Predicted Target Position Research Articles

Fuzzy-Logic-Based, Obstacle Information-Aided Multiple-Model Target Tracking

Incorporating obstacle information into maneuvering target-tracking algorithms may lead to a better performance when the target when the target maneuver is caused by avoiding collision with obstacles. In this paper, we propose a fuzzy-logic-based method incorporating new obstacle information into the interacting multiple-model (IMM) algorithm (FOIA-MM). We use convex polygons to describe the obstacles and then extract the distance from and the field angle of these obstacle convex polygons to the predicted target position as obstacle information. This information is fed to two fuzzy logic inference systems; one system outputs the model weights to their probabilities, the other yields the expected sojourn time of the models for the transition probability matrix assignment. Finally, simulation experiments and an Unmanned Aerial Vehicle experiment are carried out to demonstrate the efficiency and effectiveness of the proposed algorithm.

Persistent standoff tracking guidance using constrained particle filter for multiple UAVs

This paper presents a new standoff tracking framework of a moving ground target using UAVs with limited sensing capabilities and motion constraints. To maintain persistent track of the target even in case of target loss for a certain period, this study predicts the target existence area using the particle filter and produces control commands that ensure that all predicted particles can stay within the field-of-view of the UAV sensor at all times. To improve target position prediction and estimation accuracy, the road information is incorporated into the constrained particle filter where the road boundaries are modelled as inequality constraints. Both Lyapunov vector field guidance and nonlinear model predictive control-based methods are applied, and the characteristics of them are compared using numerical simulations.

Bearings-only multi-target tracking using an improved labeled multi-Bernoulli filter

Most classical bearing-only target tracking algorithms model the measurement likelihood by one Gaussian distribution. The effectiveness of one Gaussian distribution model relies heavily on the accuracy of the predicted target position. However, due to the high nonlinearity of the bearing-only measurement, the predicted target position is mostly inaccurate before the target state observability is established. As a consequence, some classical nonlinear filters become not applicable for tracking bearing-only targets, especially when the measurements of multiple targets and clutter are present. The published bearings-only multiple-target tracking algorithms suffer from either the estimation inaccuracy or lack of track trajectories. Motivated by the problems mentioned above, we propose an improved labeled multi-Bernoulli filter for the goal of reducing estimation error under the premise that track trajectories are guaranteed. The proposed method divides the bearing measurement uncertainty into several measurement components that the measurement likelihood can be approximated by a Gaussian mixture. By assigning each track a unique label, the previous scan estimations and current scan measurements are associated and the track trajectories become available. Simulation results show that the proposed method considerably reduces estimation error. Further, various scenario parameters are investigated to validate the effectiveness of the proposed method.

Source-Target Inference Models for Spatial Instruction Understanding

Models that can execute natural language instructions for situated robotic tasks such as assembly and navigation have several useful applications in homes, offices, and remote scenarios.We study the semantics of spatially-referred configuration and arrangement instructions, based on the challenging Bisk-2016 blank-labeled block dataset. This task involves finding a source block and moving it to the target position (mentioned via a reference block and offset), where the blocks have no names or colors and are just referred to via spatial location features.We present novel models for the subtasks of source block classification and target position regression, based on joint-loss language and spatial-world representation learning, as well as CNN-based and dual attention models to compute the alignment between the world blocks and the instruction phrases. For target position prediction, we compare two inference approaches: annealed sampling via policy gradient versus expectation inference via supervised regression. Our models achieve the new state-of-the-art on this task, with an improvement of 47% on source block accuracy and 22% on target position distance.

Evaluation of target coverage and margins adequacy during CyberKnife Lung Optimized Treatment.

