Advanced Deep Learning with Python

Moving object detection and tracking

We now have an idea of what sensors the vehicle uses, and we have briefly mentioned the importance of knowing its exact location on the map. With this knowledge, the vehicle could theoretically navigate to its destination by simply following a breadcrumb trail of fine-grained points. However, the task of autonomous driving isn't that simple, because the environment is dynamic, as it includes moving objects such as vehicles, pedestrians, cyclists, and so on. An autonomous vehicle must constantly know the positions of the moving objects and track them as it plans its trajectory. This is one area where we can apply deep-learning algorithms to the raw sensor data. First, we'll do this for the camera. In