Visual odometry

Nistér, D.; Naroditsky, Oleg; Bergen, James R.

doi:10.1109/cvpr.2004.1315094

Cited by 1,164 publications

(896 citation statements)

References 11 publications

Supporting

Mentioning

887

Contrasting

Unclassified

Order By: Relevance

“…In particular, a specialized term "visual SLAM" (V-SLAM in short) was coined to distinguish the SLAM systems relying mainly on cameras, which relates to the fact that the estimation of subsequent poses of the moving camera is called "visual odometry" (VO) (Nistér et al, 2004).…”

Section: Introductionmentioning

confidence: 99%

“…Typically, it is based on matching features extracted from both current and previous images, finding parts of both images corresponding to the same scene elements. There Efficient generation of 3D surfel maps using RGB-D sensors 101 are algorithms based only on RGB image features (either for a single camera (Nistér et al, 2004) or a stereo-camera case ), but the additional depth information makes the matching process much easier. As a result, a sparse 3D cloud of features is generated, allowing robust estimation of the transformation between camera poses.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Efficient generation of 3D surfel maps using RGB–D sensors

Wilkowski

Kornuta

Stefańczyk

et al. 2016

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

The article focuses on the problem of building dense 3D occupancy maps using commercial RGB-D sensors and the SLAM approach. In particular, it addresses the problem of 3D map representations, which must be able both to store millions of points and to offer efficient update mechanisms. The proposed solution consists of two such key elements, visual odometry and surfel-based mapping, but it contains substantial improvements: storing the surfel maps in octree form and utilizing a frustum culling-based method to accelerate the map update step. The performed experiments verify the usefulness and efficiency of the developed system.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Efficient generation of 3D surfel maps using RGB–D sensors

Wilkowski

Kornuta

Stefańczyk

et al. 2016

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

“…The quality of the recovered trajectories directly affects the performance of attractive higher level tasks such as structure from motion [1], visual odometry [2], concurrent mapping and localization [3], and visual servoing [4]. However, the priorities of the desired tracking behaviour may differ between the particular contexts, since the former two involve larger numbers of "nameless" features, while the latter ones usually focus on fewer but more important landmarks.…”

Section: Introductionmentioning

confidence: 99%

“…The two main approaches for conceiving a point feature tracker are iterative first-order differential approximation [5,6], and exhaustive matching [2,7]. In both approaches, a straightforward implementation based on integrating inter-frame motion is a viable solution only for short-term operation, due to the incontrollable growth of the accumulated drift.…”

Section: Introductionmentioning

confidence: 99%

“…In both approaches, a straightforward implementation based on integrating inter-frame motion is a viable solution only for short-term operation, due to the incontrollable growth of the accumulated drift. It is therefore necessary either to adapt the higher-level task to work only with short feature tracks [2], if applicable, or to devise a monitoring approach which would try to correct the drift by aligning the current appearance of the feature with a previously stored template image or reference. The desired alignment is usually performed by minimizing the norm of the error image, which is obtained by subtracting the current feature from the reference [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support

Šegvić

Remazeilles

Chaumette

2006

Computer Vision – ECCV 2006

View full text Add to dashboard Cite

Abstract. We consider the problem of tracking a given set of point features over large sequences of image frames. A classic procedure for monitoring the tracking quality consists in requiring that the current features nicely warp towards their reference appearances. The procedure recommends focusing on features projected from planar 3D patches (planar features), by enforcing a conservative threshold on the residual of the difference between the warped current feature and the reference. However, in some important contexts, there are many features for which the planarity assumption is only partially satisfied, while the true planar features are not so abundant. This is especially true when the motion of the camera is mainly translational and parallel to the optical axis (such as when driving a car along straight sections of the road), which induces a permanent increase of the apparent feature size. Tracking features containing occluding boundaries then becomes an interesting goal, for which we propose a multi-scale monitoring solution striving to maximize the lifetime of the feature, while also detecting the tracking failures. The devised technique infers the parts of the reference which are not projected from the same 3D surface as the patch which has been consistently tracked until the present moment. The experiments on real sequences taken from cars driving through urban environments show that the technique is effective in increasing the average feature lifetimes, especially in sequences with occlusions and large photometric variations.The presented work has been performed within the french national project Predit Mobivip (Individual Public Vehicles for Mobility in the City), and within the project Robea Bodega. The authors would also like to acknowledge Prof. Axel Pinz for a helpful discussion on this subject.

show abstract

Relative Navigation in GPS‐Degraded Environments

Wheeler

Nyholm

Koch

et al. 2016

Encyclopedia of Aerospace Engineering

View full text Add to dashboard Cite

For unmanned aircraft systems to become fully integrated into society, safe and reliable methods for estimation and control are required even when global measurements such as GPS are degraded or unavailable. In these situations, estimating the vehicle's global state directly leads to inaccuracy and inconsistency. The relative navigation framework avoids these issues by estimating the vehicle's state with respect to a current local coordinate frame associated with a visual odometry algorithm. A globally consistent and localized pose‐graph map is produced by compounding these local estimates and opportunistically incorporating additional constraints such as GPS measurements and loop closures. This architecture increases the safety and performance of the system by decoupling critical tasks, such as stabilization and obstacle avoidance, from tasks such as global map optimization and mission planning that are more computationally intensive and can produce discontinuities. The architecture and components of the general relative navigation framework are described, and hardware results are presented for an example multirotor implementation.

show abstract

Visual odometry

Cited by 1,164 publications

References 11 publications

Efficient generation of 3D surfel maps using RGB–D sensors

Efficient generation of 3D surfel maps using RGB–D sensors

Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support

Relative Navigation in GPS‐Degraded Environments

Contact Info

Product

Resources

About