Evaluation of target coverage and verification of safety margins, in motion management strategies implemented by Lung Optimized Treatment (LOT) module in CyberKnife system. Three fiducial-less motion management strategies provided by LOT can be selected according to tumor visibility in the X ray images acquired during treatment. In 2-view modality the tumor is visible in both X ray images and full motion tracking is performed. In 1-view modality the tumor is visible in a single X ray image, therefore, motion tracking is combined with an internal target volume (ITV)-based margin expansion. In 0-view modality the lesion is not visible, consequently the treatment relies entirely on an ITV-based approach. Data from 30 patients treated in 2-view modality were selected providing information on the three-dimensional tumor motion in correspondence to each X ray image. Treatments in 1-view and 0-view modalities were simulated by processing log files and planning volumes. Planning target volume (PTV) margins were defined according to the tracking modality: end-exhale clinical target volume (CTV)+3mm in 2-view and ITV+5mm in 0-view. In the 1-view scenario, the ITV encompasses only tumor motion along the non-visible direction. Then, non-uniform ITV to PTV margins were applied: 3mm and 5mm in the visible and non-visible direction, respectively. We defined the coverage of each voxel of the CTV as the percentage of X ray images where such voxel was included in the PTV. In 2-view modality coverage was calculated as the intersection between the CTV centred on the imaged target position and the PTV centred on the predicted target position, as recorded in log files. In 1-view modality, coverage was calculated as the intersection between the CTV centred on the imaged target position and the PTV centred on the projected predictor data. In 0-view modality coverage was calculated as the intersection between the CTV centred on the imaged target position and the non-moving PTV. Similar to dose-volume histogram, CTV coverage-volume histograms (defined as CVH) were derived for each patient and treatment modality. The geometric coverages of the 90% and 95% of CTV volume (C90, C95, respectively) were evaluated. Patient-specific optimal margins (ensuring C95≥95%) were computed retrospectively. The median±interquartile-rage of C90 and C95 for upper lobe lesions was 99.1±0.6% and 99.0±3.1%, whereas they were 98.9±4.2% and 97.8±7.5% for lower and middle lobe tumors. In 2-view, 1-view and 0-view modality, adopted margins ensured C95≥95% in 70%, 85% and 63% of cases and C95≥90% in 90%, 88% and 83% of cases, respectively. In 2-view, 1-view and 0-view a reduction in margins still ensured C95≥95% in 33%, 78% and 59% of cases, respectively. CTV coverage analysis provided an a-posteriori evaluation of the treatment geometric accuracy and allowed a quantitative verification of the adequacy of the PTV margins applied in CyberKnife LOT treatments offering guidance in the selection of CTV margins.

2D recurrent neural networks: a high-performance tool for robust visual tracking in dynamic scenes

This paper proposes a novel method for robust visual tracking of arbitrary objects, based on the combination of image-based prediction and position refinement by weighted correlation. The effectiveness of the proposed approach is demonstrated on a challenging set of dynamic video sequences, extracted from the final of triple jump at the London 2012 Summer Olympics. A comparison is made against five baseline tracking systems. The novel system shows remarkable superior performances with respect to the other methods, in all considered cases characterized by changing background, and a large variety of articulated motions. The novel architecture, from here onward named 2D Recurrent Neural Network (2D-RNN), is derived from the well-known recurrent neural network model and adopts nearest neighborhood connections between the input and context layers in order to store the temporal information content of the video. Starting from the selection of the object of interest in the first frame, neural computation is applied to predict the position of the target in each video frame. Normalized cross-correlation is then applied to refine the predicted target position. 2D-RNN ensures limited complexity, great adaptability and a very fast learning time. At the same time, it shows on the considered dataset fast execution times and very good accuracy, making this approach an excellent candidate for automated analysis of complex video streams.

Effect of tumor amplitude and frequency on 4D modeling of Vero4DRT system.

An important issue in indirect dynamic tumor tracking with the Vero4DRT system is the accuracy of the model predictions of the internal target position based on surrogate infrared (IR) marker measurement. We investigated the predictive uncertainty of 4D modeling using an external IR marker, focusing on the effect of the target and surrogate amplitudes and periods. A programmable respiratory motion table was used to simulate breathing induced organ motion. Sinusoidal motion sequences were produced by a dynamic phantom with different amplitudes and periods. To investigate the 4D modeling error, the following amplitudes (peak-to-peak: 10-40mm) and periods (2-8s) were considered. The 95th percentile 4D modeling error (4D-E95%) between the detected and predicted target position (μ+2SD) was calculated to investigate the 4D modeling error. 4D-E95% was linearly related to the target motion amplitude with a coefficient of determination R2=0.99 and ranged from 0.21 to 0.88mm. The 4D modeling error ranged from 1.49 to 0.14mm and gradually decreased with increasing target motion period. We analyzed the predictive error in 4D modeling and the error due to the amplitude and period of target. 4D modeling error substantially increased with increasing amplitude and decreasing period of the target motion.

