On-Skin Interaction Using Body Landmarks

Steimle, Jürgen; Bergström-Lehtovirta, Joanna; Weigel, Martin; Nittala, Aditya Shekhar; Boring, Sebastian; Olwal, Alex; Hornbak, Kasper

doi:10.1109/mc.2017.3641636

Cited by 22 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These overlays sense touch [41], multi-touch [59] or pressure [4] but can only be placed on top of the skin, and have not been designed for a repeated amount of stretch and strain. Another approach to implement On-skin interfaces without the need for additional overlays is to use optical tracking to detect gestures directly on the user skin [15,30,101,87,97,28,50,61]. This allows users to benefit fully from the haptic properties of the skin even if the tracking is less accurate than with a thin sensing overlay.…”

Section: On-skin Interfacesmentioning

confidence: 99%

Skin-On Interfaces

Teyssier

Bailly

Pélachaud

et al. 2019

Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

show abstract

Section: On-skin Interfacesmentioning

confidence: 99%

Skin-On Interfaces

Teyssier

Bailly

Pélachaud

et al. 2019

Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

show abstract

“…Our tactile feel-through concept is inspired by pioneering work on Tactile Augmented Reality (TAR) by Bau et al [5]. We also drew inspiration from flexible on-skin interfaces [40,64,46,65] which contain sensors and displays (but not tactile output) that are thin enough to allow the user to feel-through natural tactile body landmarks [65,57]. Indirect tactile actuation technologies [5,71,69] do not need to overlay the interaction area and hence provide an alternative to feel-through interfaces.…”

Section: Related Workmentioning

confidence: 99%

“…On-skin interaction is an emerging area of growing importance [19,72,64,56]. Tactile features of the human body, such as knuckles and wrinkles, have been shown to offer affordances and landmarks that can guide the user during eyes-free on-body input [65,57]. However, these landmarks are static.…”

Section: Dynamic Tactile Landmarks For Eyes-free On-body Inputmentioning

confidence: 99%

“…A feel-through display on the fingertip is also compatible with various kinds of dexterous interactions, such as writing with a pen or leafing through pages of a document. Moreover, it enables novel types of on-skin interfaces that provide dynamic tactile output while still allowing the user to feel static tactile body landmarks, such as knuckles, wrinkles, or veins, which provide guidance and orientation during eyesfree interaction [57].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tacttoo

Withana

Groeger

Steimle

2018

Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology

136

View full text Add to dashboard Cite

show abstract

“…Such a role in 3D scan processing is played by human body landmarks. The body landmarks are described as unique and unambiguous locations on the human skin that can act as references for users to locate and identify points of interest [9]. Due to the direct influence on a measurement quality, these points are one of the most important scopes of interest in anthropometry [10].…”

Section: Introductionmentioning

confidence: 99%

Algorithm for Detecting Characteristic Points on a Three-Dimensional, Whole-Body Human Scan

2020

View full text Add to dashboard Cite

Anthropometric landmarks obtained from three-dimensional (3D) body scans are widely used in medicine, civil engineering, and virtual reality. For all those fields, an acquisition of certain and accurate landmark positions is crucial for obtaining satisfying results. Manual marking is time-consuming and is affected by the subjectivity of the human operator. Therefore, an automatic approach has become increasingly popular. This paper provides a short survey of different attempts for automatic landmark localization, from which one machine learning-based method was further analyzed and extended in the case of input data preparation for a convolutional neural network (CNN). A novel method of data processing is presented which utilize a mid-surface projection followed by further unwrapping. The article emphasizes its significance and the way it affects the outcome of a deep neural network. The workflow and the detailed description of algorithms used are included in this paper. To validate the method, it was compared with the orthogonal projection used for the state-of-the-art approach. Datasets consisting of 200 specimens, acquired using both methods, were used for convolutional neural networks training and 20 for validation. In this paper, we used YOLO v.3 architecture for detection and ResNet-152 for classification. For each approach, localizations of 22 normalized body landmarks for 10 male and 10 female subjects of different ages and various postures were obtained. To compare the accuracy of approaches, errors and their distribution were measured for each characteristic point. Experiments confirmed that the mid-surface projections resulted, on average, in a 14% accuracy improvement and up to 15% enhancement of resistance on errors related to scan imperfections.

show abstract

On-Skin Interaction Using Body Landmarks

Cited by 22 publications

References 11 publications

Skin-On Interfaces

Skin-On Interfaces

Tacttoo

Algorithm for Detecting Characteristic Points on a Three-Dimensional, Whole-Body Human Scan

Contact Info

Product

Resources

About