search

JunshengFu / tracking-with-Extended-Kalman-Filter

Object (e.g Pedestrian, vehicles) tracking by Extended Kalman Filter (EKF), with fused data from both lidar and radar sensors.
MIT License
752 stars 260 forks source link

Where is the fusion part? #2

Closed zhangjun-xyz closed 7 years ago

zhangjun-xyz commented 7 years ago

Hello I read all your codes but I cannot the fusion part. In your codes lidar and radar data are processed, respectively. I don't know whether my understand is right.

JunshengFu commented 7 years ago

@zhangjun-xyz The fusion part is here: void FusionEKF::ProcessMeasurement(const MeasurementPackage &measurement_pack) {}

Lidar and radar data should be processed respectively since they are different measurements: lidar: px and py (pz is not used in this project); radar: range, bearing, radial velocity.

You can see how EKF works here, and you may find these following two material useful for understanding EKF. http://home.wlu.edu/~levys/kalman_tutorial/ http://biorobotics.ri.cmu.edu/papers/sbp_papers/integrated3/kleeman_kalman_basics.pdf

zhangjun-xyz commented 7 years ago

Thanks a lot! I found that. So the fusion is to process the measurements given by the two sensors successively. Is my understanding right?

JunshengFu commented 7 years ago

@zhangjun-xyz check this out: https://en.wikipedia.org/wiki/Sensor_fusion "Sensor fusion is combining of sensory data or data derived from disparate sources such that the resulting information has less uncertainty than would be possible when these sources were used individually... "

zhangjun-xyz commented 7 years ago

Okay, I understand. Thanks for your sharing.