Tracking control in x-y plane of an offshore container crane

A tracking controller is proposed for a crane attached to a mobile harbor (MH) equipped with a dual-stage trolley system, to dynamically position a container from the MH to the container ship or vice versa. Wave-induced motions of the MH and container ship occur during loading and unloading operations owing to external disturbances such as waves. However, a challenging task is to move a payload with unwanted swing motions accurately to the loading and unloading positions on a moving target vessel. To solve this problem, a dynamic MH crane model is derived in three-dimensional space, with roll, pitch, and heave motions caused by sea-wave disturbances. The MH crane model is then linearized to design a tracking controller and the parameters of the linearized model are obtained by carrying out the system identification process. A preview tracking control method that includes feedback and feed-forward control with the predicted target position in the x-y plane in the near future is utilized. Through numerical simulations and experiments with a scaled model, the tracking performance of the proposed dynamic positioning control system is considered when sinusoidal roll and pitch motions of the MH are generated to mimic the wavy sea environment.

A clustering-based improved Grey-Markov target tracking algorithm in wireless sensor networks

Target position prediction in wireless sensor networks WSN has long been an important but difficult problem to be addressed. Owing to the dynamic motion of the target, the accuracy of prediction results is still far from what we expect in real applications. In order to solve this problem, this paper presents a clustering-based improved Grey-Markov target tracking CIGMTT for short algorithm to combine Markov process with a segmentation Grey model to adapt to the changes of target motion. The algorithm can greatly improve prediction accuracy by introducing new initial value and background value into the segmentation Grey model. After getting the predicted position, a clustering routing mechanism is used to transmit the tracking information. Our clustering routing mechanism is based on node distance to the predicted target position and node residual energy to dynamically construct the tracking cluster. In this way, sensor nodes can wake up in advance so that we can complete the target tracking with as few nodes as possible and maximise the network lifetime. The performance analysis and simulation results show that the proposed algorithm is energy-efficient and achieves a superior performance in tracking accuracy and tracking probability.

Target Tracking Algorithm Using Angular Point Matching Combined with Compressive Tracking

To solve the problems of tracking errors such as target missing that emerged in compressive tracking (CT) algorithm due to factors such as pose variation, illumination change, and occlusion, a novel tracking algorithm combined angular point matching with compressive tracking (APMCCT) was proposed. A sparse measurement matrix was adopted to extract the Haar-like features. The offset of the predicted target position was integrated into the angular point matching, and the new target position was calculated. Furthermore, the updating mechanism of the template was optimized. Experiments on different video sequences have shown that the proposed APMCCT performs better than CT algorithm in terms of accuracy and robustness and adaptability to pose variation, illumination change, and occlusion.

Small Target Detecting and Tracking Using Mean Shifter Guided Kalman Filter

Because of the importance of small target detection in infrared images, many studies have been carried out in this area. Using a Kalman filter and mean shift algorithm, this study proposes an algorithm to track multiple small moving targets even in cases of target disappearance and appearance in serial infrared images in an environment with many noises. Difference images, which highlight the background images estimated with a background estimation filter from the original images, have a relatively very bright value, which becomes a candidate target area. Multiple target tracking consists of a Kalman filter section (target position prediction) and candidate target classification section (target selection). The system removes error detection from the detection results of candidate targets in still images and associates targets in serial images. The final target detection locations were revised with the mean shift algorithm to have comparatively low tracking location errors and allow for continuous tracking with standard model updating. In the experiment with actual marine infrared serial images, the proposed system was compared with the Kalman filter method and mean shift algorithm. As a result, the proposed system recorded the lowest tracking location errors and ensured stable tracking with no tracking location diffusion.

Predictive uncertainty in infrared marker‐based dynamic tumor tracking with Vero4DRTa)

