A Survey on Hand Pose Estimation with Wearable Sensors and Computer-Vision-Based Methods

Chen, Weiya; Yu, Chenchen; Tu, Chenyu; Lyu, Zehua; Tang, Jing; Ou, Shifeng; Fu, Yan; Xue, Zhidong

doi:10.3390/s20041074

Cited by 97 publications

(52 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several approaches to recognize hand gestures: vision based [ 6 , 7 , 8 ], data glove based [ 9 , 10 ], and bio-signal based [ 11 , 12 , 13 , 14 ]. In particular, this study has focused on hand gesture recognition based on the data glove approach.…”

Section: Introductionmentioning

confidence: 99%

“…In the surveys of Rashid and Hasan [ 27 ] and Chen et al [ 8 ], they introduced four type of sensors for developing data gloves: flex sensor [ 28 , 29 , 30 , 31 ], stretch sensor [ 15 , 32 , 33 , 34 , 35 , 36 , 37 ], inertial measurement unit (IMU) [ 38 , 39 ], and magnetic sensor [ 40 , 41 ]. IMU sensor is popularly used for measuring the orientation in 3D space by fusing the information of accelerometers, gyroscopes, and magnetometers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hand Gesture Recognition Using EGaIn-Silicone Soft Sensors

Shin

Yoon

Yoo

2021

Sensors

View full text Add to dashboard Cite

Exploiting hand gestures for non-verbal communication has extraordinary potential in HCI. A data glove is an apparatus widely used to recognize hand gestures. To improve the functionality of the data glove, a highly stretchable and reliable signal-to-noise ratio sensor is indispensable. To do this, the study focused on the development of soft silicone microchannel sensors using a Eutectic Gallium-Indium (EGaIn) liquid metal alloy and a hand gesture recognition system via the proposed data glove using the soft sensor. The EGaIn-silicone sensor was uniquely designed to include two sensing channels to monitor the finger joint movements and to facilitate the EGaIn alloy injection into the meander-type microchannels. We recruited 15 participants to collect hand gesture dataset investigating 12 static hand gestures. The dataset was exploited to estimate the performance of the proposed data glove in hand gesture recognition. Additionally, six traditional classification algorithms were studied. From the results, a random forest shows the highest classification accuracy of 97.3% and a linear discriminant analysis shows the lowest accuracy of 87.4%. The non-linearity of the proposed sensor deteriorated the accuracy of LDA, however, the other classifiers adequately overcame it and performed high accuracies (>90%).

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hand Gesture Recognition Using EGaIn-Silicone Soft Sensors

Shin

Yoon

Yoo

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Computer vision-based hand pose estimation methods can be categorized into three types [7]. The first is a generative (model-based) method [8]- [11] to predict the position of the hand joints using a 3D hand model constructed based on prior knowledge of the hand structure.…”

Section: Introductionmentioning

confidence: 99%

3D Hand Pose Estimation via Graph-Based Reasoning

Song

Kang

2021

IEEE Access

View full text Add to dashboard Cite

Hand pose estimation from a single depth image has recently received significant attention owing to its importance in many applications requiring human-computer interaction. The rapid progress of convolutional neural networks (CNNs) and technological advances in low-cost depth cameras have greatly improved the performance of the hand pose estimation method. Nevertheless, regressing joint coordinates is still a challenging task due to joint flexibility and self-occlusion. Previous hand pose estimation methods have limitations in relying on a deep and complex network structure without fully utilizing hand joint connections. A hand is an articulated object and consists of six parts that represent the palm and five fingers. The kinematic constraints can be obtained by modeling the dependency between adjacent joints. This paper proposes a novel CNN-based approach incorporating hand joint connections to features through both a global relation inference for the entire hand and local relation inference for each finger. Modeling the relations between the hand joints can alleviate critical problems for occlusion and self-similarity. We also present a hierarchical structure with six branches that independently estimate the position of the palm and five fingers by adding hand connections of each joint using graph reasoning based on graph convolutional networks. Experimental results on public hand pose datasets show that the proposed method outperforms previous state-of-the-art methods. Specifically, our method achieves the best accuracy compared to state-of-the-art methods on public datasets. In addition, the proposed method can be utilized for real-time applications with an execution speed of 103 fps in a single GPU environment.INDEX TERMS 3D hand pose estimation, depth image, graph convolutional network.

show abstract

“…Conventional BLCs are characterized by large dimensions as they consist of two orthogonal pairs of 90° transmission lines (TLs). Miniaturization is an important pre-requisite to facilitate the application of couplers in modern communication systems, such as portable [ 9 , 10 ], or wearable electronics [ 11 , 12 ], but also Internet of Things (IoT) devices [ 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Low-Cost Automated Design of Compact Branch-Line Couplers

Bekasiewicz

2020

Sensors

View full text Add to dashboard Cite

Branch-line couplers (BLCs) are important components of wireless communication systems. Conventional BLCs are often characterized by large footprints which make miniaturization an important pre-requisite for their application in modern devices. State-of-the-art approaches to design compact BLCs are largely based on the use of high-permittivity substrates and multi-layer topologies. Alternative methods involve replacement of transmission-line sections of the circuit, with their composite counterparts, referred to as compact cells (CCs). Due to the efficient use of available space, CC-based couplers are often characterized by small footprints. The design of compact BLCs is normally conducted based on engineering experience. The process is laborious and requires many adjustments of topology followed by manual or, semi-automatic tuning of design parameters. In this work, a framework for low-cost automated design of compact BLCs using pre-defined CCs is proposed. The low cost of the presented design technique is ensured using equivalent-circuit models, space mapping correction methods, and trust-region-based local optimization algorithms. The performance of the framework is demonstrated based on three examples, concerning the design of unequal-power split coupler, comparison of automatically generated compact BLCs, as well as rapid re-design of the coupler for different substrates. Furthermore, the approach has been benchmarked against the state-of-the-art methods for low-cost design of circuits.

show abstract

A Survey on Hand Pose Estimation with Wearable Sensors and Computer-Vision-Based Methods

Cited by 97 publications

References 108 publications

Hand Gesture Recognition Using EGaIn-Silicone Soft Sensors

Hand Gesture Recognition Using EGaIn-Silicone Soft Sensors

3D Hand Pose Estimation via Graph-Based Reasoning

Low-Cost Automated Design of Compact Branch-Line Couplers

Contact Info

Product

Resources

About