Low-Drift Visual Odometry in Structured Environments by Decoupling Rotational and Translational Motion

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

doi:10.1109/icra.2018.8463207

Cited by 69 publications

(43 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our proposed approach with five methods: ORB-SLAM2 [10], DVO [24], InfiniTAM [25], LPVO [27], and L-SLAM [28]. ORB-SLAM2 is a state-of-the-art point-based SLAM system; DVO estimates the robust poses with photometric and depth error by using the color and depth images together; InfiniTAM estimates the camera poses from the RGB and depth images with a GPU in real time; LPVO exploits the line and plane to estimate the zero-drift rotation and then estimates the 3D poses with tracked points in the MW scenes; L-SLAM estimates the camera position and plane landmarks with a linear SLAM formulation in the MW environments.…”

Section: Resultsmentioning

confidence: 99%

“…Zhou et al [26] developed a mean shift paradigm to extract and track planar modes to achieve drift-free rotation, and they estimated the translation using three simple 1D density alignments in man-made environments. In the work of Kim et al [27], lines and planes were exploited to estimate drift-free rotation, and the translation was recovered by minimizing the de-rotated reprojection error. Kim et al [28] also proposed a linear SLAM method based on the Bayesian filtering framework for MW scenes.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

RGB-D SLAM Using Point–Plane Constraints for Indoor Environments

Guo

Peng

Wang

et al. 2019

Sensors

View full text Add to dashboard Cite

Pose estimation and map reconstruction are basic requirements for robotic autonomous behavior. In this paper, we propose a point–plane-based method to simultaneously estimate the robot’s poses and reconstruct the current environment’s map using RGB-D cameras. First, we detect and track the point and plane features from color and depth images, and reliable constraints are obtained, even for low-texture scenes. Then, we construct cost functions from these features, and we utilize the plane’s minimal representation to minimize these functions for pose estimation and local map optimization. Furthermore, we extract the Manhattan World (MW) axes on the basis of the plane normals and vanishing directions of parallel lines for the MW scenes, and we add the MW constraint to the point–plane-based cost functions for more accurate pose estimation. The results of experiments on public RGB-D datasets demonstrate the robustness and accuracy of the proposed algorithm for pose estimation and map reconstruction, and we show its advantages compared with alternative methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

RGB-D SLAM Using Point–Plane Constraints for Indoor Environments

Guo

Peng

Wang

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Hybrid approaches use both surface normals obtained in depth image and vanishing directions extracted in the RGB image to estimate rotation, which shows more robust performance. 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.…”

Section: Center Of Projectionmentioning

confidence: 99%

“…We tested pose estimation on four datasets, "Living Room 2", "Office Room 3", "fr3_struc_tex", and "fr3_nostruc_tex". These datasets provide the ground-truth pose for each image; we measured the root mean squared error (RMSE) of the absolute translational error (ATE) and compared it with state-of-the-art approaches, namely, ORB_SLAM [12], dense visual odometry (DVO) [15], and line-plane based visual odometry (LPVO) [22]. The comparison of ATE.RMSE is shown in Table 3; the smallest error for each sequence is indicated in bold.…”

Section: Application To Pose Estimationmentioning

confidence: 99%

“…Since 3D geometric structures can easily be calculated by using the camera that provides both depth information and color image with 3 channels (red, green, and blue), called the RGB-D camera. The RGB-D camera has become a popular alternative to monocular and stereo cameras for the purpose of rotation estimation, and estimation accuracy has been prominently improved by using the MW assumption with a RGB-D camera [20][21][22][23]. However, a major disadvantage of these MW-based methods is that the number of lines and planes used for tracking the MW axes must be no less than 2, which is the minimal sampling for 3 degrees of freedom (DoF).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

RLP‐VIO: Robust and lightweight plane‐based visual‐inertial odometry for augmented reality

Zhou

Yang

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

We propose RLP-VIO-a robust and lightweight monocular visual-inertial odometry system using multiplane priors. With planes extracted from the point cloud, visual-inertial-plane PnP uses the plane information for fast localization. Depth estimation is susceptible to degenerated motion, so the planes are expanded in a reprojection consensus-based way robust to depth errors.For sensor fusion, our sliding-window optimization uses a novel structureless plane-distance error cost, which prevents the fill-in effect that poisons the BA problem's sparsity and permits the use of a smaller sliding window while maintaining good accuracy. The total computational cost is further reduced with our modified marginalization strategy. To further improve the tracking robustness, the landmark depths are constrained using the planes during degenerated motion. The whole system is parallelized with a three-stage pipeline. Under controlled environments, this parallelization runs deterministically and produces consistent results. The resulting VIO system is tested on widely used datasets and compared with several state-of-the-art systems. Our system achieves competitive accuracy and works robustly even on long and challenging sequences.To demonstrate the effectiveness of the proposed system, we also show the AR application running on mobile devices in real-time.

show abstract

Low-Drift Visual Odometry in Structured Environments by Decoupling Rotational and Translational Motion

Cited by 69 publications

References 5 publications

RGB-D SLAM Using Point–Plane Constraints for Indoor Environments

RGB-D SLAM Using Point–Plane Constraints for Indoor Environments

Robust Visual Compass Using Hybrid Features for Indoor Environments

RLP‐VIO: Robust and lightweight plane‐based visual‐inertial odometry for augmented reality

Contact Info

Product

Resources

About