Poster abstract: Maximizing accuracy of fall detection and alert systems based on 3D convolutional neural network
- Title
- Poster abstract: Maximizing accuracy of fall detection and alert systems based on 3D convolutional neural network
- Author(s)
- Hwang, Seokhyun ; Ahn, DaeHan ; Park, Homin ; Park, Taejoon
- DGIST Authors
- Hwang, Seokhyun ; Ahn, DaeHan ; Park, Homin ; Park, Taejoon
- Issued Date
- 2017
- Type
- Conference
- Article Type
- Conference Paper
- ISBN
- 9781450000000
- Abstract
- We present a deep-learning-based approach to maximize the accuracy and reliability of vision-based fall detection and alert systems. The proposed approach utilizes a 3D convolutional neural network (3D-CNN) to analyze the continuous motion data obtained from depth cameras and exploits a data augmentation method to do away with overfitting. Our preliminary evaluation results demonstrate that it achieves the classification accuracy of up to 96.9%. © 2017 ACM.
- Publisher
- Association for Computing Machinery, Inc
- Files in This Item:
-
There are no files associated with this item.
- Appears in Collections:
- ETC 2. Conference Papers
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.