Activity recognition using first-person-view cameras based on sparse optical flows
Journal
Proceedings - International Conference on Pattern Recognition
Pages
81-86
Date Issued
2020
Author(s)
Abstract
First-person-view (FPV) cameras are finding wide use in daily life to record activities and sports. In this paper, we propose a succinct and robust 3D convolutional neural network (CNN) architecture accompanied with an ensemble-learning network for activity recognition with FPV videos. The proposed 3D CNN is trained on low-resolution (32 ? 32) sparse optical flows using FPV video datasets consisting of daily activities. According to the experimental results, our network achieves an average accuracy of 90%. © 2020 IEEE
SDGs
Other Subjects
Cameras; Convolutional neural networks; Optical flows; Activity recognition; Daily activity; Daily lives; Ensemble learning; First person; Low resolution; Video datasets; Pattern recognition
Type
conference paper