NORMA eResearch @NCI Library

Fall risk monitoring scheme based on human posture estimation using Transfer learning

Balasubramanian, Chitra Raghavi (2020) Fall risk monitoring scheme based on human posture estimation using Transfer learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (669kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


For the past few years, it has been witnessed a raise in fall detection-related research projects. Therefore, this paper presents the fall detection system using a vision based approach. For conducting this experiment, publicly available dataset has been taken that contains a record of Falls and Activities of daily life (ADL). This project mainly deals with the classification of fall and not-fall images. Before training the model, human motion was tracked in the consecutive frames using optical flow algorithm. Further, these optical flow images are fed into Convolutional neural network (CNN) to extract the features from the images for detecting the fall events. VGG-16, ResNet-50 and DenseNet-205 were implemented based on transfer learning approach with the help of pre trained “ImageNet” data. A 10-fold cross-validation was performed on the training set and applied it on the testing set to improve the accuracy of the model. Finally, the comparison has been made between three CNN architectures such as VGG16, ResNet-50 and DenseNet-201, and found that ResNet-50 performed better in classifying the falls and not fall labels correctly. The performance of the developed model is evaluated using Accuracy and Confusion matrix.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 22 Jan 2021 10:25
Last Modified: 22 Jan 2021 10:25

Actions (login required)

View Item View Item