To quantify the predictive uncertainty in infrared (IR)-marker-based dynamic tumor tracking irradiation (IR Tracking) with Vero4DRT (MHI-TM2000) for lung cancer using logfiles. A total of 110 logfiles for 10 patients with lung cancer who underwent IR Tracking were analyzed. Before beam delivery, external IR markers and implanted gold markers were monitored for 40 s with the IR camera every 16.7 ms and with an orthogonal kV x-ray imaging subsystem every 80 or 160 ms. A predictive model [four-dimensional (4D) model] was then created to correlate the positions of the IR markers (PIR) with the three-dimensional (3D) positions of the tumor indicated by the implanted gold markers (Pdetect). The sequence of these processes was defined as 4D modeling. During beam delivery, the 4D model predicted the future 3D target positions (Ppredict) from the PIR in real-time, and the gimbaled x-ray head then tracked the target continuously. In clinical practice, the authors updated the 4D model at least once during each treatment session to improve its predictive accuracy. This study evaluated the predictive errors in 4D modeling (E4DM) and those resulting from the baseline drift of PIR and Pdetect during a treatment session (EBD). E4DM was defined as the difference between Ppredict and Pdetect in 4D modeling, and EBD was defined as the mean difference between Ppredict calculated from PIR in updated 4D modeling using (a) a 4D model created from training data before the model update and (b) an updated 4D model created from new training data. The mean E4DM was 0.0 mm with the exception of one logfile. Standard deviations of E4DM ranged from 0.1 to 1.0, 0.1 to 1.6, and 0.2 to 1.3 mm in the left-right (LR), anterior-posterior (AP), and superior-inferior (SI) directions, respectively. The median elapsed time before updating the 4D model was 13 (range, 2-33) min, and the median frequency of 4D modeling was twice (range, 2-3 times) per treatment session. EBD ranged from -1.0 to 1.0, -2.1 to 3.3, and -2.0 to 3.5 mm in the LR, AP, and SI directions, respectively. EBD was highly correlated with BDdetect in the LR (R = -0.83) and AP directions (R = -0.88), but not in the SI direction (R = -0.40). Meanwhile, EBD was highly correlated with BDIR in the SI direction (R = -0.67), but not in the LR (R = 0.15) or AP (R = -0.11) direction. If the 4D model was not updated in the presence of intrafractional baseline drift, the predicted target position deviated from the detected target position systematically. Application of IR Tracking substantially reduced the geometric error caused by respiratory motion; however, an intrafractional error due to baseline drift of >3 mm was occasionally observed. To compensate for EBD, the authors recommend checking the target and IR marker positions constantly and updating the 4D model several times during a treatment session.

Secure and robust clustering for quantized target tracking in wireless sensor networks

We consider the problem of secure and robust clustering for quantized target tracking in wireless sensor networks (WSN) where the observed system is assumed to evolve according to a probabilistic state space model. We propose a new method for jointly activating the best group of candidate sensors that participate in data aggregation, detecting the malicious sensors and estimating the target position. Firstly, we select the appropriate group in order to balance the energy dissipation and to provide the required data of the target in the WSN. This selection is also based on the transmission power between a sensor node and a cluster head. Secondly, we detect the malicious sensor nodes based on the information relevance of their measurements. Then, we estimate the target position using quantized variational filtering (QVF) algorithm. The selection of the candidate sensors group is based on multi-criteria function, which is computed by using the predicted target position provided by the QVF algorithm, while the malicious sensor nodes detection is based on Kullback-Leibler distance between the current target position distribution and the predicted sensor observation. The performance of the proposed method is validated by simulation results in target tracking for WSN.

Characterizing multivariate decoding models based on correlated EEG spectral features

ObjectiveMultivariate decoding methods are popular techniques for analysis of neurophysiological data. The present study explored potential interpretative problems with these techniques when predictors are correlated. MethodsData from sensorimotor rhythm-based cursor control experiments was analyzed offline with linear univariate and multivariate models. Features were derived from autoregressive (AR) spectral analysis of varying model order which produced predictors that varied in their degree of correlation (i.e., multicollinearity). ResultsThe use of multivariate regression models resulted in much better prediction of target position as compared to univariate regression models. However, with lower order AR features interpretation of the spectral patterns of the weights was difficult. This is likely to be due to the high degree of multicollinearity present with lower order AR features. ConclusionsCare should be exercised when interpreting the pattern of weights of multivariate models with correlated predictors. Comparison with univariate statistics is advisable. SignificanceWhile multivariate decoding algorithms are very useful for prediction their utility for interpretation may be limited when predictors are correlated.

A Tracking System Exploiting Interaction Between a Detector With Localization Capabilities and the KF

In the present paper, we focus on the design of a Kalman-based algorithm to track a single target in range. The proposed approach exploits spillover of target energy between consecutive matched filter samples; to this end, at the kth scan, a GLRT-based detector is fed by the predicted target position (computed by the tracker using measurements up to the (k-1)th scan) and returns to the tracker an estimate of the current target position (measurement) obtained by taking into account target strength over consecutive samples. We assume that the target echo is known up to a complex deterministic parameter; moreover, we suppose that the target is embedded in white Gaussian noise with unknown power. The performance analysis is conducted in comparison to a more conventional Kalman-based tracker that interpolates consecutive samples to take advantage of the spillover. Remarkably, the proposed estimation scheme can provide accurate estimates of the target position within the cell under test.

