• Stars
    star
    133
  • Rank 272,600 (Top 6 %)
  • Language
    Python
  • License
    MIT License
  • Created over 2 years ago
  • Updated over 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation

SUO-SLAM

This repository hosts the code for our CVPR 2022 paper "Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation". ArXiv link.

Citation

If you use any part of this repository in an academic work, please cite our paper as:

@inproceedings{Merrill2022CVPR,
  Title      = {Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation},
  Author     = {Nathaniel Merrill and Yuliang Guo and Xingxing Zuo and Xinyu Huang and Stefan Leutenegger and Xi Peng and Liu Ren and Guoquan Huang},
  Booktitle  = {2022 Conference on Computer Vision and Pattern Recognition (CVPR)},
  Year       = {2022},
  Address    = {New Orleans, USA},
  Month      = jun,
}

Installation

Click for details... This codebase was tested on Ubuntu 18.04. To use the BOP rendering (i.e. for keypoint labeling) install
sudo apt install libfreetype6-dev libglfw3

You will also need a python environment that contains the required packages. To see what packages we used, check out the list of requirements in requirements.txt. They can be installed via pip install -r requirements.txt

Preparing Data

Click for details...

Datasets

To be able to run the training and testing (i.e. single view or with SLAM), first decide on a place to download the data to. The disk will need a few hundred GB of space for all the data (at least 150GB for download and more to extract). All of our code expects the data to be in a local directory ./data, but you can of course symlink this to another location (perhaps with more disk space). So, first of all, in the root of this repo run

$ mkdir data

or to symlink to an external location

$ ln -s /path/to/drive/with/space/ ./data

You can pick and choose what data you want to download (for example just T-LESS or YCBV). Note that all YCBV and TLESS downloads have our keypoint labels packaged along with the data. Download the following google drive links into ./data and extract them.

When all is said and done, the tree should look like this

$ cd ./data && tree --filelimit 3
.
├── bop_datasets
│   ├── tless 
│   └── ycbv 
├── saved_detections
└── VOCdevkit
    └── VOC2012

Pre-trained models

You can download the pretrained models anywhere, but I like to keep them in the results directory that is written to during training.

Training

Click for details...

First set the default arguments in ./lib/args.py for your username if desired, then execute

$ ./train.py

with the appropriate arguments for your filesystem. You can also run

$ ./train.py -h

for a full list of arguments and their meaning. Some important args are batch_size, which is the number of images loaded for each training batch. Note that there may be a variable number of objects in each image, and the objects are all stacked together into one big batch to run the network -- so the actual batch size being run might be multiple times batch_size. In order to keep batch_size reasonably large, we provide another arg called truncate_obj, which, as the help says, truncates the object batches to this number if it exceeds it. We recommend that you start with a large batch size so that you can find out the maximum truncate_obj for you GPUs, then reduce the batch size until there are little to no warnings about too many objects being truncated.

Evaluation

Click for details...

Before you can evaluate in a single-view or SLAM fashion, you will need to build the thirdparty libraries for PnP and graph optimization. First make sure that you have CERES solver installed. The run

$ ./build_thirdparty.sh

Reproducing Results

To reproduce the results of the paper with the pretrained models, check out the scripts under the scripts directory:

eval_all_tless.sh  eval_all_ycbv.sh  make_video.sh

These will reproduce most of the results in the paper as well as any video clips you want. You may have to change the first few lines of each script. Note that these examples can also show you the proper arguments if you want to run from command line alone.

Note that for the T-LESS dataset, we use the thirdparty BOP toolkit to get the VSD error recall, which will show up in the final terminal output as "Mean object recall" among other numbers.

Labeling

Click for details...

Overview

We manually label keypoints on the CAD model to enable some keypoints with semantic meaning. For the full list of keypoint meanings, see the specific README

We provide our landmark labeling tool. Check out the script manual_keypoints.py. This same script can be used to make a visualization of the keypoints as shown below with the --viz option.

The script will show a panel of the same object but oriented slightly differently. The idea is that you pick the same keypoint multiple times to ensure correctness and to get a better label by averaging multiple samples.

The script will also print the following directions to follow in the terminal.

============= Welcome ===============
Select the keypoints with a left click!
Use the "wasd" to turn the objects.
Press "i" to zoom in and "o" to zoom out.
Make sure that the keypoint colors match between all views.
Messed up? Just press 'u' to undo.
Press "Enter" to finish and save the keypoints
Press "Esc" to just quit

Once you have pressed "enter", you will get to an inspection pane.

Where the unscaled mean keypoints are on the left, and the ones scaled by covariance is on the left, where the ellipses are the Gaussian 3-sigma projected onto the image. If the covariance is too large, or the mean is out of place, then you may have messed up. Again, the program will print out these directions to terminal:

Inspect the results!
Use the "wasd" to turn the object.
Press "i" to zoom in and "o" to zoom out.
Press "Esc" to go back, "Enter" to accept (saving keypoints and viewpoint for vizualization).
Please pick a point on the object!

