| I. Vernikos, T. Spyropoulos, E. Spyrou, Ph. Mylonas |
| Human Activity Recognition in Presence of Occlusion |
| Sensors, 23(10), MDPI, 19 May 2023 |
|
ABSTRACT
|
| The presence of occlusion in Human Activity Recognition (HAR) tasks hinders the performance of recognition algorithms, as it is responsible for loss of crucial motion data. Although it is intuitive that it may occur in almost any real-life environment, it is often underestimated in most research works, which tend to rely on datasets that have been collected under ideal conditions, i.e., without any occlusion. In this work we present an approach that aims to deal with occlusion in a HAR task. We rely on previous work on HAR and artificially create occluded data samples, assuming that occlusion may prevent the recognition of one or two body parts. The HAR approach we use is based on a Convolutional Neural Network (CNN) that has been trained using 2-D representations of 3-D skeletal motion. We consider the cases where the network is trained with and without occluded samples and evaluate our approach in single-view, cross-view and cross-subject cases and using two large scale human motion datasets. Our experimental results indicate that the proposed training strategy is able to provide a significant boost of performance, in presence of occlusion.
|
| 19 May , 2023 |
| I. Vernikos, T. Spyropoulos, E. Spyrou, Ph. Mylonas, "Human Activity Recognition in Presence of Occlusion", Sensors, 23(10), MDPI, 19 May 2023 |
[  PDF] [
BibTex] [
Print] [
 Back] |
