Book Image

Practical Computer Vision

By : Abhinav Dadhich
Book Image

Practical Computer Vision

By: Abhinav Dadhich

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.
Table of Contents (12 chapters)

Introduction to object detection

To begin with object detection, we will first see an overview of image recognition as detection is one part of it. In the following figure, an overview of object recognition is described using an image from Pascal VOC dataset. The input is passes through a model which then produces information in four different styles:

The model in the previous image performs generic image recognition where we can predict the following information:

  • A class name for the object in the image
  • Object center pixel location
  • A bounding box surrounding the object as output
  • In instance image where each pixel is classified into a class. The classes are for object as well as background

When we say object detection, we are usually referring to the first and third type of image recognition. Our goal is to estimate class names as well as bounding box surrounding target objects...