A CSI-based Human Activity Recognition using Canny Edge Detector
Conference paper
Hossein Shahverdi, Parisa Fard Moshiri, Mohammad Nabati, Reza Asvadi and Ghorashi, S. 2022. A CSI-based Human Activity Recognition using Canny Edge Detector. 4th International Conference on Activity and Behavior Computing (ABC 2022). London, UK. 27 - 29 Oct 2022 CRC Press: Taylor & Francis Group.
Authors | Hossein Shahverdi, Parisa Fard Moshiri, Mohammad Nabati, Reza Asvadi and Ghorashi, S. |
---|---|
Type | Conference paper |
Abstract | Human Activity Recognition (HAR) is one of the hot topics in the field of human-computer interaction. It has a wide variety of applications in different tasks such as health rehabilitation, smart houses, smart grids, robotics, and human action prediction. HAR can be carried out through different approaches such as vision-based, sensor-based, radar-based, and Wi-Fi-based. Due to the ubiquitous and easyto-deploy characteristic of Wi-Fi devices, Wi-Fi-based HAR has gained the interest of both academia and industry in recent years.WiFi-based HAR can be implemented by two channel metrics: Channel State Information (CSI) and Received Signal Strength Indicator (RSSI). Recently, converting the CSI data to images has led to increasing the accuracy level of activity prediction. However, none of the previous research has focused on extracting the features of converted images using image-processing techniques. In this study, we investigate three available datasets, gathered using CSI property, and took advantage of Deep Learning (DL), with convolutional layers and edge detection technique to increase overall system accuracy. The canny edge detector extracts the most important features of the image, and giving it to the DL |
Year | 2022 |
Conference | 4th International Conference on Activity and Behavior Computing (ABC 2022) |
Publisher | CRC Press: Taylor & Francis Group |
Accepted author manuscript | License File Access Level Repository staff only |
Publication dates | |
26 Jan 2024 | |
Publication process dates | |
Accepted | Sep 2022 |
Deposited | 16 Jun 2023 |
Journal citation | In Press |
Book title | Human Activity and Behavior Analysis: Advances in Computer Vision and Sensors: Volume 2 |
Book editor | Ahad, M. |
Inoue, S. | |
Lopez, G. | |
Hossain, T. | |
ISBN | 9781032598765 |
Web address (URL) of conference proceedings | https://www.routledge.com/9781032598765 |
Web address (URL) | https://abc-research.github.io/2022/ |
Copyright holder | © 2022, The Author(s) |
https://repository.uel.ac.uk/item/8w29v
Restricted files
Accepted author manuscript
59
total views29
total downloads6
views this month0
downloads this month