Rotation Estimation Research Articles

Low-Complexity Visible Light Positioning and Rotation Estimation Based on Eigenvalue Decomposition

Most existing visible light positioning (VLP) systems assume vertically placed receivers, or estimate the receiver rotations through gyroscopes. Although several recent VLP systems can deal with the arbitrary tilting of the receiver without the additional sensors, the positioning frequency, algorithm efficiency and stability are still to be improved. In this work, we propose a novel positioning and rotation estimation algorithm based on the eigenvalue decomposition of the covariance matrix of light direction vectors. Four or more light-emitting diodes (LEDs) serve as the anchors and three or more tilted photodiodes are equipped on the mobile receiver. The new algorithm's computational complexity only grows linearly with the number of LEDs, and it can distinguish and bypass the local optima by verifying if the objective function reaches its theoretical maximum. We use simulations to reveal the error patterns of the algorithm and build a low-cost prototype to verify its real performance. The measured average positioning error is 1.83 cm and the orientation estimation error is 0.04 rad. The proposed scheme can be used for positioning and navigation that require fast response, low power consumption, low cost, high accuracy and small device size.

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator.

The electro-hydrostatic actuator (EHA) is a promising actuating apparatus used in flight control systems for more electric aircraft (MEA) due to its high power density and low maintenance. Since the reliability of the system decreases with increasing complexity, fault detection is becoming increasingly important. In this paper, an adaptive filter was designed based on a normalized least mean square (NLMS) algorithm, which could identify the resistance of the motor windings online to detect electrical faults in the EHA. Additionally, based on the analytical relationship between rotational speed and displacement, a rotational speed estimation method was designed. By comparing the actual rotational speed with the estimated one, hydraulic faults could be detected. To verify the efficacy of the aforementioned method, software was applied for the modeling and simulations, which included fault injection and detection. On this basis, an experimental platform was built and then subjected to a series of validation experiments. The results indicate that the fault detection method has the potential to detect electrical and hydraulic faults in an EHA.

Contrast independent biologically inspired translational optic flow estimation

The visual systems of insects are relatively simple compared to humans. However, they enable navigation through complex environments where insects perform exceptional levels of obstacle avoidance. Biology uses two separable modes of optic flow to achieve this: rapid gaze fixation (rotational motion known as saccades); and the inter-saccadic translational motion. While the fundamental process of insect optic flow has been known since the 1950’s, so too has its dependence on contrast. The surrounding visual pathways used to overcome environmental dependencies are less well known. Previous work has shown promise for low-speed rotational motion estimation, but a gap remained in the estimation of translational motion, in particular the estimation of the time to impact. To consistently estimate the time to impact during inter-saccadic translatory motion, the fundamental limitation of contrast dependence must be overcome. By adapting an elaborated rotational velocity estimator from literature to work for translational motion, this paper proposes a novel algorithm for overcoming the contrast dependence of time to impact estimation using nonlinear spatio-temporal feedforward filtering. By applying bioinspired processes, approximately 15 points per decade of statistical discrimination were achieved when estimating the time to impact to a target across 360 background, distance, and velocity combinations: a 17-fold increase over the fundamental process. These results show the contrast dependence of time to impact estimation can be overcome in a biologically plausible manner. This, combined with previous results for low-speed rotational motion estimation, allows for contrast invariant computational models designed on the principles found in the biological visual system, paving the way for future visually guided systems.

Image Large Rotation and Scale Estimation Using the Gabor Filter

This paper proposes a novel image large rotation and scale estimation method based on the Gabor filter and pulse-coupled neural network (PCNN). First, the Gabor features of the template image and its rotated one are extracted by performing the Gabor filter. Second, we present a modified PCNN model to measure the similarity between the Gabor features of the image and its rotated one. Finally, the rotation angle is calculated by searching the global minimum of the correlation coefficients. Besides rotation estimation, we also propose a scale estimation method based on the max-projection strategy. The Gabor feature image is projected along the estimated rotation angle, and the scale is calculated by searching the peak of this projection result. Moreover, experiments illustrate that the proposed method has high accuracy on rotation and scale estimation and is robust to noise. Compared with the state-of-the-art methods, the proposed approach has a more stable performance.

