Multiple Object Recognition and Detection
Multiple object recognition and detection involves detecting and recognizing several objects within an image. This task involves labeling every single object with a bounding box and then recognizing the type of that object.
Because of this, there are many available pre-trained models that detect a lot of objects. The neural network called YOLO is one of the best models for this specific task and works in real time. YOLO will be explained in depth in the next chapter for the development of the simulator for the robot.
For this chapter, the YOLO network that we want to use is trained to recognize and detect 80 different classes. These classes are:
person, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light, fire hydrant, stop_sign, parking meter, bench, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, ...