So if you are done, and the result looks good, then press "Enter", if not then "Esc" to go back. Make sure also that when you are done, you rotate and scale the object into the best "view pose" (with the front facing the camera, and top facing up), as this pose is used by both the above vizualization and the actual training code for determining the best symmetry to pick for an initial detection.

Labeling Tips

Even though there are 8 panels, you don't need to fill out all 8. Each keypoint just needs at least 3 samples to sample the covariance.

We recommend that you label the same keypoint (say keypoint i) on all the object renderings first, then go to the inspection panel at the end of this each time so that you can easily undo a mistake for keypoint i with the "u" key and not lose any work. Otherwise, if you label each object rendering completely, then you may have to undo a lot of labelings that were not mistakes.

Also, if there is an object that you want to label a void in the CAD model, like the top center of the bowl, then you can use the multiple samples to your advantage, and choose samples that will average to the desired result, since the labels are required to land on the actual CAD model in the labeling tool.

<\details>

More Repositories

1

open_vins

An open source platform for visual-inertial navigation research.
C++
2,111
star
2

R-VIO

Robocentric Visual-Inertial Odometry
C++
737
star
3

kalibr_allan

IMU Allan standard deviation charts for use with Kalibr and inertial kalman filters.
MATLAB
577
star
4

MINS

An efficient and robust multisensor-aided inertial navigation system with online calibration that is capable of fusing IMU, camera, LiDAR, GPS/GNSS, and wheel sensors. Use cases: VINS/VIO, GPS-INS, LINS/LIO, multi-sensor fusion for localization and mapping (SLAM). This repository also provides multi-sensor simulation and data.
C++
427
star
5

cpi

Closed-form Preintegration for Graph-based Visual-Inertial Navigation
C++
249
star
6

R-VIO2

Square-Root Robocentric Visual-Inertial Odometry with Online Spatiotemporal Calibration
C++
228
star
7

ov_plane

A monocular plane-aided visual-inertial odometry
C++
197
star
8

calc

Convolutional Autoencoder for Loop Closure
Python
190
star
9

lips

LiDAR-Inertial 3D Plane Simulator
MATLAB
150
star
10

android-camera-calibration

Updated (opencv3 and camera2 API) android camera calibration application
C++
118
star
11

calc2.0

CALC2.0: Combining Appearance, Semantic and Geometric Information for Robust and Efficient Visual Loop Closure
Python
95
star
12

vicon2gt

Vicon-IMU fusion for groundtruth trajectory generation.
C++
95
star
13

ov_maplab

Interface for OpenVINS with the maplab project
C++
82
star
14

ocekf-slam

Observability-Constrained (OC)-EKF for 2D SLAM
MATLAB
79
star
15

android-dataset-recorder

Dataset collection app that will collect both IMG and IMU measurements for offline processing
Java
60
star
16

icalib.github.io

Inertial Aided Multi-Sensor Calibration
60
star
17

ov_secondary

Secondary posegraph adapted for interfacing with OpenVINS, based on VINS-Mono / VINS-Fusion.
C++
59
star
18

ar_table_dataset

Small-scale indoor table AR visual-inertial datasets with 6DoF groundtruth.
Python
53
star
19

reach_ros_node

ROS driver for the Reach RTK GNSS module by Emlid
Python
36
star
20

mast_project

Underwater Camera and Sonar SLAM (Kevin and Linde's MAST class project)
C++
36
star
21

pointgrey_ladybug

ROS Driver for Pointgrey Ladybug Cameras
C++
30
star
22

clatt

cooperative localization and target tracking
MATLAB
28
star
23

android_sensors_driver

ROS Driver for Android Sensors (opencv3 and camera1 API)
Java
26
star
24

xsens_standalone

Python Standalone library for use with the xsens IMU
Python
19
star
25

rosbags

Github mirror of https://gitlab.com/ternaris/rosbags
Python
18
star
26

kitti_parser

C++ parser for the RAW KITTI dataset, with callbacks
C++
15
star
27

gps_path_pub

Handy publishing of a path and and frame from a single GPS sensor.
C++
13
star
28

CSO

Calibration the rigid transformation between the stereo and odometry
C++
12
star
29

img_imu_record

Easy recording of image and imu data to disk
C++
9
star
30

orb_slam_mapmerge

A Versatile and Accurate Monocular SLAM (with map merging)
C++
7
star
31

apriltags-cpp

A simple ros wrapper for apriltag-cpp
C++
7
star
32

vins_source

Helper package with launch files for getting imu and video sources.
CMake
6
star
33

microstrain_comm

IMU driver for the Microstrain 3DM-GX3®-25. Converted to run on the ROS framework.
C
5
star
34

Microstrain-3DM-GX3-35

ROS driver for Microstrain 3DM-GX3-35 IMU
C
3
star
35

firefly

AscTec Firefly Documentation
1
star
36

ZED_Odom_Grabber

Grab zed stereo images and odometry from turtlebot at the same time.
C++
1
star
37

dvs128-viewer

A driver for dvs128 camera
Java
1
star