Camera Tracking System Research Articles

A Study on Moving Direction Detection of Construction Machine and Camera Control for Automatic Tracking Camera System by Image Processing

A Study on Moving Direction Detection of Construction Machine and Camera Control for Automatic Tracking Camera System by Image Processing

Physical performance analysis of elite soccer players during the extra-time periods of the 2016 UEFA Euro Championship

Background: Despite the importance of extra-time in determining success in the knockout stages of soccer tournaments, there remains scant information on the physical demands of extra time on elite players.
 Methods: This study investigated the physical performance profiles of all soccer players (N=59) who completed four matches that went to extra time at the 2016 UEFA Euro Championship. Players were categorised as follows: central defenders (CDs), wide defenders (WDs), central midfielders (CMs), wide midfielders (WMs), and attackers (ATs). Match activities were captured using a validated camera tracking system (InStat®).
 Results: The findings showed that total distances covered by players during matches consistently decreased by 13% from the first half of the game (112.79±10.17 m) to extra time (103.17±6.39 m). The reduction of the total distance covered, especially in high-intensity running (i.e., high-speed running and sprinting), was more apparent in ATs than players in other positions.
 Conclusion: Intervention strategies needed to sustain soccer players’ physical performance during extra-time periods and of post-match recovery modalities warrant further investigation.

Physical performance analysis of elite soccer players during the extra-time periods of the 2016 UEFA Euro Championship

Background: Despite the importance of extra-time in determining success in the knockout stages of soccer tournaments, there remains scant information on the physical demands of extra time on elite players.
 Methods: This study investigated the physical performance profiles of all soccer players (N=59) who completed four matches that went to extra time at the 2016 UEFA Euro Championship. Players were categorised as follows: central defenders (CDs), wide defenders (WDs), central midfielders (CMs), wide midfielders (WMs), and attackers (ATs). Match activities were captured using a validated camera tracking system (InStat®).
 Results: The findings showed that total distances covered by players during matches consistently decreased by 13% from the first half of the game (112.79±10.17 m) to extra time (103.17±6.39 m). The reduction of the total distance covered, especially in high-intensity running (i.e., high-speed running and sprinting), was more apparent in ATs than players in other positions.
 Conclusion: Intervention strategies needed to sustain soccer players’ physical performance during extra-time periods and of post-match recovery modalities warrant further investigation.

Real-time depth camera tracking with geometrically stable weight algorithm

We present an approach for real-time camera tracking with depth stream. Existing methods are prone to drift in sceneries without sufficient geometric information. First, we propose a new weight method for an iterative closest point algorithm commonly used in real-time dense mapping and tracking systems. By detecting uncertainty in pose and increasing weight of points that constrain unstable transformations, our system achieves accurate and robust trajectory estimation results. Our pipeline can be fully parallelized with GPU and incorporated into the current real-time depth camera tracking system seamlessly. Second, we compare the state-of-the-art weight algorithms and propose a weight degradation algorithm according to the measurement characteristics of a consumer depth camera. Third, we use Nvidia Kepler Shuffle instructions during warp and block reduction to improve the efficiency of our system. Results on the public TUM RGB-D database benchmark demonstrate that our camera tracking system achieves state-of-the-art results both in accuracy and efficiency.

Neuro-Analogical Gate Tuning of Trajectory Data Fusion for a Mecanum-Wheeled Special Needs Chair

Trajectory tracking of mobile wheeled chairs using internal shaft encoder and inertia measurement unit(IMU), exhibits several complications and accumulated errors in the tracking process due to wheel slippage, offset drift and integration approximations. These errors can be realized when comparing localization results from such sensors with a camera tracking system. In long trajectory tracking, such errors can accumulate and result in significant deviations which make data from these sensors unreliable for tracking. Meanwhile the utilization of an external camera tracking system is not always a feasible solution depending on the implementation environment. This paper presents a novel sensor fusion method that combines the measurements of internal sensors to accurately predict the location of the wheeled chair in an environment. The method introduces a new analogical OR gate structured with tuned parameters using multi-layer feedforward neural network denoted as “Neuro-Analogical Gate” (NAG). The resulting system minimize any deviation error caused by the sensors, thus accurately tracking the wheeled chair location without the requirement of an external camera tracking system. The fusion methodology has been tested with a prototype Mecanum wheel-based chair, and significant improvement over tracking response, error and performance has been observed.

Performance analysis of male handball goalkeepers at the World Handball championship 2015.

