Gesture Recognition with Sensor Data Fusion of Two Complementary Sensing Methods

Landgraf, Maximilian; Yoo, In Seong; Seßner, Julian; Mooser, Maximilian; Kaufmann, D.; Mattejat, David; Reitelshöfer, Sebastian; Franke, Jörg

doi:10.1109/biorob.2018.8487949

Cited by 6 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments using proposed model of feature fusion and decision fusion was conducted on 10 normal subjects and five post stroke patients showed increased classification accuracy. This classification accuracy is comparable to other sensors fusion method such as EMG and force myograph (FMG) (Jiang et al, 2020 ), EMG and IMU (Georgi et al, 2015 ), and EMG and strain sensors (Landgraf et al, 2018 ). However, Leap motion is easy to use and off-the-shelf compared with these sensors.…”

Section: Discussionsupporting

confidence: 58%

Toward Hand Pattern Recognition in Assistive and Rehabilitation Robotics Using EMG and Kinematics

Zhou

Zhang

et al. 2021

Front. Neurorobot.

View full text Add to dashboard Cite

Wearable hand robots are becoming an attractive means in the facilitating of assistance with daily living and hand rehabilitation exercises for patients after stroke. Pattern recognition is a crucial step toward the development of wearable hand robots. Electromyography (EMG) is a commonly used biological signal for hand pattern recognition. However, the EMG based pattern recognition performance in assistive and rehabilitation robotics post stroke remains unsatisfactory. Moreover, low cost kinematic sensors such as Leap Motion is recently used for pattern recognition in various applications. This study proposes feature fusion and decision fusion method that combines EMG features and kinematic features for hand pattern recognition toward application in upper limb assistive and rehabilitation robotics. Ten normal subjects and five post stroke patients participating in the experiments were tested with eight hand patterns of daily activities while EMG and kinematics were recorded simultaneously. Results showed that average hand pattern recognition accuracy for post stroke patients was 83% for EMG features only, 84.71% for kinematic features only, 96.43% for feature fusion of EMG and kinematics, 91.18% for decision fusion of EMG and kinematics. The feature fusion and decision fusion was robust as three different levels of noise was given to the classifiers resulting in small decrease of classification accuracy. Different channel combination comparisons showed the fusion classifiers would be robust despite failure of specific EMG channels which means that the system has promising potential in the field of assistive and rehabilitation robotics. Future work will be conducted with real-time pattern classification on stroke survivors.

show abstract

Section: Discussionsupporting

confidence: 58%

Toward Hand Pattern Recognition in Assistive and Rehabilitation Robotics Using EMG and Kinematics

Zhou

Zhang

et al. 2021

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…They are obtained from an elastomeric insulating layer (e.g., made of a silicone rubber) sandwiched between two layers of a deformable electrode material (e.g., a carbon black-loaded silicone rubber), so as to assemble a stretchable capacitor. By arranging a set of these sensors such that they are stretched by specific postures and movements, following a calibration it is possible to relate occurring variations of capacitance to thee motions of body segments, as shown by several studies [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ].…”

Section: Introductionmentioning

confidence: 99%

“…Recently, some of us presented a low-cost wearable concept to monitor movements of the trunk, using elastomeric capacitive sensors in combination with modified shoulder straps [ 29 ]. The latter were intended to make the system easily wearable onto or under common clothes, so as to avoid less practical/stable, uncomfortable or more expensive solutions, such as sticking the sensors onto the skin [ 22 , 23 , 24 , 25 , 27 ] or creating dedicated elastic garments that integrate printed sensors [ 26 ].…”

Section: Introductionmentioning

confidence: 99%

“…The implementation of a calibration strategy that avoids the limitations of typical approaches reported in the literature, such as measuring the angles with bulky, unpractical, and/or expensive external equipment (e.g., stereophotogrammetry [ 19 , 20 , 21 , 22 , 23 , 24 , 25 ]), or using interpolations of data captured from reference poses (which enables pose recognitions but does not provide accurate measurements of angles [ 26 , 27 , 28 ]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wearable Detection of Trunk Flexions: Capacitive Elastomeric Sensors Compared to Inertial Sensors

Frediani

Bocchi

Vannetti

et al. 2021

Sensors

View full text Add to dashboard Cite

Continuous monitoring of flexions of the trunk via wearable sensors could help various types of workers to reduce risks associated with incorrect postures and movements. Stretchable piezo-capacitive elastomeric sensors based on dielectric elastomers have recently been described as a wearable, lightweight and cost-effective technology to monitor human kinematics. Their stretching causes an increase of capacitance, which can be related to angular movements. Here, we describe a wearable wireless system to detect flexions of the trunk, based on such sensors. In particular, we present: (i) a comparison of different calibration strategies for the capacitive sensors, using either an accelerometer or a gyroscope as an inclinometer; (ii) a comparison of the capacitive sensors’ performance with those of the accelerometer and gyroscope; to that aim, the three types of sensors were evaluated relative to stereophotogrammetry. Compared to the gyroscope, the capacitive sensors showed a higher accuracy. Compared to the accelerometer, their performance was lower when used as quasi-static inclinometers but also higher in case of highly dynamic accelerations. This makes the capacitive sensors attractive as a complementary, rather than alternative, technology to inertial sensors.

show abstract

“…They are made of an elastomeric (e.g., silicone made) insulating membrane, sandwiched between two elastomeric conductive layers (e.g., made of a carbon black-silicone composite), acting as soft electrodes, so as to obtain a deformable capacitor. By using them as wearable sensors, it is possible, following a calibration, to relate variations of capacitances to changes in postures, as shown by various investigations [22][23][24][25][26][27][28][29][30][31].…”

Section: Introductionmentioning

confidence: 99%

Monitoring Flexions and Torsions of the Trunk via Gyroscope-Calibrated Capacitive Elastomeric Wearable Sensors

Frediani

Vannetti

Bocchi

et al. 2021

Sensors

View full text Add to dashboard Cite

Reliable, easy-to-use, and cost-effective wearable sensors are desirable for continuous measurements of flexions and torsions of the trunk, in order to assess risks and prevent injuries related to body movements in various contexts. Piezo-capacitive stretch sensors, made of dielectric elastomer membranes coated with compliant electrodes, have recently been described as a wearable, lightweight and low-cost technology to monitor body kinematics. An increase of their capacitance upon stretching can be used to sense angular movements. Here, we report on a wearable wireless system that, using two sensing stripes arranged on shoulder straps, can detect flexions and torsions of the trunk, following a simple and fast calibration with a conventional tri-axial gyroscope on board. The piezo-capacitive sensors avoid the errors that would be introduced by continuous sensing with a gyroscope, due to its typical drift. Relative to stereophotogrammetry (non-wearable standard system for motion capture), pure flexions and pure torsions could be detected by the piezo-capacitive sensors with a root mean square error of ~8° and ~12°, respectively, whilst for flexion and torsion components in compound movements, the error was ~13° and ~15°, respectively.

show abstract

Gesture Recognition with Sensor Data Fusion of Two Complementary Sensing Methods

Cited by 6 publications

References 5 publications

Toward Hand Pattern Recognition in Assistive and Rehabilitation Robotics Using EMG and Kinematics

Toward Hand Pattern Recognition in Assistive and Rehabilitation Robotics Using EMG and Kinematics

Wearable Detection of Trunk Flexions: Capacitive Elastomeric Sensors Compared to Inertial Sensors

Monitoring Flexions and Torsions of the Trunk via Gyroscope-Calibrated Capacitive Elastomeric Wearable Sensors

Contact Info

Product

Resources

About