_config_path=$
{PATH_TO_YOUR_PIPELINE_CONFIG} \
--checkpoint_dir=${PATH_TO_TRAIN_DIR} \
--eval_dir=${PATH_TO_EVAL_DIR}
Facial Recognition:
A deep learning facial recognition system called the
“DeepFace” has been developed by a group of researchers
in the Facebook, which identifies human faces in a digital
image very effectively. Google uses its own facial
recognition system in Google Photos, which automatically
segregates all the photos based on the person in the
image. There are various components involved in Facial
Recognition like the eyes, nose, mouth and the eyebrows.
Self Driving Cars:

Self-driving cars are the Future, there’s no doubt in


that. But the working behind it is very tricky as it
combines a variety of techniques to perceive their
surroundings, including radar, laser light, GPS,
odometry, and computer vision.
Advanced control systems interpret sensory
information to identify appropriate navigation
paths, as well as obstacles and once the image
sensor detects any sign of a living being in its
path, it automatically stops. This happens at a
very fast rate and is a big step towards Driverless
Cars.
Security: Object Detection plays a very important role in Security. Be it face ID of Apple or
the retina scan used in all the sci-fi movies.
It is also used by the government to access the security feed and match it with
their existing database to find any criminals or to detect the robbers’ vehicle.
The applications are limitless.
Link
s
▪ https://towardsdatascience.com/how-to-train-your-own-object-detector-with-

tensorflows-object-detector-api-bec72ecfe1d9
▪ https://www.kdnuggets.com/2017/10/deep-learning-object-detection-

comprehensive-review.html
▪ http://www.machinelearninguru.com/deep_learning/tensorflow/basics/tfrecord/tfreco

rd.html
▪ https://www.coursera.org/learn/convolutional-neural-networks
▪ https://medium.com/comet-app/review-of-deep-learning-algorithms-for-object-

detection-c1f3d437b852
▪ https://towardsdatascience.com/evolution-of-object-detection-and-localization-
algorithms-e241021d8bad
▪ https://medium.freecodecamp.org/how-to-play-quidditch-using-the-tensorflow-
ANY QUERIES!

You might also like