Ricardo Machado Leite de Barros

A flexible software for tracking of markers used in human motion analysis

In this work, we present a software for the tracking of markers used in human motion analysis. This software is based mainly on image sequences captured by video cameras and on image processing and computer vision tools. Unlike the optoelectronic systems, which record only the coordinates of the markers, a video-based system offers more visual information and flexibility which can be exploited in different applications. However, it needs a more complex tracking procedure concerned with the extraction and identification of the used markers. The tracking module presented here is divided into the following three procedures: segmentation, matching and prediction. The segmentation consists in extracting the objects of interest (markers). The matching is used to find the correspondence between the extracted objects in two consecutive frames. The prediction is important to limit the region of processing, thus reducing the execution time. Some results of the automatic tracking are presented together with their application in human motions analysis.

Tracking soccer players aiming their kinematical motion analysis

In this work, we consider the problem of tracking players, during a soccer game, through the use of multiple cameras. The main goal here consists in finding the position of the players on the pitch at each instance of time. The tracking is performed through a graph representation in which the nodes correspond to the blobs obtained by image segmentation and the edges, weighted using the blobs information and trajectory in the image sequence, represent the distance between nodes. We present a new way of trating occlusions by splitting segmented blobs based on morphological operators and a backward and forward graph representation which allows an increasing in the number of frames automatically tracked. Unlike other works in which the analysis of short video sequences is presented, this paper illustrates the tracking results for all the players during a whole game.

Gait Training Combining Partial Body-Weight Support, a Treadmill, and Functional Electrical Stimulation: Effects on Poststroke Gait

Background and Purpose: Treadmill training with harness support is a promising, task-oriented approach to restoring locomotor function in people with poststroke hemiparesis. Although the combined use of functional electrical stimulation (FES) and treadmill training with body-weight support (BWS) has been studied before, this combined intervention was compared with the Bobath approach as opposed to BWS alone. The purpose of this study was to evaluate the effects of the combined use of FES and treadmill training with BWS on walking functions and voluntary limb control in people with chronic hemiparesis. Subjects: Eight people who were ambulatory after chronic stroke were evaluated. Methods: An A1-B-A2 single-case study design was applied. Phases A1 and A2 included 3 weeks of gait training on a treadmill with BWS, and phase B included 3 weeks of treadmill training plus FES applied to the peroneal nerve. The Stroke Rehabilitation Assessment of Movement was used to assess motor recovery, and a videography analysis was used to assess gait parameters. Results: An improvement (from 54.9% to 71.0%) in motor function was found during phase B. The spatial and temporal variables cycle duration, stance duration, and cadence as well as cycle length symmetry showed improvements when phase B was compared with phases A1 and A2. Discussion and Conclusions: The combined use of FES and treadmill training with BWS led to an improvement in motor recovery and seemed to improve the gait pattern of subjects with hemiparesis, indicating the utility of this combination method during gait rehabilitation. In addition, this single-case series showed that this alternative method of gait training—treadmill training with BWS and FES—may decrease the number of people required to carry out the training.

Tracking soccer players using the graph representation

In this work, we consider the problem of tracking soccer players during a game by using multiple cameras. The main goal consists in finding the position of the players on the pitch at each instance of time. The occlusion is treated by splitting segmented blobs and the tracking is performed using a graph representation, where nodes correspond to the blobs obtained by image segmentation and edges represent the distance between the blobs.

Background recovering in outdoor image sequences: An example of soccer players segmentation

In this work, we consider the problem of background pixels information recovering which can be used, for example, in applications concerning segmentation and tracking of components in video images. Shortly, to recover the background of image sequences representing outdoor scenes, we consider a non-parametric morphological leveling operation, which takes into account the specific problem of lighting changes and the fact that we can have both slow and fast motion in the scene. We illustrate the segmentation of players based on the difference between image sequences and the corresponding recovered background representation. We also discuss the reduction of shadows in digital video of soccer games and show the good results of the whole background recovering and segmentation process.

Comparison of different camera calibration approaches for underwater applications.

The purpose of this study was to compare three camera calibration approaches applied to underwater applications: (1) static control points with nonlinear DLT; (2) moving wand with nonlinear camera model and bundle adjustment; (3) moving plate with nonlinear camera model. The DVideo kinematic analysis system was used for underwater data acquisition. The system consisted of two gen-locked Basler cameras working at 100 Hz, with wide angle lenses that were enclosed in housings. The accuracy of the methods was compared in a dynamic rigid bar test (acquisition volume-4.5×1×1.5 m(3)). The mean absolute errors were 6.19 mm for the nonlinear DLT, 1.16 mm for the wand calibration, 1.20 mm for the 2D plate calibration using 8 control points and 0.73 mm for the 2D plane calibration using 16 control points. The results of the wand and 2D plate camera calibration methods were less associated to the rigid body position in the working volume and provided better accuracy than the nonlinear DLT. Wand and 2D plate camera calibration methods presented similar and highly accurate results, being alternatives for underwater 3D motion analysis.

