Orientation Estimation Algorithm Research Articles

AERIAL OBJECT RECOGNITION ALGORITHM BASED ON CONTOUR DESCRIPTOR

Abstract. This paper describes the image recognition algorithm for on-board and stationary vision system. Suggested algorithm is intended to recognize the aerial object of a specific kind using the set of the reference objects defined by 3D models. The proposed algorithm based on the outer contour descriptor building. The algorithm consists of two stages: learning and recognition. Learning stage is devoted to the exploring of reference objects. Using 3D models we can gather set of training images by rendering the 3D model from viewpoints evenly distributed on a sphere. Sphere points distribution is made by the geosphere principle. Gathered training image set is used for calculating descriptors, which will be used in the recognition stage of the algorithm. The recognition stage is focusing on estimating the similarity of the captured object and the reference objects by matching an observed image descriptor and the reference object descriptors. The experimental research was performed using a set of the models of the aircraft of the different types. The proposed orientation estimation algorithm showed good accuracy in all case studies.

Erratum to: Development of a low-cost wearable sensing glove with multiple inertial sensors and a light and fast orientation estimation algorithm

Correct capturing the movement of hands and fingers provides natural ways of interacting with computers. However, developing a glove-based device for such interaction has been very expensive and there were technical problems such as a complicate motion measurement algorithm in limited embedded resources and a complicate calibration process. We present a practical development of a low-cost and lightweight wearable sensing glove using only one CPU and seventeen IMUs. It transmits the captured movement data of seventeen joints of hand and wrist to a host machine via Bluetooth communication. We also propose a light and fast orientation estimation algorithm for the glove system, which should compute orientations and calibrations for seventeen inertia measurement units (IMUs) in real time. The seventeen individual IMUs are composed of an accelerometer, a gyroscope and a magnetometer based on micro electro-mechanical system technology. The magnetometer has sensor bias and scale factor errors, which vary with temperatures and places. Moreover, as the wearable sensing glove has a limited battery life and a cheap embedded processor, it can only utilize limited memory and computation power. Therefore, the algorithm should compute the attitude of the IMUs and calibrate the magnetic sensor in real time with very low computational load, by maintaining only a valid subset of data points. Our experimental results indicate that the algorithm achieves sufficient levels of real-time computation and accuracy.

Inertial Motion Capture Costume Design Study.

The paper describes a scalable, wearable multi-sensor system for motion capture based on inertial measurement units (IMUs). Such a unit is composed of accelerometer, gyroscope and magnetometer. The final quality of an obtained motion arises from all the individual parts of the described system. The proposed system is a sequence of the following stages: sensor data acquisition, sensor orientation estimation, system calibration, pose estimation and data visualisation. The construction of the system’s architecture with the dataflow programming paradigm makes it easy to add, remove and replace the data processing steps. The modular architecture of the system allows an effortless introduction of a new sensor orientation estimation algorithms. The original contribution of the paper is the design study of the individual components used in the motion capture system. The two key steps of the system design are explored in this paper: the evaluation of sensors and algorithms for the orientation estimation. The three chosen algorithms have been implemented and investigated as part of the experiment. Due to the fact that the selection of the sensor has a significant impact on the final result, the sensor evaluation process is also explained and tested. The experimental results confirmed that the choice of sensor and orientation estimation algorithm affect the quality of the final results.

Sparse coding based orientation estimation for latent fingerprints

Fingerprint orientations are often used to describe the ridge flow patterns, providing useful features for further fingerprint processing and recognition. Although significant advances have been achieved for orientation estimation, it is still challenging to reliably estimate the orientations for latent fingerprints, which are usually of poor quality with unclear ridge structure and various overlapping patterns. Motivated by the recent success of sparse coding in image denoising and reconstruction, this paper proposes an orientation estimation algorithm based on dictionary learning and sparse coding for latent fingerprints. First, a texture image is obtained by decomposition of latent image with a total variation model. The structured noise is greatly reduced from the texture image. Second, we propose a multi-scale sparse coding method for iterative estimation of local ridge orientations on the texture image. Multi-scale dictionaries are learned from the orientation fields of good quality fingerprints to capture the prior knowledge of various orientation patterns, and sparse coding is iteratively applied with the increase of patch sizes to correct the corrupted orientations of latent fingerprint. The proposed algorithm can work well to reduce the effect of various noise and restore the corrupted orientations while maintain the details of singular region. Experimental results and comparisons on NIST SD27 latent fingerprint database are presented to show the effectiveness of the proposed algorithm.

