Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
About

About

Miguel Velhote Correia graduated in Electrical and Computer Engineering from University of Porto, Faculty of Engineering (FEUP) in 1990. He obtained the Master and the Doctoral degrees also from FEUP in 1995 and 2001, in the fields of Industrial Automation and Computer Vision, respectively. Currently, he is an Assistant Professor at the Department of Electrical and Computer Engineering at FEUP, since 2002 and with tenure since 2007. Since March 2008, he is also a senior research member at INESC Technology and Science – Institute of Systems and Computer Engineering of Porto, head of the Bioinstrumentation Laboratory of the Centre for Biomedicla Engineering Research. Additionally, he is co-founder and technical advisor of Kinematix Sense S.A. (formerly Tomorrow Options - Microelectronics S.A), an electronic devices start-up company of University of Porto and INESCTEC. Between 1993 and 2007, he was a researcher at INEB – Institute of Biomedical Engineering, in the Biomedical Imaging and Vision Computing group and previously at the CIM Centre of Porto at FEUP. His main research interests are in Sensors and Electronics, Biomedical Instrumentation, Computational Vision and Image and Signal Processing, with focus in sensing methods, technologies and data fusion for the measurement and analysis of human movement, perception, action and performance. Since 1990, he participated in more than twenty funded research projects and co-authored over 100 research papers published in peer reviewed journals and conference proceedings. He is also member of the Portuguese Official Engineers Association, the International Association of Pattern Recognition, through its Portuguese chapter, and co-founder of the Portuguese Experimental Psychology Association.

Interest
Topics
Details

Details

003
Publications

2018

Innovative analysis of 3D pelvis coordination on modified gait mode

Authors
Rodrigues, C; Correia, MV; Abrantes, JMCS; Nadal, J; Rodrigues, MAB;

Publication
Lecture Notes in Computational Vision and Biomechanics

Abstract
This study presents innovative analysis at the time, frequency and phase domain of the pelvis angular oscillation at transverse (T), sagittal (S) and coronal (C) planes, assessing its coordination during stiff knee gait (SKG) and slow running (SR) comparing it to normal gait (NG). Case study is considered of an adult male 70 kg mass and 1.86 m height. Computer vision is used with 8 Qualysis 100 Hz cameras tracking position of right and left anterior and posterior superior iliac spine (RAsis, LAsis, RPsis, LPsis) including one complete stride during NG, SKG and SR. 3D position coordinates are obtained from 2D image coordinate of multiple camera image using direct linear transformation (DLT). Inverse kinematics is performed using cartesian position data of RAsis, LAsis, RPsis, LPsis and scaled model to subject dimension. The angles, angular velocities and angular accelerations coordination of the pelvis oscillation at T, S, C planes were assessed using linear and cross correlation analysis (LCA, CCA), fast Fourier transform (FFT) and phase space analysis (PSA). Results point for important complementary analysis on entire series of time, frequency and phase analysis of human movement such as the pelvis coordination assessment on different gait modes. © 2018, Springer International Publishing AG.

2017

Analysis and quantification of upper-limb movement in motor rehabilitation after stroke

Authors
Silva, RM; Sousa, E; Fonseca, P; Pinheiro, AR; Silva, C; Correia, MV; Mouta, S;

Publication
Biosystems and Biorobotics

Abstract
It is extremely difficult to reduce the relations between the several body parts that perform human motion to a simplified set of features. Therefore, the study of the upper-limb functionality is still in development, partly due to the wider range of actions and strategies for motor execution. This, in turn, leads to inconsistent upper-limb movement parameterization. We propose a methodology to assess and quantify the upper-limb motor execution. Extracting key variables from different sources, we intended to quantify healthy upper-limb movement and use these parameters to quantify motor execution during rehabilitation after stroke. In order to do so, we designed an experimental setup defining a workspace for the execution of the action recording kinematic data. Results reveal an effect of object and instruction on the timing of upper-limb movement, indicating that the spatiotemporal analysis of kinematic data can be used as a quantification parameter for motor rehabilitation stages and methods. © Springer International Publishing AG 2017.

2017

Consistency of surface electromyography assessment at lower limb selected muscles during vertical countermovement

Authors
Rodrigues, C; Correia, M; Abrantes, JMCS; Nadal, J; Benedetti Rodrigues, MAB;

