期刊
IUI'22: 27TH INTERNATIONAL CONFERENCE ON INTELLIGENT USER INTERFACES
卷 -, 期 -, 页码 277-291出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3490099.3511125
关键词
Gestures; Sensing; Wearables; Mobile Devices; Deep Learning
资金
- Department of Communications and Networking - Aalto University
- Academy of Finland [328813, 318559]
- Huawei Technologies
- Horizon 2020 FET program of the European Union [CHIST-ERA-20-BCI-001]
- Finnish Center for Artificial Intelligence (FCAI)
- Academy of Finland (AKA) [328813, 318559, 328813, 318559] Funding Source: Academy of Finland (AKA)
This paper discusses the challenges and problems of gesture recognition on smartwatches. By collecting diverse gesture data and utilizing prior knowledge, it is possible to design recognisers with robust performance on resource-constrained hardware.
Gesture recognition on smartwatches is challenging not only due to resource constraints but also due to the dynamically changing conditions of users. It is currently an open problem how to engineer gesture recognisers that are robust and yet deployable on smartwatches. Recent research has found that common everyday events, such as a user removing and wearing their smartwatch again, can deteriorate recognition accuracy significantly. In this paper, we suggest that prior understanding of causes behind everyday variability and false positives should be exploited in the development of recognisers. To this end, first, we present a data collection method that aims at diversifying gesture data in a representative way, in which users are taken through experimental conditions that resemble known causes of variability (e.g., walking while gesturing) and are asked to produce deliberately varied, but realistic gestures. Secondly, we review known approaches in machine learning for recogniser design on constrained hardware. We propose convolution-based network variations for classifying raw sensor data, achieving greater than 98% accuracy reliably under both individual and situational variations where previous approaches have reported significant performance deterioration. This performance is achieved with a model that is two orders of magnitude less complex than previous state-of-the-art models. Our work suggests that deployable and robust recognition is feasible but requires systematic efforts in data collection and network design to address known causes of gesture variability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据