In the chapters on building a deep convolutional neural network and transfer learning, we have learned about detecting the class that an image belongs to using deep CNN and also by leveraging transfer learning.
While object classification works, in the real world, we will also be encountering a scenario where we would have to locate the object within an image.
For example, in the case of a self-driving car, we would not only have to detect that a pedestrian is in the view point of a car, but also be able to detect how far the pedestrian is located away from the car so that an appropriate action can then be taken.
In this chapter, we will be discussing the various techniques of detecting objects in an image. The case studies we will be covering in this chapter are as follows:
- Creating the training dataset of bounding box
- Generating region...
