Projecte llegit
Títol: Computer Vision Analysis of the body-pose similarity from two different subjects with the aim of the correct development of physical exercises.
Estudiants que han llegit aquest projecte:
MACIÁN RIBERA, SERGI (data lectura: 28-10-2020)- Cerca aquest projecte a Bibliotècnica
MACIÁN RIBERA, SERGI (data lectura: 28-10-2020)Director/a: TARRÉS RUIZ, FRANCESC
Departament: TSC
Títol: Computer Vision Analysis of the body-pose similarity from two different subjects with the aim of the correct development of physical exercises.
Data inici oferta: 22-01-2020 Data finalització oferta: 22-09-2020
Estudis d'assignació del projecte:
- MU MASTEAM 2015
| Tipus: Individual | |
| Lloc de realització: Fora UPC | |
| Supervisor/a extern: Angel Priegue Mayán | |
| Institució/Empresa: CIMNE | |
| Titulació del Director/a: Enginyer Superior Informàtica | |
| Paraules clau: | |
| Deep Learning, Image Processing, Pytorch, Tensorflow | |
| Descripció del contingut i pla d'activitats: | |
| Exercising in an incorrect way can lead us to not accomplish the exercises’ objectives
(sports, health, rehab, etc.) and also to cause injuries. That is why a correct realisation of them is a matter of relevant importance. Thanks to the computational improvements it is possible to solve this problematic by using Computer Vision techniques. The objective of this project is to take advantage of the State of the Art in terms of Pose-Recognition (or body key-points detection) in order to work on the similarities between a pose done by a professional and a pose done by a participant. |
|
| Overview (resum en anglès): | |
| In this project we have tried to generate a new neural network model capable to solve the pose estimation challenge in a sports environment. | |