An improved fingerprint orientation field extraction method based on quality grading scheme

Orientation pattern is an important feature for characterizing fingerprint and plays a very important role in the automatic fingerprint identification system (AFIS). Conventional gradient based methods are popular but very sensitive to noise. In this paper, we present an improved fingerprint orientation field (FOF) extraction method based on quality grading scheme. In order to effectively remove the noise, the point orientations are fitted by using 2D discrete orthogonal polynomial. The role of the gradient modulus is taken into full account, and the weights of the point orientations are obtained by computing the similarity of the fitted point orientations. The block qualities are assessed by the coherence of point orientations and the block orientations are estimated based on quality grading scheme. In the proposed method, it does not need any prior knowledge of singular points. To validate the performance, the proposed method has been applied to fingerprint singularity detection and fingerprint recognition. We compared the proposed method with other state-of-the-art fingerprint orientation estimation algorithms. Our statistical experiments show that the proposed method can significantly improve in both singular point detection and matching rates, and it is more robust against noise.

物理シミュレーションと透視投影カメラモデルを用いたバラ積みシーン点群生成プログラムの開発

Bin picking is an important task in industrial applications of robots. To achieve the bin picking task, approaches using 3D pointcloud have been taken. For bin picking, it is necessary to recognize picking targets from the scene pointcloud and to estimate the position and the orientation of each target. We developed a program for generating pointcloud of bin scene. This program can be used for development and verification of position and orientation estimation algorithm. By using physical simulation and simulation of stereo vision system using perspective projection model, we have achieved generating 3D pointclouds similar to that obtained by actual 3D sensors.

Orientation Estimation by Means of Extended Kalman Filter, Quaternions, and Charts

An orientation estimation algorithm is presented. This algorithm is based on the Extended Kalman Filter, and uses quaternions as the orientation descriptor. For the filter update, we use measurements from an Inertial Measurement Unit (IMU). The IMU consists in a triaxial angular rate sensor, and an also triaxial accelerometer. Quaternions describing orientations live in the unit sphere of R4. Knowing that this space is a manifold, we can apply some basic concepts regarding these mathematical objects, and an algorithm that reminds the also called “Multiplicative Extended Kalman Filter” arises in a natural way. The algorithm is tested in a simulated experiment, and in a real one.

Indoor Self-Localization and Orientation Estimation of Smartphones Using Acoustic Signals

We propose a new acoustic self-localization and orientation estimation algorithm for smartphones networks composed of commercial off-the-shelf devices equipped with two microphones and a speaker. Each smartphone acts as an acoustic transceiver, which emits and receives acoustic signals. Node locations are found by combining estimates of the range and direction of arrival (DoA) between node pairs using a maximum likelihood (ML) estimator. A tailored optimization algorithm is proposed to simultaneously solve the DoA uncertainty problem that arises from the use of only 2 microphones per node and obtain the azimuthal orientation of each node without requiring an electronic compass.

MSOE: Toward Abrupt Magnetic Change in MARG Orientation Using Multi-State Estimator With Smartphones

The phone attitude angle has been used as an effective tool to many applications, which will be a tough problem when it suffers the change of external environment, such as the magnetic field abrupt variation. In this paper, we present a novel orientation estimation and calibration algorithm MSOE, a multiple states orientation estimation based on the smartphones inertial measurement units consisting of tri-axis accelerometer, gyroscope, and MARG sensors. MSOE is divided into two parts, MSOE calibration (MSOE-C) and MSOE remainder (MSOE-R). MSOE-C skillfully borrows the crowdsourcing data expressed in the form of variational quaternions measured by the phones in the same magnet field. As the non-uniform nature exists inevitably when the crowd-phones are far away from the determinand, the crowdsourcing data may be erroneous. MSOE-R provides us a reminder by warning the control center to prevent measuring by the magnetometer and mainly utilize the gyroscope for estimation during the period with unstable environment. MSOE also incorporates a compensation filter for the tri-axis sensors deviation, especially for the gyroscope drifting. Performance has been evaluated empirically in two different Android platforms with four types of phones based on the available measurement system. Performance is also benchmarked against some current estimation algorithms and MSOE provides two times improvement on the accuracy of attitude angle estimation.

