HAUAR: Home Automation Using Action Recognition

Kotyan, Shashank; Udutalapally, Venkanna; Kumar, Nitish; Sahu, Pankaj

doi:10.1109/infocomtech.2018.8722359

Cited by 5 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic Human Action Recognition (HAR) is a research area that is utilized in various fields of application where human monitoring is infeasible due to the amount of data and scenarios where quick reaction times are vital, such as surveillance and realtime monitoring of suspicious and abnormal behavior in public areas [12,33,34,49] or intelligent hospitals and healthcare sectors [8,9] with scenarios such as fall detection [36,45], monitoring of medication intake [13] and detection of other potentially life-threatening situations [8]. Additional areas of applications include video retrieval [40], robotics [41], smart home automation [21], autonomous vehicles [52]. In recent years, approaches based on neural networks, especially GCNs, like ST-GCN [51] or 2s-AGCN [43], have achieved state-of-the-art results in classifying human actions from time series data.…”

Section: Introductionmentioning

confidence: 99%

Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks

Michael¹,

Memmesheimer²,

Paulus³

2021

Preprint

View full text Add to dashboard Cite

In this paper we present Fusion-GCN, an approach for multimodal action recognition using Graph Convolutional Networks (GCNs). Action recognition methods based around GCNs recently yielded state-of-the-art performance for skeleton-based action recognition. With Fusion-GCN, we propose to integrate various sensor data modalities into a graph that is trained using a GCN model for multi-modal action recognition. Additional sensor measurements are incorporated into the graph representation either on a channel dimension (introducing additional node attributes) or spatial dimension (introducing new nodes). Fusion-GCN was evaluated on two publicly available datasets, the UTD-MHAD-and MMACT datasets, and demonstrates flexible fusion of RGB sequences, inertial measurements and skeleton sequences. Our approach gets comparable results on the UTD-MHAD dataset and improves the baseline on the large-scale MMACT dataset by a significant margin of up to 12.37% (F1-Measure) with the fusion of skeleton estimates and accelerometer measurements.

show abstract