On-Line Vehicle Motion Estimation from Visual Terrain Information Part I: Recursive Image Registration

Merhav, S. J.; Bresler, Yoram

doi:10.1109/taes.1986.310725

Cited by 33 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The efficiency of this temporal redundancy removal depends on the efficiency and accuracy of the motion estimation. There are two classes of motion estimation methods, block matching algorithms (BMA) [2], [3] and pel-recursive algorithms (PRA) [4]. A PRA estimates motion on a pixel-by-pixel basis, whereas a BMA estimates motion on a block-by-block basis.…”

Section: Fast Algorithms For the Estimation Of Motion Vectorsmentioning

confidence: 99%

Hybrid estimation of navigation parameters from aerial image sequence

Sim

Jeong

Lee

et al. 1999

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-This work presents a hybrid method for navigation parameter estimation using sequential aerial images, where navigation parameters represent the position and velocity information of an aircraft for autonomous navigation. The proposed hybrid system is composed of two parts: relative position estimation and absolute position estimation. Computer simulation with two different sets of real aerial image sequences shows the effectiveness of the proposed hybrid parameter estimation algorithm.

show abstract

Section: Fast Algorithms For the Estimation Of Motion Vectorsmentioning

confidence: 99%

Hybrid estimation of navigation parameters from aerial image sequence

Sim

Jeong

Lee

et al. 1999

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…One of the popular frame-frame methods is SLAM (Simultaneous Localisation and Mapping) (Bailey and Durrant-Whyte, 2006), which estimates the camera motion by image matching between the current and the previous frames. Without absolute positioning information, however, these methods suffer from a drift problem which can be moderately reduced by applying filters, such as Kalman filter (Bosse, 1997) and extended Kalman filter (EKF) Merhav and Bresler, 1986). However, these methods rely on the assumption of loop closures which means that UAVs need to fly on the same area twice (Lin and Medioni, 2007).…”

Section: Introductionmentioning

confidence: 99%

Illumination-invariant image matching for autonomous UAV localisation based on optical sensing

Wan

Liu

Yan

et al. 2016

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

“…For example, Ref. [1] proposed integrating the velocity-to-height vision-based estimation with additional on-board sensors; Ref. [2] applied the subspace-constraint approach [3] to partially estimate an airborne platform's states based on measurements from an image registration process injected into an Implicit Extended Kalman filter; and Ref.…”

Section: Introductionmentioning

confidence: 99%

Navigation Aiding Based on Coupled Online Mosaicking and Camera Scanning

Indelman

Gurfil

Rivlin

et al. 2010

Journal of Guidance, Control, and Dynamics

View full text Add to dashboard Cite

This paper presents a new method for vision-aided navigation of airborne platforms. The method is based on online mosaicking using images acquired by an on-board gimballed camera, which scans ground regions in the vicinity of the flight trajectory. The coupling of the scanning and mosaicking processes improves image-based motion estimation when operating in challenging scenarios such as narrow field-of-view cameras observing low-texture scenes. These improved motion estimations are fused with an inertial navigation system. The mosaic used for navigation is constructed in two levels. A small mosaic based on recently captured images is computed in real-time, and a larger mosaic including all the images is computed in a background process. The low-level mosaic is used for immediate motion estimation, while the higher-level mosaic is used for global navigation. The correlation terms between the navigation system and the mosaic construction process are not maintained in the proposed approach. The advantage of this architecture is the low computational load required for navigation aiding. However, the accuracy of the proposed method could be compromised compared to bearing-only Simultaneous Localization and Mapping (SLAM). The new method was examined using statistical simulation runs and experiments based on Google Earth imagery, showing its superior performance compared to traditional methods for two-view navigation aiding.

show abstract

On-Line Vehicle Motion Estimation from Visual Terrain Information Part I: Recursive Image Registration

Cited by 33 publications

References 5 publications

Hybrid estimation of navigation parameters from aerial image sequence

Hybrid estimation of navigation parameters from aerial image sequence

Illumination-invariant image matching for autonomous UAV localisation based on optical sensing

Navigation Aiding Based on Coupled Online Mosaicking and Camera Scanning

Contact Info

Product

Resources

About