sram-v/superpoint-gtsam-vio

Visual Inertial Odometry using SuperPoint and GTSAM

superpoint-gtsam-vio

Visual Inertial Odometry using SuperPoint and GTSAM

Installation:

After cloning the repo:

#!bash
$ git submodule update --init --recursive
$ python3 -m venv env
$ source env/bin/activate
$ pip install -r requirements.txt

Usage:

Download the raw + synchronized KITTI data from here and the annotated depth map data set from here.

Run Visual-Inertial Odometry for e.g. date 2011_09_26 and drive 0022, skipping every 10th frame and using the first 701 frames available using the following command:

#!bash
$ python src/main.py --basedir /path/to/kitti/raw/data --date 2011_09_26 --drive 0022 --n_skip 10 --n_frames 701