Research on Event Accumulator Settings for Event-Based SLAM

Robin Shaun

Last update: Dec 21, 2022

Related tags

Overview

Research on Event Accumulator Settings for Event-Based SLAM

This is the source code for paper "Research on Event Accumulator Settings for Event-Based SLAM". For more details please refer to https://arxiv.org/abs/2112.00427

1. Prerequisites

See dv_ros and VINS-Fusion

2. Build

cd ~/catkin_ws/src
git clone https://github.com/robin-shaun/event-slam-accumulator-settings.git
cd ../
catkin_make 
source ~/catkin_ws/devel/setup.bash

3. Demo

We evaluate the proposed method quantitatively on the Event Camera Dataset. This demo takes the dynamic_6dof sequence as example.

First, start dv_ros. Notice that the event accumulator depends on the timestamp, so when you restart the dataset or davis driver, you should restart dv_ros.

roslaunch dv_ros davis240.launch

And then, start VINS-Fusion

roslaunch vins vins_rviz.launch

rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/davis/rpg_240_mono_imu_config.yaml

Finally, play the rosbag

cd ~/catkin_ws/src/event-slam-accumulator-settings/dataset
rosbag play dynamic_6dof.bag

4. Run with your devices

We have tested the code with DAVIS240 and DAVIS346. If you want to run with your devices, the most important thing to do is calibrate the event camera and imu. We advise to use Kalibr with traditional image from APS and IMU, because the intrinsics and extrinsics are almost the same for APS and DVS.

If you want to compare the event-based VINS Fusion with traditional VINS Fusion with DAVIS346, you should use this code. Because the frame from APS of DAVIS346 sometimes changes the size, we do some modification for VINS-Fusion.

5. Acknowledgements

Thanks for dv_ros and VINS-Fusion.

You might also like...

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

An implementation of the research paper "Retina Blood Vessel Segmentation Using A U-Net Based Convolutional Neural Network"

Retina Blood Vessels Segmentation This is an implementation of the research paper "Retina Blood Vessel Segmentation Using A U-Net Based Convolutional

23 Aug 20, 2022

Comments

unexpected drift on boxes_6dof bag

Hi, When I run the code on the bag boxes_6dof mentioned in your paper, the result is quite bad, as shown in the following image. Is this the problem of the configuration? If so, could you provide the config you used?

Thanks a lot.

opened by Sean0120 8

Research on Event Accumulator Settings for Event-Based SLAM

Related tags

Overview

Research on Event Accumulator Settings for Event-Based SLAM

1. Prerequisites

2. Build

3. Demo

4. Run with your devices

5. Acknowledgements

You might also like...

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

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Boost learning for GNNs from the graph structure under challenging heterophily settings. (NeurIPS'20)

Generic Event Boundary Detection: A Benchmark for Event Segmentation

Scikit-event-correlation - Event Correlation and Forecasting over High Dimensional Streaming Sensor Data algorithms

Event-forecasting - Event Forecasting Algorithms With Python

Event sourced bank - A wide-and-shallow example using the Python event sourcing library

An implementation of the research paper "Retina Blood Vessel Segmentation Using A U-Net Based Convolutional Neural Network"

Comments

unexpected drift on boxes_6dof bag

Owner

Robin Shaun

A 3D Dense mapping backend library of SLAM based on taichi-Lang designed for the aerial swarm.

FLVIS: Feedback Loop Based Visual Initial SLAM

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)

MBPO (paper: When to trust your model: Model-based policy optimization) in offline RL settings

This package is for running the semantic SLAM algorithm using extracted planar surfaces from the received detection

COVINS -- A Framework for Collaborative Visual-Inertial SLAM and Multi-Agent 3D Mapping

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

🛠️ SLAMcore SLAM Utilities

Official page of Struct-MDC (RA-L'22 with IROS'22 option); Depth completion from Visual-SLAM using point & line features