Goalkeepers have a very important role in handball. In coaching communities it is well recognized that goalkeepers’ performances can predict team ranking in major tournaments. Despite this, few studies have been conducted on elite goalkeepers participating in World Championships. Therefore, the purpose of this study was to analyse goalkeepers’ save performance during the 88 matches of the 2015 men’s World Championships tournament. Goalkeepers from 24 national teams were analysed using a tracking camera system and bespoke software (Prozone Handball V.1.2, Prozone, Leeds, UK). The purpose of this study was to examine time-motion performance parameters and to evaluate the save rates for each goalkeeper. The mean total distance covered in a game by the goalkeepers was 1634±999 m. Goalkeepers spent most of the time walking or standing. The total amount of shots to the goal was 6893, with a mean save percentage of 30% (2088 saves). A significant relationship was identified between the goalkeepers’ save statistics and the final team rankings. The save rate is important for teams to achieve a higher ranking, and therefore the selection and training of goalkeepers requires more than just assessing physical abilities. The throwing distribution and success/save rate during the Qatar 2015 Men Handball World Championships suggest strong and weak parts of the goal area, and coaches can use this information to adjust their training approaches for both goalkeepers and shooters.

複数の画像処理による重機の自動追従カメラシステムの構築と評価

複数の画像処理による重機の自動追従カメラシステムの構築と評価

Activity Profiles and Positional Differences of Handball Players During the World Championships in Qatar 2015.

Handball is an Olympic sport played indoors by 6 court players and 1 goalkeeper with rolling substitutions. Limited data exist on elite players competing in a world championship, and virtually no information exists on the evolution of time-motion performance over the course of a long tournament. To analyze time-motion characteristics of elite male handball players of the last world championships, played in Qatar in 2015. 384 handball players from 24 national teams. The athletes were analyzed during 88 matches using a tracking camera system and bespoke software (Prozone Handball v. 1.2, Prozone, Leeds, UK). The average time on court (N = 2505) during the world championships for all players was 36:48 ± 20:27 min. Goalkeepers and left and right wings were on court most of the playing time (GK 43.00 ± 25:59 min; LW 42:02 ± 21:07 min; RW 43:44 ± 21:37 min). The total distance covered during each game (2607.5 ± 1438.4 m) consisted mostly of walking and jogging. The cumulative distance covered during the tournament was 16,313 ± 9423.3 m. Players performed 857.2 ± 445.7 activity changes with a recovery time of 124.3 ± 143 s. The average running pace was 78.2 ± 10.8 m/min. There was no significant difference between high-ranked and lower-ranked teams in terms of distance covered in different locomotion categories. Specific physical conditioning is necessary to maximize performance of handball players and minimize the occurrence of fatigue when performing in long tournaments.

IACTS: A Novel Indoor Active Camera Tracking System

An active camera tracking system (ACTS) is comprised of a camera that can rotate automatically toward an object of interest so the object remains within the camera’s field of view. To rotate the camera toward an object, the camera needs to detect the object’s location. Detecting an object’s location can be achieved using image processing techniques. However, conventional image processing techniques require expensive calculations in addition to expensive hardware, which in turn limits the video frame processing speed. In this paper, we propose an effective ACTS to monitor and track objects automatically with high accuracy. The proposed approach automatically initializes the object to be tracked using an absolute difference motion detection technique. To track the object correctly, the minimum output sum of squared error (MOSSE) adaptive correlation tracker is applied to provide an accurate and fast visual tracking. We also implemented an accurate scale estimation for the visual tracking technique that detects the scale changes of the object. Additionally, the proposed ACTS uses a closed loop controller to control the pan-tilt speed of the system. By combining these techniques, the proposed ACTS can provide accurate tracking with smooth rotation.

Particle Filter -based Multitarget Multi camera Tracking System utilizing Random Finite Sets and Distributed Estimation Process

Particle Filter -based Multitarget Multi camera Tracking System utilizing Random Finite Sets and Distributed Estimation Process

GbLN-PSO and Model-Based Particle Filter Approach for Tracking Human Movements in Large View Cases

Camera tracking systems have become a common requirement in today’s society. The availability of high-quality and inexpensive video cameras and the increasing need for automated video analysis have generated a great deal of interest in numerous fields.In general, it is not easy to track human behavior in an environment with a large view. This paper aims to address four problems associated with large view in camera tracking system: 1) multiple targets in nonlinear motion; 2) relative size of the targeted object; 3) occlusion; and 4) processing time. This paper presents a new method of tracking human movements using global best local neighborhood oriented particle swarm optimization and model-based particle filter to address the above problems. The proposed method has been tested with an experimental module using several sets of video data provided by the 11th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance and two other video streams of University of British Columbia (UBC) hockey and Malaysian football games. The experiment has shown that the accuracy of tracking performance has increased up to 25% compared with other reported works in the scientific literature.

