The State-of-the-Art Sensing Techniques in Human Activity Recognition: A Survey

Abstract

Human activity recognition (HAR) has become an intensive research topic in the past decade because of the pervasive user scenarios and the overwhelming development of advanced algorithms and novel sensing approaches. Previous HAR-related sensing surveys were primarily focused on either a specific branch such as wearable sensing and video-based sensing or a full-stack presentation of both sensing and data processing techniques, resulting in weak focus on HAR-related sensing techniques. This work tries to present a thorough, in-depth survey on the state-of-the-art sensing modalities in HAR tasks to supply a solid understanding of the variant sensing principles for younger researchers of the community. First, we categorized the HAR-related sensing modalities into five classes: mechanical kinematic sensing, field-based sensing, wave-based sensing, physiological sensing, and hybrid/others. Specific sensing modalities are then presented in each category, and a thorough description of the sensing tricks and the latest related works were given. We also discussed the strengths and weaknesses of each modality across the categorization so that newcomers could have a better overview of the characteristics of each sensing modality for HAR tasks and choose the proper approaches for their specific application. Finally, we summarized the presented sensing techniques with a comparison concerning selected performance metrics and proposed a few outlooks on the future sensing techniques used for HAR tasks.

Human Action Recognition in Smart Living Services and Applications: Context Awareness, Data Availability, Personalization, and Privacy

“…Bian et al [42] present an extensive survey on sensing modalities used in HAR tasks, categorizing human activities and sensing techniques and discussing future development trends in HAR-related sensing techniques, such as sensor fusion, smart sensors, and novel sensors. Ige et al [43] survey wearable sensor-based HAR systems and unsupervised learning, discussing the adoption of unsupervised learning in wearable sensor-based HAR and highlighting future research directions.…”

Multi-dimensional task recognition for human-robot teaming: literature review

“…Human task recognition has been an active field of research for more than a decade; therefore, a number of review papers with a wide range of scope and objectives exist in the literature ( Lara and Labrador, 2013 ; Cornacchia et al, 2017 ; Nweke et al, 2018 ; Wang et al, 2019 ; Chen K. et al, 2021 ; Ramanujam et al, 2021 ; Bian et al, 2022 ; Zhang S. et al, 2022 ). This manuscript focuses on wearable sensor-based human task recognition; thus, this section is only focused on this domain.…”

Sensor-Based Human Activity and Behavior Research: Where Advanced Sensing and Recognition Technologies Meet

“…As the hardware cornerstone of all relevant research areas, sensing technology is a topic that cannot be jumped. We are delighted to have such an opening article in this Special Issue [ 10 ], which presented a thorough, in-depth survey on the state-of-the-art sensing modalities in HAR tasks to supply a solid understanding of the variant sensing principles for younger researchers of the community. The HAR-related sensing modalities are reasonably categorized into five classes: mechanical kinematic sensing, field-based sensing, wave-based sensing, physiological sensing, and hybrid/others, with the strengths and weaknesses of each modality across the categorization compared and discussed to provide newcomers with a better overview and references.…”