1‐Point RANSAC for extended Kalman filtering: Application to real‐time structure from motion and visual odometry

Civera, Javier; Grasa, Óscar G.; Davison, Andrew J.; Montiel, José María

doi:10.1002/rob.20345

Cited by 257 publications

(219 citation statements)

References 42 publications

Supporting

Mentioning

207

Contrasting

Unclassified

Order By: Relevance

“…From the two points, one computes θ k under the assumption of planar motion using (13). 12 Then, using the motion prior, one can obtain a sample of the other parameters…”

Section: A Estimating the Motion Solution And The Joint Posteriormentioning

confidence: 99%

“…Thus the distribution is very compact. 12 Notice that this is perfectly equivalent to sampling from the proposal distribution. The advantage of doing so is that we avoid explicitly computing the proposal distribution, thus making the algorithm even more efficient.…”

Section: B Remarksmentioning

confidence: 99%

“…In addition, for each candidate set of data points 5-point RANSAC returns up to ten motion solution, each to be tested. An alternative algorithm was proposed in [12] for EKF-based visual odometry. They proposed to use the available prior probabilistic information from the EKF in the RANSAC model-hypothesize stage.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting motion priors in visual odometry for vehicle-mounted cameras with non-holonomic constraints

Scaramuzza

Censi

Daniilidis

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper presents a new method to estimate the relative motion of a vehicle from images of a single camera. The biggest problem in visual motion estimation is data association; matched points contain many outliers that must be detected and removed so that the motion can be estimated accurately. A very established method for robust motion estimation in the presence of outliers is the five-point RANSAC algorithm. Fivepoint RANSAC operates by generating motion hypotheses from randomly-sampled minimal sets of five-point correspondences. These hypotheses are then tested against all data points and the motion hypothesis that after a given number of iterations returns the largest number of inliers is taken as the solution to the problem. A typical drawback of RANSAC is that the number of iterations required to find a suitable solution grows exponentially with the number of outliers, often requiring thousands of iterations for typical data from urban environments. Another problem is that -due to its random nature -sometimes the found solution is not the "best" solution to the motion estimation problem. In this paper, we describe an algorithm for relative motion estimation in the presence of outliers, which does not rely on RANSAC. Contrary to RANSAC, motion hypotheses are not generated from randomly-sampled point correspondences, but from a "proposal distribution" that is built by exploiting the vehicle non-holonomic constraints. We show that not only is the proposed algorithm significantly faster than RANSAC, but that the returned solution may also be better in that it favors the underlying motion model of the vehicle, thus overcoming the typical limitations of RANSAC. Additionally, the proposed algorithm provides the likelihood of the motion estimate, which can be very useful in all those applications where a probability distribution of the position of the vehicle is required (e.g., SLAM). Finally, the performance of the proposed method is compared to that of the standard fivepoint RANSAC on real images collected from a vehicle moving in a cluttered, urban environment.

show abstract

“…From the two points, one computes θ k under the assumption of planar motion using (13). 12 Then, using the motion prior, one can obtain a sample of the other parameters…”

Section: A Estimating the Motion Solution And The Joint Posteriormentioning

confidence: 99%

Section: B Remarksmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting motion priors in visual odometry for vehicle-mounted cameras with non-holonomic constraints

Scaramuzza

Censi

Daniilidis

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Therefore, this problem correlated to dynamic points and static points that were misclassified as dynamic points. Such points are informative for the SLAM system especially for distant points which are good for robot orientation estimation [4].…”

Section: Introductionmentioning

confidence: 99%

Dynamic feature detection using virtual correction and camera oscillations

Heshmat

Abdellatif

Nakamura

et al. 2014

2014 International Conference on 3D Imaging (IC3D)

View full text Add to dashboard Cite

Visual SLAM algorithms exploit natural scene features to infer the camera motion and build a map of a static environment. In this paper, we relax the severe assumption of a static scene to allow for the detection and deletion of dynamic points. A new "virtual correction" method is introduced which serves to detect the dynamic points by checking the re-projection error of the points before and after the virtual measurement update. It can also recover the erroneously excluded useful features, particularly the distant points which may be deleted because of the change in its position after new measurement observation. Deliberate camera oscillations are also used to improve the VSLAM accuracy and the camera observability. The simulation results showed the effectiveness of the virtual correction in improving the consistency of the VSLAM and the detection of dynamic points and in particular for difficult scenarios.

show abstract

“…In this work we extend the SLAM approach for catadioptric cameras by Gutierrez et al [9] which derives from state of the art EKF monocular SLAM for conventional cameras [2]. This approach is used to compute the visual odometry from sequences of images acquired with a catadioptric camera mounted on a helmet (Fig.…”

Section: Introductionmentioning

confidence: 99%

Full scaled 3D visual odometry from a single wearable omnidirectional camera

Gutiérrez-Gómez

Puig

Guerrero

2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-In the last years monocular SLAM has been widely used to obtain highly accurate maps and trajectory estimations of a moving camera. However, one of the issues of this approach is that, due to the impossibility of the depth being measured in a single image, global scale is not observable and scene and camera motion can only be recovered up to scale. This problem gets aggravated as we deal with larger scenes since it is more likely that scale drift arises between different map portions and their corresponding motion estimates. To compute the absolute scale we need to know some kind of dimension of the scene (e.g., actual size of an element of the scene, velocity of the camera or baseline between two frames) and somehow integrate it in the SLAM estimation. In this paper, we present a method to recover the scale of the scene using an omnidirectional camera mounted on a helmet. The high precision of visual SLAM allows the head vertical oscillation during walking to be perceived in the trajectory estimation. By performing a spectral analysis on the camera vertical displacement, we can measure the step frequency. We relate the step frequency to the speed of the camera by an empirical formula based on biomedical experiments on human walking. This speed measurement is integrated in a particle filter to estimate the current scale factor and the 3D motion estimation with its true scale. We evaluated our approach using image sequences acquired while a person walks. Our experiments show that the proposed approach is able to cope with scale drift.

show abstract

1‐Point RANSAC for extended Kalman filtering: Application to real‐time structure from motion and visual odometry

Cited by 257 publications

References 42 publications

Exploiting motion priors in visual odometry for vehicle-mounted cameras with non-holonomic constraints

Exploiting motion priors in visual odometry for vehicle-mounted cameras with non-holonomic constraints

Dynamic feature detection using virtual correction and camera oscillations

Full scaled 3D visual odometry from a single wearable omnidirectional camera

Contact Info

Product

Resources

About