Presentation is loading. Please wait.

Presentation is loading. Please wait.

Comparison of stereovision odometry approaches Niko Suenderhauf Chemnitz University of Technology Germany Kurt Konolidge SRI International USA Thomas Lemaire,

Similar presentations


Presentation on theme: "Comparison of stereovision odometry approaches Niko Suenderhauf Chemnitz University of Technology Germany Kurt Konolidge SRI International USA Thomas Lemaire,"— Presentation transcript:

1 Comparison of stereovision odometry approaches Niko Suenderhauf Chemnitz University of Technology Germany Kurt Konolidge SRI International USA Thomas Lemaire, Simon Lacroix Robotics and AI group LAAS/CNRS, Toulouse (at Laas 10/04 03/05) (at Laas (08/04 03/05)

2 On the importance of localization Reach that goal, Map this area… Missions are defined in terms of localization Environment models are required Spatial consistency ensured by localization Safe execution of the planned trajectories Robust control ensured by localization If you are not localized, you are lost !

3 Outline Principle of stereovision odometry Dead reckoning approach More global approaches Conclusions

4 2. Pixels selection 3. Pixels tracking 1. Stereovision 4.Stereovision 5. Motion estimation Principle of stereovision odometry

5 A lot of contributions now in the robotics literature –[Mallet-Lacroix-2000] –[Olson-Matthies-2000] - cf Matthies in the 80s –[Corke-2004] –…–… +Related approaches – scan matching approaches - without image feature associations (e.g. [Zhang-1992]) – [Kim-ICRA-2005] - without stereo correspondences Three functionalities involved –Stereovision (sparse or dense) –Image feature association –Pose estimation

6 Feature tracking or feature matching ? Feature tracking Close images (high spatial rate) Aiding sensor (to focus the search) No feature selection necessarily required Feature matching Feature extraction / selection (or ?) A bit more time Work for almost any motion - no estimate necessary

7 Feature matching Features : Harris precise detector [Schmid-ICCV-1998] Interest point matching [Jung-ICCV-2001]

8 Feature matching Features : Harris precise detector [Schmid-ICCV-1998] Interest point matching [Jung-ICCV-2001] Detected pointsMatched pointsAn other example

9 Feature matching Features : Harris precise detector [Schmid-ICCV-1998] Interest point matching [Jung-ICCV-2001] 1.5 scale change3.0 scale change

10 Error models Relation between correlation curve and d : Std dev. on disparities (here with ZNCC along epipolar) 1. On stereovision : empical analysis (cf [Matthies-1992]) )(cf d Error model :

11 Gaussian distribution Correlation surface Error models 2. On interest point matching : gaussian fitting model Correlation surface locally computed around the matches (ZNCC score) Validity of such a model ? Dont we miss a proportional factor ?

12 Outline Principle of stereovision odometry –Feature matching –Error models Dead reckoning approach More global approaches Conclusions

13 Dead reckoning approach Relative t+1 / t poses computed with constrained least square minimisation (e.g. [Haralick-1989]) Simple iterative outlier rejection algorithm (no RANSAC required) Fairly good precision (up to 1% on 100m trajectories)

14

15 Dead reckoning error Propagating the uncertainty of 3D matching points set to optimal motion estimate [Haralick-1994] - 3D matching points set - Optimal motion estimate - Cost function Covariance of the random perturbation u : propagation using Taylor series expansion of the Jacobian of the cost function around

16 Outline Principle of stereovision odometry –Feature matching –Error models Dead reckoning approach More global approaches Conclusions

17 Bundle adjustment approach Classic way to solve the structure from motion problem in computer vision Non linear-minimization provides a MLE (up to a scale parameter) Can also optimize camera parameters (11 d.o.f. in P i ) n points, m poses : 3n + 6m parameters… Better have good initial estimates ! Sparse bundle adjustment [Hartley-2004] : 3D points : image coordinates

18 Sparse bundle adjustment with stereo Simply add second image pixels/poses in the function to minimize Naïve outlier rejection procedure costly (better use RANSAC ?) Various possibilities : –Used in a dead reckoning way –Used on a fixed size of images (or within a given distance) : sliding window approach –Global optimization : Full SBA

