Classification of Human Movements with Motion Capture Data in a Motor Rehabilitation Context

Rodrigues, Luis Guilherme Silva; Dias, Diego Roberto Colombo; Guimarães, Marcelo de Paiva; Brandão, Alexandre Fonseca; Rocha, Leonardo Cristian; Iope, Rogério Luiz; Brega, José Remo Ferreira

doi:10.1145/3488162.3488210

Cited by 3 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model was able to generalize the movements of people outside the training set in the previous work (Rodrigues et al, 2021), while this work does not focus on this test. The humanoid shown on the left side of the screen (Figure 1) has feedback on the tracking and storing because it receives the same rotation used in the model.…”

Section: Resultsmentioning

confidence: 97%

“…This extended version of the work done by Rodrigues et al (2021) presents a broader implementation of body movements classification using the same system. We described how to use the skeleton data for a supervised classification when multiple articulations are involved.…”

Section: Discussionmentioning

confidence: 99%

“…However, the Pose Tracking technique can also generate the skeleton structure in real-time, such as the Pose Tracking model in the work of Bazarevsky et al (2020). The similarity of body structures between Kinect data and the outputs RGB Pose Tracking brings the opportunity of porting the mentioned solutions to be used in RGB-only devices as already implemented by Rodrigues et al (2021).…”

Section: Movements Classificationmentioning

confidence: 99%

“…In a previous study, Rodrigues et al (2021) presented a novel application that recognizes eight movements performed by the users. The results presented that the data generated by the tracking algorithm through RGB devices are suitable for input in classification models and suggest that the process can be extended to more types of movements, keeping the same preprocessing.…”

Section: Introductionmentioning

confidence: 99%

“…The results presented that the data generated by the tracking algorithm through RGB devices are suitable for input in classification models and suggest that the process can be extended to more types of movements, keeping the same preprocessing. This paper extended the developed system created by Rodrigues et al (2021) to analyze more complex movements and recognize both sides of the body since the previous study had only right arm movements. In this paper, we define movement classes that comprise exercises for the shoulders, elbows, and legs, involving most body articulations.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Supervised Classification of Motor-Rehabilitation Body Movements with RGB Cameras and Pose Tracking Data

Rodrigues

Dias²,

Guimarães³

et al. 2022

JIS

Self Cite

View full text Add to dashboard Cite

The technological evolution allowed the use of a single camera for precise and effective body tracking, reducing the cost and increasing the accessibility of applications in places where depth cameras and wearable sensors are not available. This paper describes and implements a supervised machine learning process consisting of a mobile application used as a motion capture device which also transforms the data into an input for a machine learning model that classifies upper and lower limbs movements (24 types of human movements). The user performs movements in front of the camera, and the trained model classifies them. We designed the system to work in a motor-rehabilitation context to assist the professional while the patient does physical exercises. The implementation can summarize the movements made during the rehabilitation sessions by counting the repetitions and classifying them when done completely or reached a specific range of motion.

show abstract

Section: Resultsmentioning

confidence: 97%

Section: Discussionmentioning

confidence: 99%

Section: Movements Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations