Please use this starter template to answer the following questions:
1. Write a short recap of the four tracking steps and what you implemented there (filter, track management, association, camera fusion). Which results did you achieve? Which part of the project was most difficult for you to complete, and why?
2. Do you see any benefits in camera-lidar fusion compared to lidar-only tracking (in theory and in your concrete results)?
3. Which challenges will a sensor fusion system face in real-life scenarios? Did you see any of these challenges in the project?
- Fine-tune your parameterization and see how low an RMSE you can achieve! One idea would be to apply the standard deviation values for lidar that you found in the mid-term project. The parameters in misc/params.py should enable a first running tracking, but there is still a lot of room for improvement through parameter tuning!
- Implement a more advanced data association, e.g. Global Nearest Neighbor (GNN) or Joint Probabilistic Data Association (JPDA).
- Feed your camera detections from Project 1 to the tracking.
- Adapt the Kalman filter to also estimate the object's width, length, and height, instead of simply using the unfiltered lidar detections as we did.
- Use a non-linear motion model, e.g. a bicycle model, which is more appropriate for vehicle movement than our linear motion model, since a vehicle can only move forward or backward, not in any direction.