Persistent Spatial Information in the Frontal Eye Field during Object-Based Short-Term Memory

Spatial attention is known to gate entry into visual short-term memory, and some evidence suggests that spatial signals may also play a role in binding features or protecting object representations during memory maintenance. To examine the persistence of spatial signals during object short-term memory, the activity of neurons in the frontal eye field (FEF) of macaque monkeys was recorded during an object-based delayed match-to-sample task. In this task, monkeys were trained to remember an object image over a brief delay, regardless of the locations of the sample or target presentation. FEF neurons exhibited visual, delay, and target period activity, including selectivity for sample location and target location. Delay period activity represented the sample location throughout the delay, despite the irrelevance of spatial information for successful task completion. Furthermore, neurons continued to encode sample position in a variant of the task in which the matching stimulus never appeared in their response field, confirming that FEF maintains sample location independent of subsequent behavioral relevance. FEF neurons also exhibited target-position-dependent anticipatory activity immediately before target onset, suggesting that monkeys predicted target position within blocks. These results show that FEF neurons maintain spatial information during short-term memory, even when that information is irrelevant for task performance.

Tracking Algorirthm Based on Location Prediction for Wireless Sensor Network

In many wireless sensor networks tracking technologies,location-based pediction target tracking technology have a natural advantage of reducing the energy consumption of nodes in tracking the process. However, the existing location-based prediction target tracking algorithm is not perfect.So Location-Based Pediction Target Tracking Algorirthm (LBP) was proposed. There are three parts in LBP,target position prediction algorithm based self-simlar,target tracking based on dynamic wakeup cluster(DWC),and three levels recovery mechanism.

The relative importance of retinal error and prediction in saccadic adaptation

When saccades systematically miss their visual target, their amplitude adjusts, causing the position errors to be progressively reduced. Conventionally, this adaptation is viewed as driven by retinal error (the distance between primary saccade endpoint and visual target). Recent work suggests that the oculomotor system is informed about where the eye lands; thus not all "retinal error" is unexpected. The present study compared two error signals that may drive saccade adaptation: retinal error and prediction error (the difference between predicted and actual postsaccadic images). Subjects made saccades to a visual target in two successive sessions. In the first session, the target was extinguished during saccade execution if the amplitude was smaller (or, in other experiments, greater) than the running median, thereby modifying the average retinal error subjects experienced without moving the target during the saccade as in conventional adaptation paradigms. In the second session, targets were extinguished at the start of saccades and turned back on at a position that reproduced the trial-by-trial retinal error recorded in the first session. Despite the retinal error in the first and second sessions having been identical, adaptation was severalfold greater in the second session, when the predicted target position had been changed. These results argue that the eye knows where it lands and where it expects the target to be, and that deviations from this prediction drive saccade adaptation more strongly than retinal error alone.

Predictive saccade in the absence of smooth pursuit: interception of moving targets in the archer fish

Interception of fast-moving targets is a demanding task many animals solve. To handle it successfully, mammals employ both saccadic and smooth pursuit eye movements in order to confine the target to their area centralis. But how can non-mammalian vertebrates, which lack smooth pursuit, intercept moving targets? We studied this question by exploring eye movement strategies employed by archer fish, an animal that possesses an area centralis, lacks smooth pursuit eye movements, but can intercept moving targets by shooting jets of water at them. We tracked the gaze direction of fish during interception of moving targets and found that they employ saccadic eye movements based on prediction of target position when it is hit. The fish fixates on the target's initial position for ∼0.2 s from the onset of its motion, a time period used to predict whether a shot can be made before the projection of the target exits the area centralis. If the prediction indicates otherwise, the fish performs a saccade that overshoots the center of gaze beyond the present target projection on the retina, such that after the saccade the moving target remains inside the area centralis long enough to prepare and perform a shot. These results add to the growing body of knowledge on biological target tracking and may shed light on the mechanism underlying this behavior in other animals with no neural system for the generation of smooth pursuit eye movements.

2P1-P07 対人追従ロボットのための曲がり角における追跡対象の見失い時予測移動(デジタルヒューマン)

2P1-P07 対人追従ロボットのための曲がり角における追跡対象の見失い時予測移動(デジタルヒューマン)