0
$\begingroup$

In autonomous driving, we know that the behaviour prediction module is concerned with understanding how the agents in the environment will behave. Similarly, in the perception module, the tracking algorithms are responsible for getting an estimate of the object's state over time.

$\endgroup$
1
  • $\begingroup$ Can you please provide a link to a reference that says that autonomous vehicles are equipped with a "behaviour prediction module" and a "perception module", which makes you think that they are different? Note that I'm not saying that this is or not the case. I just think that this post is not fully clear, especially because I don't immediately see the connection between what you wrote in the title and in the body of your post. Can you please connect the two in a clearer way? $\endgroup$ – nbro Dec 8 '20 at 17:22
0
$\begingroup$

Although both processes might be doing estimations (because data sources aren't perfect and/or have noise), there is a key difference:

  • Object tracking cares solely abouth where objects are now. That means that there is actual sensor data that can support the current position. For example: from a camera and a lidar, the computer predicts where a vehicle stands.

  • Trajectory prediction is done with the main purpose of predicting where objects will be in the future, meaning that there is no sensor data yet. For example: from past data, the computer predicts where a vehicle will be after 1 second from now.

However, both processes might need each other. In order to predict a trajectory, it could be easier to work with curated positions given by an object tracker than raw sensor data. On the other hand, past predictions might be given as input to an object tracker, in order to mitigate noise in the sensor data and acting so as a belief-based filter.

$\endgroup$
1
  • $\begingroup$ Your definitions look reasonable to me, but I am not an expert in this area, so I cannot assess the correctness of this answer. Are these definitions common in the context of computer vision (or whatever the context is)? Maybe you should provide a link to a reference for more details (given that the OP was also mentioning autonomous vehicles and it's not clear if your definitions apply to that context or, in general, apply to any computer vision applications), but I guess this is not necessary, if you more or less familiar with these topics. $\endgroup$ – nbro Dec 8 '20 at 17:26

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.