A Two-Dimensional Feature Space-Based Approach for Human Locomotion Recognition

Chinimilli, Prudhvi Tej; Redkar, Sangram; Sugar, Thomas G.

doi:10.1109/jsen.2019.2895289

Cited by 20 publications

(15 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because MHF is a task-invariant moment corresponding to the maximum value of θ th during a cycle, a threshold-based method can be used to detect the MHF in real-time. We ran the peak search algorithm in [25] during the swing period to find local maxima of the thigh angle, and then used thresholds on thigh kinematics and detection interval to determine whether a maximum was global, corresponding to MHF.…”

Section: E Real-time Detection Of Mhf and Hsmentioning

confidence: 99%

“…These periodic orbits also offer characteristic features to differentiate walking, stair ascent, and stair descent. A similar approach using A-ω features of the thigh angle demonstrated real-time activity classification with a 2-D feature space [25]. However, the features of these two methods also involved non-intuitive mathematical operations (e.g., coordinate transformations and Fast Fourier Transforms), which can be difficult for the user to understand and control.…”

Section: Introductionmentioning

confidence: 99%

“…We also consider different walking inclinations and speeds to be part of the same walking activity, which can be continuously parameterized by estimates of these parameters from the IMU and encoders on a prosthetic leg [28]. This paradigm results in a simpler (and more accurate) classification problem than many methods that differentiate ramps as discrete activities [7], [13], [16], [25]. We train and validate the main classifiers offline using supervised learning algorithms with a pre-recorded dataset of 10 able-bodied subjects performing different activities [30].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Activity Recognition With Instantaneous Characteristic Features of Thigh Kinematics

Cheng¹,

Bolívar

Gregg

2021

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Current supervised learning or deep learning-based activity recognition classifiers can achieve high accuracy in recognizing locomotion activities. Most available techniques use a high-dimensional space of features, e.g., combinations of EMG, kinematics and kinetics, and transformations over those signals.The associated classification rules are therefore complex; the machine tries to understand the human, but the human does not understand the machine. This paper presents an activity recognition system that uses signals from a thigh-mounted IMU and a force sensitive resistor to classify transitions between sitting, walking, stair ascending, and stair descending. The system uses the thigh's orientation and velocity with foot contact information at specific moments within a given activity as the features to classify transitions to other activities. We call these Instantaneous Characteristic Features (ICFs). Because these ICFs are biomechanically intuitive, they are easy for the user to understand and thus control the activity transitions of wearable robots. We assessed our classification algorithm offline using an existing dataset with 10 able-bodied subjects and online with another 10 able-bodied subjects wearing a real-time system. The offline study analyzed the effect of subject-dependency and ramp inclinations. The real-time classification accuracy was evaluated before and after training the subjects on the ICFs. The real-time system achieved overall pre-subject-training and post-subjecttraining error rates of 0.59% ± 0.24% and 0.56% ± 0.20%, respectively. We also evaluated the feasibility of our ICFs for amputee ambulation by analyzing a public dataset with the open-source bionic leg. The simplicity of these classification rules demonstrates a new paradigm for activity recognition where the human can understand the machine and vice-versa.

show abstract

Section: E Real-time Detection Of Mhf and Hsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Activity Recognition With Instantaneous Characteristic Features of Thigh Kinematics

Cheng¹,

Bolívar

Gregg

2021

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…In general, gait assistance exoskeletons need to generate force/torque according to the user’s lower-limb motion. Due to the multiple daily locomotion activities (such as walking, stair ascending/descending and crossing over obstacles), wearable sensors are introduced to detect the gait motion states [ 12 , 13 , 14 ]. In addition to the complex gait locomotion modes, individual differences also bring significant challenges to partial-assist exoskeletons for keeping synchronization with human movements.…”

Section: Introductionmentioning

confidence: 99%

Differential Soft Sensor-Based Measurement of Interactive Force and Assistive Torque for a Robotic Hip Exoskeleton

Wang

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

With the emerging of wearable robots, the safety and effectiveness of human-robot physical interaction have attracted extensive attention. Recent studies suggest that online measurement of the interaction force between the robot and the human body is essential to the aspects above in wearable exoskeletons. However, a large proportion of existing wearable exoskeletons monitor and sense the delivered force and torque through an indirect-measure method, in which the torque is estimated by the motor current. Direct force/torque measuring through low-cost and compact wearable sensors remains an open problem. This paper presents a compact soft sensor system for wearable gait assistance exoskeletons. The contact force is converted into a voltage signal by measuring the air pressure within a soft pneumatic chamber. The developed soft force sensor system was implemented on a robotic hip exoskeleton, and the real-time interaction force between the human thigh and the exoskeleton was measured through two differential soft chambers. The delivered torque of the hip exoskeleton was calculated based on a characterization model. Experimental results suggested that the sensor system achieved direct force measurement with an error of 10.3 ± 6.58%, and torque monitoring for a hip exoskeleton which provided an understanding for the importance of direct force/torque measurement for assistive performance. Compared with traditional rigid force sensors, the proposed system has several merits, as it is compact, low-cost, and has good adaptability to the human body due to the soft structure.

show abstract

“…Human motion recognition is a key technology for intelligent video surveillance. It is widely used in various scenarios such as human-computer interaction [1], motion analysis [2][3][4][5][6][7], intelligent monitoring, gesture recognition [8,9], and facial emotion recognition [10][11][12][13]. Human motion recognition is divided into single-person motion recognition and multi-person interactive motion recognition.…”

Section: Introductionmentioning

confidence: 99%

Human Interaction Recognition Based on Whole-Individual Detection

Zhong

Chang

et al. 2020

Sensors

View full text Add to dashboard Cite

Human interaction recognition technology is a hot topic in the field of computer vision, and its application prospects are very extensive. At present, there are many difficulties in human interaction recognition such as the spatial complexity of human interaction, the differences in action characteristics at different time periods, and the complexity of interactive action features. The existence of these problems restricts the improvement of recognition accuracy. To investigate the differences in the action characteristics at different time periods, we propose an improved fusion time-phase feature of the Gaussian model to obtain video keyframes and remove the influence of a large amount of redundant information. Regarding the complexity of interactive action features, we propose a multi-feature fusion network algorithm based on parallel Inception and ResNet. This multi-feature fusion network not only reduces the network parameter quantity, but also improves the network performance; it alleviates the network degradation caused by the increase in network depth and obtains higher classification accuracy. For the spatial complexity of human interaction, we combined the whole video features with the individual video features, making full use of the feature information of the interactive video. A human interaction recognition algorithm based on whole–individual detection is proposed, where the whole video contains the global features of both sides of action, and the individual video contains the individual detail features of a single person. Making full use of the feature information of the whole video and individual videos is the main contribution of this paper to the field of human interaction recognition and the experimental results in the UT dataset (UT–interaction dataset) showed that the accuracy of this method was 91.7%.

show abstract

A Two-Dimensional Feature Space-Based Approach for Human Locomotion Recognition

Cited by 20 publications

References 38 publications

Real-Time Activity Recognition With Instantaneous Characteristic Features of Thigh Kinematics

Real-Time Activity Recognition With Instantaneous Characteristic Features of Thigh Kinematics

Differential Soft Sensor-Based Measurement of Interactive Force and Assistive Torque for a Robotic Hip Exoskeleton

Human Interaction Recognition Based on Whole-Individual Detection

Contact Info

Product

Resources

About