Algorithm and VLSI Architecture of Edge-Directed Image Upscaling for 4k Display System

High-quality and cost-efficient image upscaling design is very important for many real-time video processing applications, especially when the display panel resolution reaches ultrahigh definition. Compared with New Edge-Directed Interpolation (NEDI) based implicit edge directional upscaling, explicit methods require less computational resource and more easily reach real-time performance, especially when the required image definition and upscaling ratio are very high. Nevertheless, the investigation of applications of explicit methods in video processing systems remains largely missing arguably because it is commonly believed that explicit edge-directed interpolation tends to introduce unexpected artifacts because of inaccurate detection and hence its image quality is relatively poor. This paper proposes an explicit edge-directed adaptive interpolation method that leverages more sophisticated edge detection and orientation estimation algorithms to avoid misinterpolation, thereby providing similar or even better image quality than those with implicit methods. Targeting the real-time 4K video display system, the proposed edge-directed image upscaling algorithm is further implemented with an efficient very-large-scale integration (VLSI) architecture. The experimental results demonstrate that the proposed interpolation algorithm outperforms previous explicit and implicit edge-directed methods in both objective and subjective tests. The presented VLSI implementation further demonstrates that the maximum output video sequence of the proposed interpolation method can reach 4k × 2k@60 Hz with a reasonable hardware cost.

Development of a low-cost wearable sensing glove with multiple inertial sensors and a light and fast orientation estimation algorithm

Development of a low-cost wearable sensing glove with multiple inertial sensors and a light and fast orientation estimation algorithm

ROBUST VISION-BASED POSE ESTIMATION ALGORITHM FOR AN UAV WITH KNOWN GRAVITY VECTOR

Accurate estimation of camera external orientation with respect to a known object is one of the central problems in photogrammetry and computer vision. In recent years this problem is gaining an increasing attention in the field of UAV autonomous flight. Such application requires a real-time performance and robustness of the external orientation estimation algorithm. The accuracy of the solution is strongly dependent on the number of reference points visible on the given image. The problem only has an analytical solution if 3 or more reference points are visible. However, in limited visibility conditions it is often needed to perform external orientation with only 2 visible reference points. In such case the solution could be found if the gravity vector direction in the camera coordinate system is known. A number of algorithms for external orientation estimation for the case of 2 known reference points and a gravity vector were developed to date. Most of these algorithms provide analytical solution in the form of polynomial equation that is subject to large errors in the case of complex reference points configurations. This paper is focused on the development of a new computationally effective and robust algorithm for external orientation based on positions of 2 known reference points and a gravity vector. The algorithm implementation for guidance of a Parrot AR.Drone 2.0 micro-UAV is discussed. The experimental evaluation of the algorithm proved its computational efficiency and robustness against errors in reference points positions and complex configurations.

ROBUST VISION-BASED POSE ESTIMATION ALGORITHM FOR AN UAV WITH KNOWN GRAVITY VECTOR

Abstract. Accurate estimation of camera external orientation with respect to a known object is one of the central problems in photogrammetry and computer vision. In recent years this problem is gaining an increasing attention in the field of UAV autonomous flight. Such application requires a real-time performance and robustness of the external orientation estimation algorithm. The accuracy of the solution is strongly dependent on the number of reference points visible on the given image. The problem only has an analytical solution if 3 or more reference points are visible. However, in limited visibility conditions it is often needed to perform external orientation with only 2 visible reference points. In such case the solution could be found if the gravity vector direction in the camera coordinate system is known. A number of algorithms for external orientation estimation for the case of 2 known reference points and a gravity vector were developed to date. Most of these algorithms provide analytical solution in the form of polynomial equation that is subject to large errors in the case of complex reference points configurations. This paper is focused on the development of a new computationally effective and robust algorithm for external orientation based on positions of 2 known reference points and a gravity vector. The algorithm implementation for guidance of a Parrot AR.Drone 2.0 micro-UAV is discussed. The experimental evaluation of the algorithm proved its computational efficiency and robustness against errors in reference points positions and complex configurations.

