A Novel Relative Camera Motion Estimation Algorithm with Applications to Visual Odometry

Jiang, Yue; Kang, Mun-Cheon; Fan, Ming; Chae, Sung-Ho; Ko, Sung-Jea

doi:10.1109/ism.2018.000-4

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Afterwards, it can be projected on the k th image via camera model with the coordinate p ′ i . The brightness of the same point in the two consecutive frames is assumed unchanged due to the transient time interval (Jiang et al, 2018). Thus, the residual function can be formed based on the gray value difference of the image patches adjacent the (k − 1) th feature point and the reprojected point of the…”

Section: Step I Direct Methods Based Pose Estimationmentioning

confidence: 99%

“…Visual localization is generally realized via visual SLAM technologies, where the visual odometry (VO) (Jiang et al, 2018) can be used to estimate the pose variation of the camera via captured consecutive frames, usually divided into two categories, i.e., indirect/feature-based methods and direct methods (Su and Cai, 2018). The most representative of the feature methods is the ORB-SLAM (Mur-Artal et al, 2015), with the aid of ORB (Oriented FAST and Rotated Brief) feature possessing rotation invariance and scale invariance via pyramid construction so as to assist SLAM algorithm to have endogenous consistency in the feature extraction and tracking, keyframe selection, 3D reconstruction, and closed-loop detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

UAV Based Indoor Localization and Objection Detection

Zhou

2022

Front. Neurorobot.

View full text Add to dashboard Cite

This article targets fast indoor positioning and 3D target detection for unmanned aerial vehicle (UAV) real-time task implementation. With the combined direct method and feature method, a method is proposed for fast and accurate position estimation of the UAV. The camera pose is estimated by the visual odometer via the photometric error between the frames. Then the ORB features can be extended from the keyframes for the map consistency improvement by Bundle Adjustment with local and global optimization. A depth filter is also applied to assist the convergence of the map points with depth information updates from multiple frames. Moreover, the convolutional neural network is used to detect the specific target in an unknown space, while YOLOv3 is applied to obtain the semantic information of the target in the images. Thus, the spatial map points of the feature in the keyframes can be associated with the target detection box, while the statistical outlier filter can be simultaneously applied to eliminate the noise points. Experiments with public dataset, and field experiments on the established UAV platform in indoor environments have been carried out for visual based fast localization and object detection in real-time for the efficacy verification of the proposed method.

show abstract

Section: Step I Direct Methods Based Pose Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

UAV Based Indoor Localization and Objection Detection

Zhou

2022

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

Confidence Estimator Design for Dynamic Feature Point Removal in Robot Visual-Inertial Odometry

Reginald

Al-Buraiki

Fi̇dan

et al. 2022

IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society

View full text Add to dashboard Cite

An Accurate and Efficient Voting Scheme for a Maximally All-Inlier 3D Correspondence Set

Sahloul

Shirafuji

Ota

2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

We present a highly accurate and efficient, yet simple, two-stage voting scheme for distinguishing inlier 3D correspondences by densely assessing and ranking their local and global geometric consistencies. The strength of the proposed method stems from both the novel idea of post-validated voting set, as well as single-point superimposition transforms, which are computationally cheap and avoid rotational ambiguities. Using a well-known dataset consisting of various 3D models and numerous scenes that include different occlusion rates, the proposed scheme is evaluated against state-of-the-art 3D voting schemes, in terms of both the correspondence PR (precision-recall) AUC (area under curve), and the execution time. A total of 374 experiments were conducted for each method, which involved a combination of four models, 50 scenes, and two down-samplings. The proposed scheme outperforms the state-of-the-art 3D voting schemes in terms of both accuracy and speed. Quantitatively, the proposed scheme scores 97.0 % ± 12.9 % on the PR AUC metric, averaged over all of the experiments, while the two state-of-the-art schemes score 74.2 % ± 22.2 % and 78.3 % ± 26.4 %. Furthermore, the proposed scheme requires only 24.1 % ± 6.0 % of the time consumed by the fastest state-of-the-art scheme. The proposed voting scheme also demonstrates high robustness against occlusions and scarce inliers.

show abstract

A Novel Relative Camera Motion Estimation Algorithm with Applications to Visual Odometry

Cited by 3 publications

References 9 publications

UAV Based Indoor Localization and Objection Detection

UAV Based Indoor Localization and Objection Detection

Confidence Estimator Design for Dynamic Feature Point Removal in Robot Visual-Inertial Odometry

An Accurate and Efficient Voting Scheme for a Maximally All-Inlier 3D Correspondence Set

Contact Info

Product

Resources

About