Hands-On Vision and Behavior for Self-Driving Cars: Explore visual perception, lane detection, and object classification with Python 3 and OpenCV 4

Venturi

Korda

$34.99 ~~$38.99~~

3.3 (3 Ratings)

eBook Oct 2020 374 pages 1st Edition

Venturi

Korda

$34.99 ~~$38.99~~

3.3 (3 Ratings)

eBook Oct 2020 374 pages 1st Edition

What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

View table of contents

Preview Book

Download Code

Key benefits

Explore the building blocks of the visual perception system in self-driving cars
Identify objects and lanes to define the boundary of driving surfaces using open-source tools like OpenCV and Python
Improve the object detection and classification capabilities of systems with the help of neural networks

Description

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.

Who is this book for?

This book is for software engineers who are interested in learning about technologies that drive the autonomous car revolution. Although basic knowledge of computer vision and Python programming is required, prior knowledge of advanced deep learning and how to use sensors (lidar) is not needed.

What you will learn

Understand how to perform camera calibration
Become well-versed with how lane detection works in self-driving cars using OpenCV
Explore behavioral cloning by self-driving in a video-game simulator
Get to grips with using lidars
Discover how to configure the controls for autonomous vehicles
Use object detection and semantic segmentation to locate lanes, cars, and pedestrians
Write a PID controller to control a self-driving car running in a simulator

What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

$65.99

$54.99

Applied Deep Learning and Computer Vision for Self-Driving Cars

$48.99

Total $ 169.97

Shane Lee Jan 09, 2021

What I like:1. This book covers very well and detail use of open source libraries and tools, on OpenCV and NumPy, especially on the coding and development environment setup.2. This books uses pictures to illustrate a topic whenever possible, this is very helpful in the domain of perception and camera based image processing.What I don't like:1. It is short of mathematical fundamentals, in my view, every domain, and chapter covers the goal of solving self-driving technology, should have a corresponding mathematical equations, or models to begin with, before jumping to the use of open source library, or coding. This will really help readers embrace the understanding of the technologies.2. On the mapping and SLAM part, it lacks some of the real scenarios, and problems that needs to be solved in order to benefit the self-driving.What I would like to see:1. It would be great to extend the full details of using open source tools, to cover a balance of 3 pillars - 1) Real-time object detection and perception, 2) real-time absolute positioning with GNSS, and 3)HD mapping.Even though today no one is really covering well on these 3 pillars strongly and tightly enough to render a robust self-driving engine yet, but it is essential to have before we reach the all-weather, all-time, all scenarios self-driving world.

Amazon Verified review

Amazon Customer Jan 11, 2021

What I like: This book is a introductory manual into self driving cars. It basically explains what is what like the module in vision which has the basic pipe line for predicting lanes. If you are working on a similar problem it’s better to have this book handy so that you can figure out what to do next. All the other modules are helpful as well like the one which explains signals can how to read them. This particular section I found is very useful as a controls engineer myself I find myself working with different type of communication interfaces like CAN, SPI etcThis book can also be used as a reference for self driving car course by udacity.What Ibwould like to see: more in depth mathematical proofs and applications for different concepts

John Smith Aug 25, 2022

Consider this line of code from chapter 1 about camera calibration:corners = cv2.cornerSubPix(img_src, corners, (11, 11), (-1, -1), (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001))what is (11,11) or what is (-1,-1). There is absolutely no explanation and you have to consult OpenCV documentation all the time.When I buy a book like this, I expect the author to provide an explanation for all those arguments so that I can save time.It seems OpenCV documentation is more complete and easier to follow.

Hands-On Vision and Behavior for Self-Driving Cars: Explore visual perception, lane detection, and object classification with Python 3 and OpenCV 4

What do you get with eBook?