Indoor RGB-D Compass from a Single Line and Plane

Kim, Pyojin; Coltin, Brian; Kim, H. Jin

doi:10.1109/cvpr.2018.00491

Cited by 15 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other techniques based on the shape of objects such as coplanar circles [9] and repeated patterns [40] have also been proposed. When an RGB-D camera is available, one can solve for the upright orientation by assuming an ideal Manhattan world [15,42,43,24]. When the scene in question has been mapped in 3D, one can also solve for the camera pose by re-localizing the cameras with respect to the 3D maps [29,7,39,8,23].…”

Section: Related Workmentioning

confidence: 99%

UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images

Xian

Snavely

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We introduce UprightNet, a learning-based approach for estimating 2DoF camera orientation from a single RGB image of an indoor scene. Unlike recent methods that leverage deep learning to perform black-box regression from image to orientation parameters, we propose an end-to-end framework that incorporates explicit geometric reasoning. In particular, we design a network that predicts two representations of scene geometry, in both the local camera and global reference coordinate systems, and solves for the camera orientation as the rotation that best aligns these two predictions via a differentiable least squares module. This network can be trained end-to-end, and can be supervised with both ground truth camera poses and intermediate representations of surface geometry. We evaluate UprightNet on the single-image camera orientation task on synthetic and real datasets, and show significant improvements over prior state-of-the-art approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images

Xian

Snavely

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…The method proposed by Kim et al [22] exploited both line and plane primitives to deal with degenerate cases in surface-normal-based methods for stable and accurate zero-drift rotation estimation. In the work of Kim et al [27], only a single line and a single plane in RANSAC were used to estimate camera orientation, and refinement is performed by minimizing the average orthogonal distance from the endpoints of the lines parallel to the MW axes once the initial rotation estimation is found. Bazin et al [17] introduced a related one-line RANSAC for situations where the horizon plane is known.…”

Section: Center Of Projectionmentioning

confidence: 99%

“…We compared our proposed approach with two state-of-the-art MW-based methods proposed by Zhou et al [23] and Kim et al [27], namely, orthogonal planes based rotation estimation (OPRE) and 1P1L. OPRE estimates absolute and drift-free rotation by exploiting orthogonal planes from depth images.…”

mentioning

confidence: 99%

Robust Visual Compass Using Hybrid Features for Indoor Environments

et al. 2019

View full text Add to dashboard Cite

Orientation estimation is a crucial part of robotics tasks such as motion control, autonomous navigation, and 3D mapping. In this paper, we propose a robust visual-based method to estimate robots’ drift-free orientation with RGB-D cameras. First, we detect and track hybrid features (i.e., plane, line, and point) from color and depth images, which provides reliable constraints even in uncharacteristic environments with low texture or no consistent lines. Then, we construct a cost function based on these features and, by minimizing this function, we obtain the accurate rotation matrix of each captured frame with respect to its reference keyframe. Furthermore, we present a vanishing direction-estimation method to extract the Manhattan World (MW) axes; by aligning the current MW axes with the global MW axes, we refine the aforementioned rotation matrix of each keyframe and achieve drift-free orientation. Experiments on public RGB-D datasets demonstrate the robustness and accuracy of the proposed algorithm for orientation estimation. In addition, we have applied our proposed visual compass to pose estimation, and the evaluation on public sequences shows improved accuracy.

show abstract

“…For extensive tasks relevant to 3D vision, such as camera calibration [10,43,56], matching across views [44] and 3D reconstruction [20,37,56] , edges have demonstrated more robustness to lighting changes and preserve more information than points. Several recent works [22,55,60] show that line segments could largely facilitate 3D modeling of indoor scenes.…”

Section: Introductionmentioning

confidence: 99%

PPGNet: Learning Point-Pair Graph for Line Segment Detection

Zhang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

In this paper, we present a novel framework to detect line segments in man-made environments. Specifically, we propose to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods. In order to extract a line segment graph from an image, we further introduce the PPGNet, a convolutional neural network that directly infers a graph from an image. We evaluate our method on published benchmarks including York Urban and Wireframe datasets. The results demonstrate that our method achieves satisfactory performance and generalizes well on all the benchmarks. The source code of our work is available at https://github.com/svip-lab/PPGNet.

show abstract

Indoor RGB-D Compass from a Single Line and Plane

Cited by 15 publications

References 21 publications

UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images

UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images

Robust Visual Compass Using Hybrid Features for Indoor Environments

PPGNet: Learning Point-Pair Graph for Line Segment Detection

Contact Info

Product

Resources

About