Book Image

Hands-On Vision and Behavior for Self-Driving Cars

By : Luca Venturi, Krishtof Korda
Book Image

Hands-On Vision and Behavior for Self-Driving Cars

By: Luca Venturi, Krishtof Korda

Overview of this book

The visual perception capabilities of a self-driving car are powered by computer vision. The work relating to self-driving cars can be broadly classified into three components - robotics, computer vision, and machine learning. This book provides existing computer vision engineers and developers with the unique opportunity to be associated with this booming field. You will learn about computer vision, deep learning, and depth perception applied to driverless cars. The book provides a structured and thorough introduction, as making a real self-driving car is a huge cross-functional effort. As you progress, you will cover relevant cases with working code, before going on to understand how to use OpenCV, TensorFlow and Keras to analyze video streaming from car cameras. Later, you will learn how to interpret and make the most of lidars (light detection and ranging) to identify obstacles and localize your position. You’ll even be able to tackle core challenges in self-driving cars such as finding lanes, detecting pedestrian and crossing lights, performing semantic segmentation, and writing a PID controller. By the end of this book, you’ll be equipped with the skills you need to write code for a self-driving car running in a driverless car simulator, and be able to tackle various challenges faced by autonomous car engineers.
Table of Contents (17 chapters)
1
Section 1: OpenCV and Sensors and Signals
5
Section 2: Improving How the Self-Driving Car Works with Deep Learning and Neural Networks
12
Section 3: Mapping and Controls

Chapter 6: Improving Your Neural Network

In Chapter 4, Deep Learning with Neural Networks, we designed a network that is able to achieve almost 93% accuracy in the training dataset, but that translated to less than 66% accuracy in the validation dataset.

In this chapter, we will continue working on that neural network, with the aim to improve the validation accuracy significantly. Our goal is to reach at least 80% validation accuracy. We will apply some of the knowledge acquired in Chapter 5, Deep Learning Workflow, and we will also learn new techniques that will help us very much, such as batch normalization.

We will cover the following topics:

  • Reducing the number of parameters
  • Increasing the size of the network and the number of layers
  • Understanding batch normalization
  • Improving validation with early stopping
  • Virtually increasing the dataset size with data augmentation
  • Improving validation accuracy with dropout
  • Improving validation accuracy with...