Keywords: FAST Feature Detection, LK Feature Tracking, Five-Point Motion Estimation

• Python 3.6.4
• Numpy
• OpenCV
• utm

This repository enables the use of tracking data set KITTI tracking data set (Left Color, GPS/IMU data, 15 GB)

Or, you can use the original odometry data set KITTI odometry data set (grayscale, 22 GB)

• Modify the path in test.py to your image sequences and ground truth trajectories, then run

python test.py 0007

• Use ground truth to calculate absolute scale, add

--use_abs_scale

• To skip frames, add

--skip_frame 2

• This repository is from monoVO-python
• Monocular Visual Odometry using OpenCV and its related project report Monocular Visual Odometry | Avi Singh