Rotation Estimation Based on Serial Network and Application in Cave Buddha Statues

Rotation estimation is one of the crucial elements of pose estimation. Accurate pose estimation facilitates the observation of objects in the metaverse and is also the most fundamental part of automated archaeological mapping. Many studies have been conducted on 6D pose estimation, but no systematic study has only been conducted on 3D rotation estimation. We systematically study the rotation estimation problem for 3D point cloud models. Firstly, we discuss the representation of rotation and how it affects the training of the neural network. After that, the dataset is created. A new method of generating labels is also proposed, in which two points are used as labels, with the two points being able to recover the initial orientation. Finally, a new serial network is proposed, which can be used to improve the performance of rotational estimation systems. The research described in this paper has been successfully applied to the restoration of the Huangze Temple Grotto Buddha statue in Guangyuan, Sichuan Province, providing a reliable scheme for solving the rotation estimation problem with faster convergence and higher accuracy.

How much I moved: Robust biases in self-rotation perception

Vestibular cues are crucial to sense the linear and angular acceleration of our head in three-dimensional space. Previous literature showed that vestibular information precociously combines with other sensory modalities, such as proprioceptive and visual, to facilitate spatial navigation. Recent studies suggest that auditory cues may improve self-motion perception as well. The present study investigated the ability to estimate passive rotational displacements with and without virtual acoustic landmarks to determine how vestibular and auditory information interact in processing self-motion information. We performed two experiments. In both, healthy participants sat on a Rotational-Translational Chair. They experienced yaw rotations along the earth-vertical axis and performed a self-motion discrimination task. Their goal was to estimate both clockwise and counterclockwise rotations’ amplitude, with no visual information available, reporting whether they felt to be rotated more or less than 45°. According to the condition, vestibular-only or audio-vestibular information was present. Between the two experiments, we manipulated the procedure of presentation of the auditory cues (passive vs. active production of sounds). We computed the point of subjective equality (PSE) as a measure of accuracy and the just noticeable difference (JND) as the precision of the estimations for each condition and direction of rotations. Results in both experiments show a strong overestimation bias of the rotations, regardless of the condition, the direction, and the sound generation conditions. Similar to previously found heading biases, this bias in rotation estimation may facilitate the perception of substantial deviations from the most relevant directions in daily navigation activities.

Constraining the interiors of asteroids through close encounters

ABSTRACT Knowledge of the interior density distribution of an asteroid can reveal its composition and constrain its evolutionary history. However, most asteroid observational techniques are not sensitive to interior properties. We investigate the interior constraints accessible through monitoring variations in angular velocity during a close encounter. We derive the equations of motion for a rigid asteroid’s orientation and angular velocity to arbitrary order and use them to generate synthetic angular velocity data for a representative asteroid on a close Earth encounter. We develop a toolkit AIME (Asteroid Interior Mapping from Encounters) which reconstructs asteroid density distribution from these data, and we perform injection-retrieval tests on these synthetic data to assess AIME’s accuracy and precision. We also perform a sensitivity analysis to asteroid parameters (e.g. asteroid shape and orbital elements), observational setup (e.g. measurement precision and cadence), and the mapping models used. We find that high precision in rotational period estimates (≲0.27 s) is necessary for each cadence, and that low perigees (≲ 18 Earth radii) are necessary to resolve large-scale density non-uniformities with uncertainties of $\sim 0.1{{\ \rm per\ cent}}$ of the local density under some models.

DR-SLAM: drift rejection SLAM with Manhattan regularity for indoor environments

In this paper, a drift rejection SLAM (Simultaneous Localization and Mapping) method is proposed targeting indoor scenarios, where SLAM generates large drifts due to the lack of reliable features. To provide sufficient features, we leverage multiple feature primitives and geometric restraints (parallel or perpendicular) restraint in man-made environments. Under some satisfy Manhattan World (MW) assumption scene, such as corridors, we can get absolute and drift-free rotation estimation using a Gaussian sphere. By fully utilizing drift-free rotation estimation under MW assumption and the local stability of purely track restricted by point, line, and plane features, our drift rejection SLAM method becomes more accurate and robust. Additionally, by exploiting the constraint of planar motion on ground robot, we propose an ingenious strategy to reduce translation drift by eliminating vertical movement in the Manhattan world. Advantages of our method over other state-of-the-art algorithms are validated on public datasets and real-world experiments. The code is released at https://github.com/WangWen-Believer/DR-SLAM.

