Direct Edge Alignment (D-EA)

Abstract

There has been a paradigm shifting trend towards feature-less methods due to their elegant formulation, accuracy and ever increasing computational power. In this work, we present a direct edge alignment approach for 6-DOF tracking. We argue that photo-consistency based methods are plagued by a much smaller convergence basin and are extremely sensitive to noise, changing illumination and fast motion. We propose to use the Distance Transform in the energy formulation which can significantly extend the influence of the edges for tracking. We address the problem of non-differentiability of our cost function and of the previous methods by use of a sub-gradient method. Through extensive experiments we show that the proposed method gives comparable performance to the previous method under nominal conditions and is able to run at 30 Hz in single threaded mode. In addition, under large motion we demonstrate our method outperforms previous methods using the same run-time configuration for our method.

Illustration

output_7eWDBS
Showing residues at every iteration as the optimization proceeds to estimate the relative pose (rotation and translation) between a pair of images spaced about 90ms apart. Red represents higher residues, blue represent smaller residues.

output_OLSoI0
Reprojected 3D edge pixels from reference image, overlayed on distance transform of the edge image of the current frame.

Screenshot from 2016-02-10 22:47:13

Publication

Kuse M., Shen S. “Robust Camera Motion Estimation using Direct Edge Alignment and Sub-gradient Method“. In Proc. of IEEE International Conference on Robotics and Automation (ICRA), 2016 in Stockholm, Sweden. [PDF]

Yonggen Ling, Manohar Kuse, and Shaojie Shen, “Direct Edge Alignment-Based Visual-Inertial Fusion for Tracking of Aggressive Motions“, submitted in Springer Autonomous Robots (Impact factor 2.706 in 2016). [PDF][More][Code-github][Springer-link][youtube-video]

Source Code & Documents

Git Repo :  https://github.com/mpkuse/rgbd_odometry 
Documentation : [ZIP] (generated with Doxygen)
Pre-requisites: ROS (hydro and above), Eigen, IGL Library, OpenCV.

Standalone implementation: https://github.com/mpkuse/edge_alignment

Code-github from Ling Yongyen

Full Presentation : [PDF]
ICRA Spot-light talk : [Google Slides] [Copy of]
Interactive Poster : [Prezi]

Other Data for Download

Reprojections for a image-pair (full results similar to figure-1 of the paper) : [ZIP]
Relatives Poses for sequences and related scripts : [ZIP]

Summary of Algorithm

(For details please refer to the publication)

Screenshot from 2016-02-10 22:16:26

2 thoughts on “Direct Edge Alignment (D-EA)

  1. Hi Im’ Sadie. As you mentioned that we can find more results on this website, but I couldn’t open the zip file (the dropbox is empty now). So could you pls send me your results of DEA on other TUM sequences? Thanks a lot!!

  2. Hi also me.
    I have another question. Um.. I found that the results of Kerl’s work on fr2_desk_people and Fr3_sit_half in your paper is inconsistent with the one in 2016 Trans on Robotics…and the results of Kerl’s work in your paper is better….could you pls tell me…why?…..thank you!!

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s