A spectral analysis of team dynamics and tactics in Brazilian football

Abstract The purposes of this study were to characterise the total space covered and the distances between players within teams over ten Brazilian First Division Championship matches. Filmed recordings, combined with a tracking system, were used to obtain the trajectories of the players (n = 277), before and after half-time. The team surface area (the area of the convex hull formed by the positions of the players) and spread (the Frobenius norm of the distance-between-player matrix) were calculated as functions of time. A Fast Fourier Transform (FFT) was applied to each time series. The median frequency was then calculated. The results of the surface area time series median frequencies for the first half (0.63 ± 0.10 cycles · min−1) were significantly greater (P < 0.01) than the second-half values (0.47 ± 0.14 cycles · min−1). Similarly, the spread variable median frequencies for the first half (0.60 ± 0.14 cycles · min−1) were significantly greater (P < 0.01) than the second-half values (0.46 ± 0.16 cycles · min−1). The median frequencies allowed the characterisation of the time series oscillations that represent the speed at which players distribute and then compact their team formation during a match. This analysis can provide insights that allow coaches to better control the team organisation on the pitch.

Three-dimensional kinematic analysis of upper and lower limb motion during gait of post-stroke patients

The aim of this study was to analyze the alterations of arm and leg movements of patients during stroke gait. Joint angles of upper and lower limbs and spatiotemporal variables were evaluated in two groups: hemiparetic group (HG, 14 hemiparetic men, 53 ± 10 years) and control group (CG, 7 able-bodied men, 50 ± 4 years). The statistical analysis was based on the following comparisons (P ≤ 0.05): 1) right versus left sides of CG; 2) affected (AF) versus unaffected (UF) sides of HG; 3) CG versus both the affected and unaffected sides of HG, and 4) an intracycle comparison of the kinematic continuous angular variables between HG and CG. This study showed that the affected upper limb motion in stroke gait was characterized by a decreased range of motion of the glenohumeral (HG: 6.3 ± 4.5, CG: 20.1 ± 8.2) and elbow joints (AF: 8.4 ± 4.4, UF: 15.6 ± 7.6) on the sagittal plane and elbow joint flexion throughout the cycle (AF: 68.2 ± 0.4, CG: 46.8 ± 2.7). The glenohumeral joint presented a higher abduction angle (AF: 14.2 ± 1.6, CG: 11.5 ± 4.0) and a lower external rotation throughout the cycle (AF: 4.6 ± 1.2, CG: 22.0 ± 3.0). The lower limbs showed typical alterations of the stroke gait patterns. Thus, the changes in upper and lower limb motion of stroke gait were identified. The description of upper limb motion in stroke gait is new and complements gait analysis.

Method for the estimation of a double hinge kinematic model for the trapeziometacarpal joint using MR imaging

In this paper, we propose a method to estimate the parameters of a double hinge model of the trapeziometacarpal joint (TMC) by MRI-based motion analysis. The model includes two non-orthogonal and non-intersecting rotation axes accounting for flexion–extension (F–E) and adduction–abduction (A–A). We evaluated the quality of the estimated model parameters in the prediction of the relative motion of the first metacarpal bone with respect to the trapezium. As a result, we obtained that: (a) the estimated location and orientation of the F–E and A–A axes were in agreement with previous in vitro studies, (b) the motion of the first metacarpal predicted by the 2 degrees of freedom (2DoF) model exhibits a maximum surface distance error in the range of about 2 mm and (c) four thumb postures at the boundary of the TMC range of motion are sufficient to provide a good estimation of the 2DoF TMC kinematic model and good reproducibility (∼1.7 mm) of the real thumb motion at TMC level.

Analysis of the distances covered and technical actions performed by professional tennis players during official matches.

ABSTRACT The purpose of this study was to analyse the physical and technical performances of professional tennis players during official matches. The trajectories of eight players were obtained during matches, using an automatic tracking method. The distances covered and technical performances were analysed for the first and second sets. The athletes covered (mean ± standard deviation) a total of 1702.4 ± 448.2 m in the first set, 1457.6 ± 678.1 m in the second set and 3160.0 ± 880.1 in the entire match. No differences were found between the sets for the physical variables (lateral and forward displacements, distance covered per rally, per game and per set, and the percentage of time spent in each range of velocity). However, the distances covered by the athletes during the rallies in which they were serving (median = 5.2; interquartile range (IQR) = 6.7 m) were statistically smaller than when they were returning (median = 6.2; IQR = 7.7 m). Forehand ground stroke proficiency decreased from the first (mean ± standard deviation: 75.2 ± 4.11%) to the second set (mean ± standard deviation = 65.5 ± 14.3%). In conclusion, tennis players did not present reduced physical performance from the first to the second set.