Pedestrian Navigation Activity Recognition Based on Segmentation Transformer
- 1 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (15) , 26020-26032
Abstract
In the context of the Internet of Things, utilizing the inherent inertial sensors in smartphones for human activity recognition (HAR) has garnered considerable attention owing to its wide-ranging applications. However, prevailing HAR approaches primarily treat activity identification as a single-label classification task, focusing solely on discerning pedestrian motion modes or device usage modes, while disregarding their interrelatedness. Additionally, HAR methods employing sliding windows encounter challenges associated with the multiclass window problem, wherein certain sample labels differ from the label assigned to the window. This article aims to address these issues. This article presents a novel approach for simultaneously recognizing pedestrian motion and device usage modes by utilizing the segmentation Transformer. The proposed joint recognition framework effectively annotates sensor data at each timestamp and achieves dense prediction of time-series data through the encoding and decoding of the annotated data. To optimize the utilization of information extracted from each Transformer layer, a global up-sampling decoder based on the pyramid attention module is introduced, enabling dense decoding of features obtained from each Transformer layer. We performed experiments on two publicly available data sets to comprehensively assess the effectiveness of the proposed methodology. The results demonstrate that our approach achieves an accuracy of 99.79% and a weighted F-score of 99.77%, surpassing the performance of existing state-of-the-art methods. Furthermore, we constructed heterogeneous data sets to validate the robustness of our method. The extensive experimental findings indicate that the joint recognition framework effectively uncovers the inherent correlations between pedestrian motion and device usage modes, leading to enhanced accuracy in recognition and addressing the challenges posed by the multiclass window problem.Keywords
Funding Information
- Joint Research Fund for Beijing Natural Science Foundation and Haidian Original Innovation (L232001)
- Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515011866)
- Central Guidance on Local Science and Technology Development Fund of Shanxi Province (YDZJSX20231D005)
- National Natural Science Foundation of China (62002026)
- University of Science and Technology Beijing Young Faculty International Exchange and Development Program (QNXM20230016)
- Beijing Science and Technology Plan (Z231100005923025)
This publication has 50 references indexed in Scilit:
- A novel two-level interactive action recognition model based on inertial data fusionInformation Sciences, 2023
- Boosting Inertial-Based Human Activity Recognition With TransformersIEEE Access, 2021
- Multi-input CNN-GRU based human activity recognition using wearable sensorsComputing, 2021
- End-to-End Object Detection with Transformers2020
- Human Activity Recognition Based on Motion Sensor Using U-NetIEEE Access, 2019
- Deep learning for time series classification: a reviewData Mining and Knowledge Discovery, 2019
- The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics With Mobile DevicesIEEE Access, 2018
- Efficient dense labelling of human activity sequences from wearables using fully convolutional networksPattern Recognition, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Human Activity Recognition Model Based on Decision Tree2013