Rotation-aware dynamic temporal consistency with spatial sparsity correlation tracking

Recently, discriminative correlation filter (DCF)-based trackers have been widely applied to visual tracking. However, a significant problem of DCF-based trackers is that the model uses the fixed patterns of temporal modeling and fails to suppress the distractive features. To obviate the issue, we propose the dynamic temporal consistency with spatial sparsity correlation filter. The dynamics refers to the adaptive temporal consistency hidden in the response maps and dynamic lasso constraint moderated by the prior knowledge. Unlike the classical temporal modeling method applied to filter model, we exploit the consistency of the response maps to perceive adaptive temporal continuity modeling to enable the filter to have self-regularized ability. Temporal modeling and spatial sparsity are incorporated in a unified optimization learning model and optimized together with ADMM algorithm and Sherman-Morrison formula. In particular, the tracking performance is hindered by the weak capacity to rotation variation. For the sake of estimating the rotation angle accurately to maintain rotation invariance, we explore the coarse-to-fine rotation estimation module. The coarse rotation is supported by the angle pool and the part-based tracker. By introducing the connected hyper ellipse fitting strategy to eliminate fake distractors to ensure a pure target region, the fine level attempts to achieve the optimal rotation angle with the minimum second order statistical bias. The design enables the filter to train with the recovered rotated image instead of axis-aligned bounding box, which attributes to alleviating the impact of ambiguous region and concentrating on the interested target. Extensive experimental results validate the superiority of the proposed method against other state-of-the art trackers and exhibit a remarkable generality in the rotated challenging scenarios. • Dynamic temporal modeling can make the filter highlight the ever-changing region. • Dynamic temporal consistency modeling and spatial sparsity are incorporated in a unified optimization learning model. • The connected hyper ellipse fitting strategy tries to achieve the optimal rotation angle. • Comprehensive experiments have fully demonstrated the superior performance of our proposed method.

Overview of RBF NN and Antenna Systems

This paper presents the application of Radial Basis Function neural network in antenna array systems and in the estimation of polarization rotation estimation in the ionosphere. Radial Basis Function neural network is used as it satisfies both universal and best approximation property. We present the architecture of the network, as part of the total system. Presented results show low mean error values and very good match between the referent values and gained one, which shows the successfulness of the particular neural network.

An Adaptive and Accurate Method for Rotational Angular Velocity Estimation of Rotor Targets via Fourier Coefficient Interpolation

As a special micro-motion feature of rotor targets, rotational angular velocity can provide a discriminant basis for target classification and recognition. In this paper, an adaptive and accurate method is proposed for estimating the rotational angular velocity of rotor targets via a Fourier coefficient interpolation algorithm that is based on modified frequency index residue initialization. The negative frequency complex exponential signal component is removed at each iteration to eliminate the estimation bias caused by spectrum superposition and improve the estimation accuracy. The frequency index residue initialization is modified, based on a normalized Fourier spectrum, to improve the estimable range of the rotational angular velocity and reduce the computational complexity of the algorithm. The simulation results show that the estimation performance of the proposed method achieves the Cramér–Rao lower bound and outperforms state-of-the-art methods in terms of the estimable range and estimation accuracy of the rotational angular velocity.

Tomato harvesting robotic system based on Deep-ToMaToS: Deep learning network using transformation loss for 6D pose estimation of maturity classified tomatoes with side-stem

This paper presents the development of an autonomous harvesting robot system for tomato, a representative crop cultivated in the facility horticulture smart farm. The automated harvesting work using a robotic system is very challenging because of the appearance, environmental features, such as the atypical directions of the peduncles or their growing form in a bunch. Also, the robot system should enable the harvesting of the target fruit only without damaging other fruits, stems, and branches. Hence, this paper presents a deep learning network pipeline, Deep-ToMaToS, capable of three-level maturity classification and 6D pose (3D translation + 3D rotation) estimation of the target fruit simultaneously. Due to the difficulties encountered in building a large-scale dataset to train and test the deep learning model for the 6D pose estimation in the real world, we presented an automatic data collection scheme based on a photo-realistic 3D simulator environment. The robotic harvesting system includes a harvesting motion control algorithm based on the result of the 6D pose estimation. The overall process of the motion control phase is described along with the decision way of the appropriate final posture of the harvesting module mounted at the end-effector of the robot manipulator via removal of invalid motions getting out of the valid workspace or redundant motions. We conducted experiments on the 6D pose estimation based on the Deep-ToMaToS and the harvesting motion control in virtual and real smart farm environments. The experimental results showed a 6D pose estimation accuracy of 96 % based on the ADD_S metric, and the proposed harvesting motion control algorithm achieves the harvesting success rate of 84.5 % on average. The experimental results reveal that the harvesting robot system has significant potential to extend to harvesting works for other fruits and crops.

