Practical Computer Vision

By : Abhinav Dadhich

1.5 (2)

Buy this Book

Practical Computer Vision

1.5 (2)

By: Abhinav Dadhich

Buy this Book

Overview of this book

In this book, you will find several recently proposed methods in various domains of computer vision. You will start by setting up the proper Python environment to work on practical applications. This includes setting up libraries such as OpenCV, TensorFlow, and Keras using Anaconda. Using these libraries, you'll start to understand the concepts of image transformation and filtering. You will find a detailed explanation of feature detectors such as FAST and ORB; you'll use them to find similar-looking objects. With an introduction to convolutional neural nets, you will learn how to build a deep neural net using Keras and how to use it to classify the Fashion-MNIST dataset. With regard to object detection, you will learn the implementation of a simple face detector as well as the workings of complex deep-learning-based object detectors such as Faster R-CNN and SSD using TensorFlow. You'll get started with semantic segmentation using FCN models and track objects with Deep SORT. Not only this, you will also use Visual SLAM techniques such as ORB-SLAM on a standard dataset. By the end of this book, you will have a firm understanding of the different computer vision techniques and how to apply them in your applications.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

A Fast Introduction to Computer Vision

What constitutes computer vision?

Computer vision is everywhere

Getting started

Computer vision research conferences

Summary

Libraries, Development Platform, and Datasets

Libraries and installation

Datasets

Summary

References

Image Filtering and Transformations in OpenCV

Datasets and libraries required

Image manipulation

Introduction to filters

Transformation of an image

Image pyramids

Summary

What is a Feature?

Features use cases

Harris Corner Detection

Summary

References

Convolutional Neural Networks

Datasets and libraries used

Introduction to neural networks

Revisiting the convolution operation

Convolutional Neural Networks

CNN in practice

Summary

Feature-Based Object Detection

Introduction to object detection

Challenges in object detection

Dataset and libraries used

Methods for object detection

Summary

References

Segmentation and Tracking

Datasets and libraries

Segmentation

Tracking

Summary

References

3D Computer Vision

Dataset and libraries

Applications

Image formation

Aligning images

Visual odometry

Visual SLAM

Summary

References

Mathematics for Computer Vision

Datasets and libraries

Linear algebra

Introduction to probability theory

Summary

Machine Learning for Computer Vision

What is machine learning?

Kinds of machine learning techniques

Dimensionality's curse

A rolling-ball view of learning

Useful tools

Evaluation

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

1.5 (2)

5 star

4 star

3 star

2 star

50%

1 star

50%

Visual SLAM

SLAM refers to Simultaneous Localization and Mapping and is one of the most common problems in robot navigation. Since a mobile robot does not have hardcoded information about the environment around itself, it uses sensors onboard to construct a representation of the region. The robot tries to estimate its position with respect to objects around it like trees, building, and so on. This is, therefore, a chicken-egg problem, where the robot first tries to localize itself using objects around it and then uses its obtained location to map objects around it; hence the term Simultaneous Localization and Mapping. There are several methods for solving the SLAM problem. In this section, we will discuss special types of SLAM using a single RGB camera.

Visual SLAM methods extend visual odometry by computing a more robust camera trajectory as well as constructing a robust representation...