An algorithm for automatic detection and orientation estimation of planar structures in LiDAR-scanned outcrops

The spatial orientation of linear and planar structures in geological fieldwork is still obtained using simple hand-held instruments such as a compass and clinometer. Despite their ease of use, the amount of data obtained in this way is normally smaller than would be considered as representative of the area available for sampling. LiDAR-based remote sensors are capable of sampling large areas and providing huge sets of digitized spatial points. However, the visual identification of planes in sets of points on geological outcrops is a difficult and time-consuming task. An automatic method for detecting and estimating the orientation of planar structures has been developed to reduce analysis and processing times, and to fit the best plane for each surface represented by a set of points and thus to increase the sampled area. The algorithm detects clusters of points that are part of the same plane based on the principal component analysis (PCA) technique. When applied to real cases, it has shown high precision in both the detection and orientation of fractures planes.

Fourier-based integration of quasi-periodic gait accelerations for drift-free displacement estimation using inertial sensors.

BackgroundIn biomechanical studies Optical Motion Capture Systems (OMCS) are considered the gold standard for determining the orientation and the position (pose) of an object in a global reference frame. However, the use of OMCS can be difficult, which has prompted research on alternative sensing technologies, such as body-worn inertial sensors.MethodsWe developed a drift-free method to estimate the three-dimensional (3D) displacement of a body part during cyclical motions using body-worn inertial sensors. We performed the Fourier analysis of the stride-by-stride estimates of the linear acceleration, which were obtained by transposing the specific forces measured by the tri-axial accelerometer into the global frame using a quaternion-based orientation estimation algorithm and detecting when each stride began using a gait-segmentation algorithm. The time integration was performed analytically using the Fourier series coefficients; the inverse Fourier series was then taken for reconstructing the displacement over each single stride. The displacement traces were concatenated and spline-interpolated to obtain the entire trace.ResultsThe method was applied to estimate the motion of the lower trunk of healthy subjects that walked on a treadmill and it was validated using OMCS reference 3D displacement data; different approaches were tested for transposing the measured specific force into the global frame, segmenting the gait and performing time integration (numerically and analytically). The width of the limits of agreements were computed between each tested method and the OMCS reference method for each anatomical direction: Medio-Lateral (ML), VerTical (VT) and Antero-Posterior (AP); using the proposed method, it was observed that the vertical component of displacement (VT) was within ±4 mm (±1.96 standard deviation) of OMCS data and each component of horizontal displacement (ML and AP) was within ±9 mm of OMCS data.ConclusionsFourier harmonic analysis was applied to model stride-by-stride linear accelerations during walking and to perform their analytical integration. Our results showed that analytical integration based on Fourier series coefficients was a useful approach to accurately estimate 3D displacement from noisy acceleration data.

How Angular Velocity Features and Different Gyroscope Noise Types Interact and Determine Orientation Estimation Accuracy.

In human movement analysis, 3D body segment orientation can be obtained through the numerical integration of gyroscope signals. These signals, however, are affected by errors that, for the case of micro-electro-mechanical systems, are mainly due to: constant bias, scale factor, white noise, and bias instability. The aim of this study is to assess how the orientation estimation accuracy is affected by each of these disturbances, and whether it is influenced by the angular velocity magnitude and 3D distribution across the gyroscope axes. Reference angular velocity signals, either constant or representative of human walking, were corrupted with each of the four noise types within a simulation framework. The magnitude of the angular velocity affected the error in the orientation estimation due to each noise type, except for the white noise. Additionally, the error caused by the constant bias was also influenced by the angular velocity 3D distribution. As the orientation error depends not only on the noise itself but also on the signal it is applied to, different sensor placements could enhance or mitigate the error due to each disturbance, and special attention must be paid in providing and interpreting measures of accuracy for orientation estimation algorithms.

Using frequency analysis to improve the precision of human body posture algorithms based on Kalman filters

With the advent of miniaturized inertial sensors many systems have been developed within the last decade to study and analyze human motion and posture, specially in the medical field. Data measured by the sensors are usually processed by algorithms based on Kalman Filters in order to estimate the orientation of the body parts under study. These filters traditionally include fixed parameters, such as the process and observation noise variances, whose value has large influence in the overall performance. It has been demonstrated that the optimal value of these parameters differs considerably for different motion intensities. Therefore, in this work, we show that, by applying frequency analysis to determine motion intensity, and varying the formerly fixed parameters accordingly, the overall precision of orientation estimation algorithms can be improved, therefore providing physicians with reliable objective data they can use in their daily practice.