Squeezing-enhanced parameter estimation with a hybrid spin-oscillator interferometer

Inspired by the recent work [Nature (London) 521, 336 (2015)], we propose a scheme to suppress the backaction-induced dephasing of the spin state in a spin-oscillator system by squeezing the quantum fluctuation of the two-mode oscillator. We show specifically that squeezing either on a single mode individually or on both modes simultaneously could be used to effectively suppress spin dephasing. Therefore, with a spin-oscillator interferometer input by the spin-dependent squeezing cat state, the sensitivity of the rotational parameter estimation can be significantly enhanced. Given that various squeezings on the two-mode vibrations of the oscillator have been experimentally demonstrated, the proposal could provide a possibility to implement the sensitive parameter estimation, particularly in the ion-trap system.

Iterative BTreeNet: Unsupervised learning for large and dense 3D point cloud registration

3D point cloud registration is a computational process that aligns two 3D point clouds through transformation. i.e. finding matching translation and rotation. Existing state-of-the-art learning-based methods require ground-truth transformation as supervision and often perform poorly in dealing with partial point clouds and large scenes that are not trained, resulting in poor generalization for neural networks.In this paper, we propose a novel unsupervised deep learning network - Binary Tree Network (BTreeNet) that consists of a novel forward propagation, which learns features for the rotation separately from the translation and avoids the interference between the estimations of rotation and translation in one single matrix. We then propose an Iterative Binary Tree Network (IBTreeNet) to continuously improve the registration accuracy for large and dense 3D point clouds. The Chamfer Distance and the Earth Mover’s Distance are adopted as the loss function for unsupervised learning. We show that BTreeNet and IBTreeNet outperform state-of-the-art learning-based and traditional methods on partial and noisy point clouds without training them in such scenarios. Most importantly, the proposed methods exhibit remarkable generalization and robustness to unseen large and dense scenes that are never trained.

A Quadrifocal Tensor SFM Photogrammetry Positioning and Calibration Technique for HOFS Aerial Sensors

Nowadays, the integration between photogrammetry and structure from motion (SFM) has become much closer, and many attempts have been made to combine the two approaches to realize the positioning, calibration, and 3D reconstruction of a large number of images. For the positioning and calibration of high oblique frame sweep (HOFS) aerial cameras, a quadrifocal tensor SFM photogrammetry technique is proposed to resolve the positioning and calibration task of such cameras. It adopts the quadrifocal tensor idea into the OpenMVG SFM pipeline to solve the complexity problem caused by the small single-viewing imaging area and the high image overlapping ratio. It also integrates the photogrammetry iteration idea into the OpenMVG SFM pipeline to enhance the positioning and calibration accuracy, which includes a coarse to fine three-stage Bundle Adjustment (BA) processing approach. In this paper, the overall workflow of the proposed technique was first introduced in detail, from feature extraction and image matching, relative rotation and translation estimation, global rotation and translation estimation, and the quadrifocal tensor model construction to the three-stage BA process and calibration. Then, experiments were carried out in the Zhengzhou area, implementing four types of adjustment methods. The results suggest that the proposed quadrifocal tensor SFM photogrammetry is suitable for large tilt frame sweep camera positioning and calibration without prior information on detailed camera intrinsic parameters and structure. The modifications made to the OpenMVG SFM pipeline enhanced the precision of image positioning and calibration and provided the precision level of professional photogrammetry software.

An Unsupervised Monocular Visual Odometry Based on Multi-Scale Modeling.

Unsupervised deep learning methods have shown great success in jointly estimating camera pose and depth from monocular videos. However, previous methods mostly ignore the importance of multi-scale information, which is crucial for pose estimation and depth estimation, especially when the motion pattern is changed. This article proposes an unsupervised framework for monocular visual odometry (VO) that can model multi-scale information. The proposed method utilizes densely linked atrous convolutions to increase the receptive field size without losing image information, and adopts a non-local self-attention mechanism to effectively model the long-range dependency. Both of them can model objects of different scales in the image, thereby improving the accuracy of VO, especially in rotating scenes. Extensive experiments on the KITTI dataset have shown that our approach is competitive with other state-of-the-art unsupervised learning-based monocular methods and is comparable to supervised or model-based methods. In particular, we have achieved state-of-the-art results on rotation estimation.

