학술논문
Automatic Video Labeling with Assembly Actions of Workers on a Production Line Using ResNet
Document Type
Conference
Author
Valadao, Myke D.M.; Amoedo, Diego A.; Torres, Gustavo M.; Mattos, Edma V.C.U.; Pereira, Antonio M.C.; Uchoa, Matheus S.; Torres, Lucas M.; Cavalcante, Victor L.G.; Linhares, Jose E.B.S.; Silva, Mateus O.; Silva, Agemilson P.; Cruz, Caio F.S.; Romulo, S.F.; Belem, Ruan J.S.; Bezerra, Thiago B.; Junior, Waldir S.S.; Carvalho, Celso B.
Source
2022 IEEE International Conference on Consumer Electronics - Taiwan Consumer Electronics - Taiwan, 2022 IEEE International Conference on. :323-324 Jul, 2022
Subject
Language
ISSN
2575-8284
Abstract
In this work, conducted by two partners, called UFAM/CETELI and, Envision (TPV Group), we present a method of automatic labeling of frames of worker's actions in factory environments using a model generated by a residual neural network. With this approach we used some manually labeled frames to training a model that provide the label of 4 classes of actions. We achieve accuracy rate over 96%, which give reliability to a supervised training of 3D dataset of actions.