- axel
- python
- make
-
download dataset
make download
-
configuration of python environment
make env
-
combination between depth and rgb
make associate
-
build project
make build
-
evaluate_rpe
make evaluation_rpe -
evaluate_ate
make evaluate_ate
-
evaluate
make evaluate
| Camera | fx | fy | cx | cy | d0 | d1 | d2 | d3 | d4 |
|---|---|---|---|---|---|---|---|---|---|
| (ROS default) | 525.0 | 525.0 | 319.5 | 239.5 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| Freiburg 1 RGB | 517.3 | 516.5 | 318.6 | 255.3 | 0.2624 | -0.9531 | -0.0054 | 0.0026 | 1.1633 |
| Freiburg 2 RGB | 520.9 | 521.0 | 325.1 | 249.7 | 0.2312 | -0.7849 | -0.0033 | -0.0001 | 0.9172 |
| Freiburg 3 RGB | 535.4 | 539.2 | 320.1 | 247.6 | 0 | 0 | 0 | 0 | 0 |
-
rewrite matlab code to python
No task modules deadline status 1.1 se3Log14.06.2020 implemented 1.2 se3Exp14.06.2020 implemented 1.3 imreadbw14.06.2020 implemented 1.4 calcResiduals14.06.2020 implemented 1.5 deriveResidualsAnalytic14.06.2020 - 1.6 deriveResidualsNumeric14.06.2020 implemented 1.7 downscale14.06.2020 implemented 1.8 doAlignment14.06.2020 implemented -
Implement keyframe-based camera tracking through direct image alignment.
No task modules deadline status 2.1 process the RGB-D images only up to a downsampled size in the image pyramid - implemented 2.2 Choose thresholds on the rotational and translational distance to create new keyframes, when the image overlap gets too small for camera tracking implemented 2.3 Implement the relative entropy measure to decide when to create new keyframes 2.4 Implement pose-graph optimization for the keyframe poses using the Gauss-Newton algorithm and left-multiplied increments on the poses. The sample of
2.2is bellow:
-
optimal key-frame
No task modules deadline status 3.1 3.2 3.3 3.4 -
second party
No task modules deadline status 4.1 4.2 4.3 4.4 -
pending