Rotation Estimation Based on Anisotropic Angular Radon Spectrum

In this paper, we present the anisotropic Angular Radon Spectrum (ARS), a novel feature for global estimation of rotation in a two dimension space. ARS effectively describes collinearity of points and has the properties of translation-invariance and shift-rotation. We derive the analytical expression of ARS for Gaussian Mixture Models (GMM) representing point clouds where the Gaussian kernels have arbitrary covariances. Furthermore, we developed a preliminary procedure for simplification of GMM suitable for efficient computation of ARS. Rotation between point clouds is estimated by searching of maximum of correlation between their spectra. Correlation is efficiently computed from Fourier series expansion of ARS. Experiments on datasets of distorted object shapes, laser scans and on robotic mapping datasets assess the accuracy and robustness to noise in global rotation estimation.

Homography Decomposition Networks for Planar Object Tracking

Planar object tracking plays an important role in AI applications, such as robotics, visual servoing, and visual SLAM. Although the previous planar trackers work well in most scenarios, it is still a challenging task due to the rapid motion and large transformation between two consecutive frames. The essential reason behind this problem is that the condition number of such a non-linear system changes unstably when the searching range of the homography parameter space becomes larger. To this end, we propose a novel Homography Decomposition Networks~(HDN) approach that drastically reduces and stabilizes the condition number by decomposing the homography transformation into two groups. Specifically, a similarity transformation estimator is designed to predict the first group robustly by a deep convolution equivariant network. By taking advantage of the scale and rotation estimation with high confidence, a residual transformation is estimated by a simple regression model. Furthermore, the proposed end-to-end network is trained in a semi-supervised fashion. Extensive experiments show that our proposed approach outperforms the state-of-the-art planar tracking methods at a large margin on the challenging POT, UCSB and POIC datasets. Codes and models are available at https://github.com/zhanxinrui/HDN.

DeTarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration

Point cloud registration is a fundamental step for many tasks. In this paper, we propose a neural network named DetarNet to decouple the translation t and rotation R, so as to overcome the performance degradation due to their mutual interference in point cloud registration. First, a Siamese Network based Progressive and Coherent Feature Drift (PCFD) module is proposed to align the source and target points in high-dimensional feature space, and accurately recover translation from the alignment process. Then we propose a Consensus Encoding Unit (CEU) to construct more distinguishable features for a set of putative correspondences. After that, a Spatial and Channel Attention (SCA) block is adopted to build a classification network for finding good correspondences. Finally, the rotation is obtained by Singular Value Decomposition (SVD). In this way, the proposed network decouples the estimation of translation and rotation, resulting in better performance for both of them. Experimental results demonstrate that the proposed DetarNet improves registration performance on both indoor and outdoor scenes. Our code will be available in https://github.com/ZhiChen902/DetarNet.

RAMC: A Rotation Adaptive Tracker with Motion Constraint for Satellite Video Single-Object Tracking

Single-object tracking (SOT) in satellite videos (SVs) is a promising and challenging task in the remote sensing community. In terms of the object itself and the tracking algorithm, the rotation of small-sized objects and tracking drift are common problems due to the nadir view coupled with a complex background. This article proposes a novel rotation adaptive tracker with motion constraint (RAMC) to explore how the hybridization of angle and motion information can be utilized to boost SV object tracking from two branches: rotation and translation. We decouple the rotation and translation motion patterns. The rotation phenomenon is decomposed into the translation solution to achieve adaptive rotation estimation in the rotation branch. In the translation branch, the appearance and motion information are synergized to enhance the object representations and address the tracking drift issue. Moreover, an internal shrinkage (IS) strategy is proposed to optimize the evaluation process of trackers. Extensive experiments on space-born SV datasets captured from the Jilin-1 satellite constellation and International Space Station (ISS) are conducted. The results demonstrate the superiority of the proposed method over other algorithms. With an area under the curve (AUC) of 0.785 and 0.946 in the success and precision plots, respectively, the proposed RAMC achieves optimal performance while running at real-time speed.