19 SBA with stereo : indoor data set Full SBA « local » SBAs

20 SBA with stereo : outdoor data set D-CP-GPS Full SBA « local » SBAs

21 SBA with stereo : conclusions Full SBA simply not tractable (batch, required 4.5 min CPU time on the outdoor data set) Sliding window SBA seems better than dead-reckoning approach –Nb of images of 3-4 seems enough

22 EKF-SLAM approach –Landmark detection –Relative observations (measures) Of the landmark positions Of the robot motions –Observation associations –Refinement of the landmark and robot positions General SLAM operations ÕVision : interest points ÕStereovision ÕVisual motion estimation / INS / Odo ÕInterest points matching ÕExtended Kalman filter Stereo-based SLAM operations « Local memory » SLAM : forget landmarks that disappear Can be run in « real time » Can incorporate any aiding sensor Various « forget strategies » can be defined

23 Local EKF-SLAM approach : data set Along a 60m loop trajectory : 100 stereo pairs Looking inwards By the way, between images 31 and 32 :

24 Local EKF-SLAM approach : results

25

26 (Full EKF-SLAM approach : results) landmark uncertainty ellipses (x5)

27 (Full EKF-SLAM approach : results) Frame 1/100 Reference Std. Dev. VME result VME Abs.error SLAM result SLAM Std. Dev. SLAM Abs. error 0.52°0.31°2.75°2.23°0.88°0.98°0.36 ° 0.36°0.25°-0.11°0.47°0.72°0.74°0.36 ° -0.14°0.16°1.89°2.03°1.24°1.84°1.38° txtx -0.012m0.010m0.057m0.069m-0.077m0.069m0.065m tyty -0.243m0.019m-1.018m0.775m-0.284m0.064m0.041m tztz 0.019m0.015m0.144m0.125m0.018m0.019m0.001m

28 (((( Full EKF-SLAM approach : results ))))

29 Outline Principle of stereovision odometry –Feature matching –Error models Dead reckoning approach More global approaches –SBA-based approach –EKF-SLAM approach Conclusions ?

30 Conclusions A vast number of parameters to check/assess –Algorithmic parameters : Kind of matching algorithm (stereo and motion matches) Feature definition and selection Estimation –Dead reckoning –SBA approaches –SLAM approaches –System parameters : Image size Focal length Stereovision baseline and height Bench orientation (forward, sidewards, downwards) Panoramic cameras !!! (not even stereo ? cf visual- SLAM recent results, view- based localisation…

31 The Journal of Field Robotics seeks to promote rapid dissemination of important research results in robotics for unstructured and dynamic environments. Articles describing robotics research with applications to the environment, construction, forestry, agriculture,,mining, subsea, intelligent highways, search and rescue, military, and space (orbital and planetary) are encouraged. Articles in sensing, sensors, mechanical design, computing architectures, communication, planning, learning, and control, applied to field applications are encouraged. The first issue is expected to be available in January 2006. Further Details: http://www.ri.cmu.edu/~jfr Journal of Field Robotics Editor-In-Chief Sanjiv Singh, Carnegie Mellon Editorial Board Robert Ambrose, NASA JSC Greg Baiden, Laurentian Univ. Martin Buehler, Boston Dynamics Raja Chatila, LAAS Peter Corke, CSIRO Eric Feron, MIT Ernie Hall, Univ. of Cincinnati Alonzo Kelly, CMU Larry Matthies, NASA JPL Eduardo Nebot, Univ. of Sydney Simon LaCroix, LAAS Annibal Ollero, Univ. of Seville Vincent Rigaud, IFREMER Jonathan Roberts, CSIRO David Wettergreen, CMU Ron Arkin, Georgia Tech, Alberto Broggi, Univ. of Parma Aarne Halme, HUT Peter Lawrence, Univ. of British Columbia David Nister, Univ. of Kentucky John Reid, John Deere Mirek Skibinewski, Purdue James Trevelyan, Univ of Western Australia Tony Stentz, CMU Brian Wilcox, NASA JPL Kazuya Yoshida, Tohoku Univ.


Download ppt "Comparison of stereovision odometry approaches Niko Suenderhauf Chemnitz University of Technology Germany Kurt Konolidge SRI International USA Thomas Lemaire,"

Similar presentations


Ads by Google