Hands-On Vision and Behavior for Self-Driving Cars

Chapter 7: Detecting Pedestrians and Traffic Lights

Congratulations on covering deep learning and progressing to this new section! Now that you know the basics of how to build and tune neural networks, it is time to move toward more advanced topics.

If you remember, in Chapter 1, OpenCV Basics and Camera Calibration, we already detected pedestrians using OpenCV. In this chapter, we will learn how to detect objects using a very powerful neural network called Single Shot MultiBox Detector (SSD), and we will use it to detect not only pedestrians but also vehicles and traffic lights. In addition, we will train a neural network to detect the color of the traffic lights using transfer learning, a powerful technique that can help you achieve good results ...