A LINE-MOD-based markerless tracking approachfor AR applications

Markerless tracking is still a very challenging problem in augmented reality applications, especially the real elements are textureless. In this paper, we proposed a model-based method to tackle the markerless tracking problem. Motivated by LINE-MOD algorithm, one of the state-of-the-art object detection methods, and multiview-based 3D model retrieval approach, we built a camera tracking system utilizing image retrieval. In the off-line training stage, 3D models were used to generate templates automatically. To estimate the camera pose accurately in the online matching stage, LINE-MOD was adapted into a scale-invariant descriptor using depth information obtained from Softkinetic, and an interpolation method combined with other mathematical calculations was used for camera pose refinement. The experimental result shows that the proposed method is fast and robust for markerless tracking in augmented reality environment; the tracking accuracy is much closer to that of ARToolKit markers.

Construct validity of a video-tracking system based on orthogonal cameras approach for objective assessment of laparoscopic skills

This study was aimed to establish the construct validity of a video-tracking system based on orthogonal cameras approach for assessment of laparoscopic psychomotor skills in training environments. The camera-tracking system consists of two webcams placed in orthogonal configuration at a distance of 13.5 cm. The orthogonal cameras employ a color segmentation algorithm to register the 3D motions of the laparoscopic instruments using colored tapes placed on the distal end. For construct validity, 31 participants (4 experts and 27 residents) performed three training tasks in a laparoscopic box trainer with the built-in orthogonal cameras system. Eleven motion-related parameters were used to evaluate their performance. Statistical analysis was performed, and results between two groups were compared using a Mann-Whitney U-test. Construct validity results showed statistical differences in almost all motion-related parameters for assessment of laparoscopic technical skills. Results demonstrated that the orthogonal video-based tracking system was able to differentiate laparoscopic experience between experts and trainees surgeons. The orthogonal cameras system was successfully validated in a laparoscopic box trainer. This video-based tracking system was able to distinguish performance between experts and trainees surgeons, showing its potential as a reliable tool to assess laparoscopic psychomotor skills. The orthogonal cameras allow incorporating the advantages of this video motion-tracking technology with the benefits of the traditional laparoscopic box trainers, creating realistic haptic feedback and allowing the evaluation of psychomotor skills of the surgeons.

自律制御ボート型ロボットの開発と河川流速計測の試み

The present study developed autonomous-mobile floating-robot using one-board microcomputer Arduino which could measure automatically mean velocity in an open-channel flow. Camera tracking system and PID control method could make the robot remain the position against main stream, and then time-averaged streamwise velocity was evaluated reasonably by a duty-ratio of screw propeller motor. Reliable laboratory experiments with electromagnetic velocimetry provided the calibration curve that connects the duty-ratio and mean current velocity. Furthermore, the present floating could be found to move successfully in not only the laboratory flume but also in natural creek.

Development Model for Surface Mount Technology Using CCD and 3D Camera Modeling and Tracking Systems

Development Model for Surface Mount Technology Using CCD and 3D Camera Modeling and Tracking Systems

Imaging and dosimetric errors in 4D PET/CT-guided radiotherapy from patient-specific respiratory patterns: a dynamic motion phantom end-to-end study