Publication
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

Abstract
Given the difficulty of invasive methods to assess muscle action during natural human movement, surface electromyography (sEMG) has been increasingly used to capture muscle activity in relation to kinesiological analysis of specific tasks. Isolated isometric, concentric and eccentric forms of muscle action have been receiving the most attention for research purposes. Nevertheless natural muscle action frequently involves the use of a preceding eccentric muscle action as a form of potentiation of immediate muscle concentric action, in what is designated as muscle stretch-shortening cycle (SSC). The most frequently applied protocols for the evaluation of SSC on vertical jumps are by virtue of their reproducibility and control of experimental conditions, squat jump (SJ) without countermovement (CM), countermovement jump (CMJ) with long CM and drop jump (DJ) with short CM. The methods used to extract information and relationship of the captured signals also present a high diversity, with the question about the consistency of the methods and obtained results. The objective of this study is to evaluate the consistency of the analysis and results by applying different EMGs signal analysis techniques related to strategic muscle groups of the lower limbs at different countermovement evaluated in vertical jumps. Raw sEMG signals of 5 lower limb muscles of 6 subjects during SJ, CMJ and DJ were rectified, filtered and obtained their envelope, and then correlated (CR) for detection of synergistic, agonist and antagonist activity, applied principal component analysis (PCA) for the detection of uncorrelated components explaining maximum variability and normalized cross-correlation (CCRN) for detection of maximum correlations and time lag. CR of EMG envelopes presented higher coactivities (CoA) in DJ relative to SJ and these CoA superior to CMJ with greater synergy in DJ relative to SJ and CMJ that present several loop cycles corresponding to time lag of activity. CCRN of the EMG envelopes presented also higher CoA in DJ when compared to SJ and both higher CoA to CMJ. PCA allowed to detect a principal component (PC) explaining 92.2% of the variability of EMG in DJ, 90.6% in SJ and 78.7% in CMJ, the second PC responsible for the explanation of 4.9% variability in DJ, 6.7% in SJ and 15.3% in CMJ. © 2017 IEEE.

2017

Visual motion perception for mobile robots through dense optical flow fields

Authors
Pinto, AM; Costa, PG; Correia, MV; Matos, AC; Moreira, AP;

Publication
ROBOTICS AND AUTONOMOUS SYSTEMS

Abstract
Recent advances in visual motion detection and interpretation have made possible the rising of new robotic systems for autonomous and active surveillance. In this line of research, the current work discusses motion perception by proposing a novel technique that analyzes dense flow fields and distinguishes several regions with distinct motion models. The method is called Wise Optical Flow Clustering (WOFC) and extracts the moving objects by performing two consecutive operations: evaluating and resetting. Motion properties of the flow field are retrieved and described in the evaluation phase, which provides high level information about the spatial segmentation of the flow field. During the resetting operation, these properties are combined and used to feed a guided segmentation approach. The WOFC requires information about the number of motion models and, therefore, this paper introduces a model selection method based on a Bayesian approach that balances the model's fitness and complexity. It combines the correlation of a histogram-based analysis with the decay ratio of the normalized entropy criterion. This approach interprets the flow field and gives an estimative about the number of moving objects. The experiments conducted in a realistic environment have proved that the WOFC presents several advantages that meet the requirements of common robotic and surveillance applications: is computationally efficient and provides a pixel-wise segmentation, comparatively to other state-of-the-art methods.

2017

Validating subject multibody dynamics estimated action with measured SEMG at lower limb muscles on different gait modes

Authors
Rodrigues, C; Correia, M; Abrantes, J;

Publication
Proceedings of the 8th ECCOMAS Thematic Conference on MULTIBODY DYNAMICS 2017, MBD 2017

Abstract
This study presents and applies a quantitative metric, based on entire time series of measured surface electromyography (sEMG) from selected lower limb muscles to validate multibody dynamics (MBD) estimated action of the same subject muscles during modified gait, stiff knee gait (SKG) and slow running (SR) in relation to normal gait (NG). MBD is being increasingly applied for estimation of internal actions according to difficulty of its direct measurements under natural conditions of movement and the importance of this estimation for prevention, diagnosis and treatment planning of specific subject skeletal and neuromuscular diseases. Inverse kinematics and inverse dynamics from position and force data have been used to estimate internal joint force moments, with muscle grouping and optimization techniques applied along with musculoskeletal model for estimation of muscle action. Nevertheless kinematic and kinetic input data of human movement must be accurate and employed model for simulation must be personalized to subject, task and moment of application. Also the results provided by the simulation with the musculoskeletal model must be compared with measured results for validation. Comparative analysis of kinematic and kinetic input data of human lower limbs is performed during modified gait modes and a personalized musculoskeletal model employed for MBD estimation of muscle actions and compare estimated muscle actions with measured sEMG of selected muscles on different gait modes, SKG and SR in relation to those registered at NG. The results from quantitative metrics followed qualitative agreement from visual inspection with better agreement between processed sEMG and MBD muscle estimated activity on phase metric than at magnitude, and combined metric presenting overall better agreement at NG and SKG than at SR, pointing to higher ability of the model to predict muscle force patterns in agreement with measured sEMG activity at NG and SKG than at SR and the need to improve model predictions for SR. Applied technique presents as a reproducible quantitative metric based on entire time series, both magnitude and phase, overcoming qualitative and subjective comparing by the observer, reducing time consuming and allowing increase at the number of automatic validation of MBD muscle action estimation.

Supervised
thesis

2017

Sensors fusion and movement analysis for sports performance optimization

Author
Bárbara França Domingues Cardoso

Institution
UP-FEUP

2017

Measure Impedance in Congestive Heart Failure Patients

Author
José Carlos Coelho Alves

Institution
UP-FEUP

2017

Rehabilitation Exercises for Knee Recovery at Home

Author
Sara Pereira Mendes de Oliveira

Institution
UP-FEUP

2017

Integração de sensores em calçado de elevado desempenho

Author
Eduardo Fernando Nogueira Rodrigues da Rocha

Institution
UP-FEUP

2017

Measurement System for Evaluation of Cycling Performance

Author
Diogo José Fernandes Gonçalves

Institution
UP-FEUP