Estimating Orientation of Flying Fruit Flies.

The recently growing interest in studying flight behaviours of fruit flies, Drosophila melanogaster, has highlighted the need for developing tools that acquire quantitative motion data. Despite recent advance of video tracking systems, acquiring a flying fly’s orientation remains a challenge for these tools. In this paper, we present a novel method for estimating individual flying fly’s orientation using image cues. Thanks to the line reconstruction algorithm in computer vision field, this work can thereby focus on the practical detail of implementation and evaluation of the orientation estimation algorithm. The orientation estimation algorithm can be incorporated into tracking algorithms. We rigorously evaluated the effectiveness and accuracy of the proposed algorithm by running experiments both on simulation data and on real-world data. This work complements methods for studying the fruit fly’s flight behaviours in a three-dimensional environment.

In-plane face orientation estimation in still images

This paper addresses a fine in-plane (roll) face orientation estimation for a perspective face analysis algorithm that requires normalized frontal faces. As most of the face analysers (e.g., gender, expression, and recognition) need frontal up-right faces, there is a clear need for the precise roll estimation, as precise face normalization has an important role in classification methods. The in-plane orientation estimation algorithm is constructed on top of regular Viola-Jones frontal face detector. When a face is detected for the first time, it is rotated with respect to the face origin to find the boundaries of the detection. Mean value of these angles is said to be the measurement of the in-plane rotation of the face. Since we only need a face detection algorithm, the proposed method can work effectively on very small sized faces where traditional landmark (eye, mouth) or planar detection based estimations fail. Experiments on controlled and unconstrained large-scale datasets (CMU Rotated, YouTube, Boston University Face Tracking, Caltech, FG-NET Aging, BioID and Manchester Talking-Face) showed that the proposed method is robust to various settings for in-plane face orientation estimation in terms of RMSE and MAE. We achieved less than ±3.5 ∘ mean absolute error for roll estimation which proves that the accuracy of the proposed method is comparable to that of the state-of-the-art tracking based approaches for the roll estimation.

A localized Richardson-Lucy algorithm for fiber orientation estimation in high angular resolution diffusion imaging.

Diffusion tensor imaging is widely used for studying neural fiber trajectories in white matter and for quantifying changes in tissue using diffusion properties at each voxel in the brain. To better model the nature of crossing fibers within complex architectures, rather than using a simplified tensor model that assumes only a single fiber direction at each image voxel, a model mixing multiple diffusion tensors is used to profile diffusion signals from high angular resolution diffusion imaging (HARDI) data. Based on the HARDI signal and a multiple tensors model, spherical deconvolution methods have been developed to overcome the limitations of the diffusion tensor model when resolving crossing fibers. The Richardson-Lucy algorithm is a popular spherical deconvolution method used in previous work. However, it is based on a Gaussian distribution, while HARDI data are always very noisy, and the distribution of HARDI data follows a Rician distribution. This current work aims to present a novel solution to address these issues. By simultaneously considering both the Rician bias and neighbor correlation in HARDI data, the authors propose a localized Richardson-Lucy (LRL) algorithm to estimate fiber orientations for HARDI data. The proposed method can simultaneously reduce noise and correct the Rician bias. Mean angular error (MAE) between the estimated Fiber orientation distribution (FOD) field and the reference FOD field was computed to examine whether the proposed LRL algorithm offered any advantage over the conventional RL algorithm at various levels of noise. Normalized mean squared error (NMSE) was also computed to measure the similarity between the true FOD field and the estimated FOD filed. For MAE comparisons, the proposed LRL approach obtained the best results in most of the cases at different levels of SNR and b-values. For NMSE comparisons, the proposed LRL approach obtained the best results in most of the cases at b-value = 3000 s/mm(2), which is the recommended schema for HARDI data acquisition. In addition, the FOD fields estimated by the proposed LRL approach in regions of fiber crossing regions using real data sets also showed similar fiber structures which agreed with common acknowledge in these regions. The novel spherical deconvolution method for improved accuracy in investigating crossing fibers can simultaneously reduce noise and correct Rician bias. With the noise smoothed and bias corrected, this algorithm is especially suitable for estimation of fiber orientations in HARDI data. Experimental results using both synthetic and real imaging data demonstrated the success and effectiveness of the proposed LRL algorithm.