Effective positron emission tomography / computed tomography (PET/CT) guidance in radiotherapy of lung cancer requires estimation and mitigation of errors due to respiratory motion. An end-to-end workflow was developed to measure patient-specific motion-induced uncertainties in imaging, treatment planning, and radiation delivery with respiratory motion phantoms and dosimeters. A custom torso phantom with inserts mimicking normal lung tissue and lung lesion was filled with [18F]FDG. The lung lesion insert was driven by six different patient-specific respiratory patterns or kept stationary. PET/CT images were acquired under motionless ground truth, tidal breathing motion-averaged (3D), and respiratory phase-correlated (4D) conditions. Target volumes were estimated by standardized uptake value (SUV) thresholds that accurately defined the ground-truth lesion volume. Non-uniform dose-painting plans using volumetrically modulated arc therapy were optimized for fixed normal lung and spinal cord objectives and variable PET-based target objectives. Resulting plans were delivered to a cylindrical diode array at rest, in motion on a platform driven by the same respiratory patterns (3D), or motion-compensated by a robotic couch with an infrared camera tracking system (4D). Errors were estimated relative to the static ground truth condition for mean target-to-background (T/Bmean) ratios, target volumes, planned equivalent uniform target doses, and 2%-2 mm gamma delivery passing rates. Relative to motionless ground truth conditions, PET/CT imaging errors were on the order of 10–20%, treatment planning errors were 5–10%, and treatment delivery errors were 5–30% without motion compensation. Errors from residual motion following compensation methods were reduced to 5–10% in PET/CT imaging, <5% in treatment planning, and <2% in treatment delivery. We have demonstrated that estimation of respiratory motion uncertainty and its propagation from PET/CT imaging to RT planning, and RT delivery under a dose painting paradigm is feasible within an integrated respiratory motion phantom workflow. For a limited set of cases, the magnitude of errors was comparable during PET/CT imaging and treatment delivery without motion compensation. Errors were moderately mitigated during PET/CT imaging and significantly mitigated during RT delivery with motion compensation. This dynamic motion phantom end-to-end workflow provides a method for quality assurance of 4D PET/CT-guided radiotherapy, including evaluation of respiratory motion compensation methods during imaging and treatment delivery.

Extended Flocking Algorithm for Self‐parameter Tuning

SUMMARYFlocking algorithms for a multiagent system are distributed algorithms that only have simple rules for each agent but generate complex formational movement. These algorithms are known as swarm intelligence and are robust and disaster tolerant for most cases. We consider that flocking algorithms that have these characteristics are the way to generate homeostasis in a system. We expect that by making use of this algorithm the system can tune its self‐parameters and thus maintain a high performance. First, to apply a flocking algorithm to a system, we extended the flocking algorithm to form an arbitrary lattice for further flexibility. We then applied the extended flocking algorithm to position tracking camera system as an example.

Evaluation of intra-articular distance narrowing during temporomandibular joint movement in patients with facial asymmetry using 3-dimensional computed tomography image and tracking camera system

IntroductionFunctional overloading can lead to disc displacement in the temporomandibular joint (TMJ), and a high incidence of disc displacement has been reported in patients with facial asymmetry. The aim of this study was to assess the dynamic condylar movement in patients (n = 26) with facial asymmetry using a simulation system with 3-dimensional computed tomographic images and tracking camera system. Material and methodsThe intra-articular distance (IAD) between the condyle and glenoid fossa was recorded during TMJ movement as a parameter for functional overloading and compared between Group I with severe asymmetry and Group II with mild asymmetry. ResultsThe average IAD was shorter in Group I than Group II, especially at the lowest point (P < 0.05). The ratio of IAD narrowing in Group I was significantly larger than in Group II (P < 0.05). The mean IAD were slightly smaller on the deviated side (3.41 mm) than on the nondeviated side (3.55 mm) in Group I, even though there was no statistical significance. The maximum displacement in Group I was longer than in Group II and had no significant difference between deviated side and nondeviated side. ConclusionWe suggested that the reduced IAD resulting from TMJ overloading can lead to internal derangement in severe facial asymmetry.

A single camera tracking system for 3D position, grasper angle, and rolling angle of laparoscopic instruments

Advances in computer vision technology and virtual reality technology have been achieved through improvements in camera performance and computability. Cost-effective simulation systems for laparoscopic surgery are proposed by combining such technologies. In this study, we propose a novel 3D instrument tracking technique using a single camera to obtain the 3D positions, roll angle, and grasper angle of a laparoscopic instrument. The 3D tracking of the instrument requires that all of the markers are collinear and that the actual distances between markers are known The results of our study show that the minimum uncertainty in the position was 0.237 mm and the maximum uncertainty in the position was 1.476 mm.

A Video Camera Tracking System for use with Robotic Radiosurgery on an Ocular Tumor

Effective management for Ocular tumor, such as Choroidal Melanoma, usually adopts localized radiation treatment, most commonly performed via radioactive plaque brachytherapy. In recent years, the success of using robotic radiosurgery to treat small-sized tumor inspired our motivation to develop a non-invasive stereotactic radiosurgery on ocular tumor by the robotic radiosurgery system. However, due to the unpredictable eye movement during treatment, the existing 6D skull tracking system cannot account for random ocular tumor positions and therefore compromises treatment delivery precision.