A New Framework of Human Interaction Recognition Based on Multiple Stage Probability Fusion

Ji, Xiaofei; Wang, Changhui; Ju, Zhaojie

doi:10.3390/app7060567

Cited by 15 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, occlusions are not considered in this research. Ji et al [19] deals with the existing problems in the interaction recognition algorithms such as imprecise feature descriptors induced by incorrect segmentation of the human body. To deal with this problem, a multi-stage probability fusion method is proposed.…”

Section: A Vision Sensor-based Rplb Analysismentioning

confidence: 99%

Monitoring Real-Time Personal Locomotion Behaviors Over Smart Indoor-Outdoor Environments Via Body-Worn Sensors

et al. 2021

View full text Add to dashboard Cite

The monitoring of human physical activities using wearable sensors, such as inertial-based sensors, plays a significant role in various current and potential applications. These applications include physical health tracking, surveillance systems, and robotic assistive technologies. Despite the wide range of applications, classification and recognition of human activities remains imprecise and this may contribute to unfavorable reactions and responses. To improve the recognition of human activities, we designed a dataset in which ten participants (five male and five female) performed 11 different activities wearing three bodyworn inertial sensors in different locations on the body. Our model extracts data via a hierarchical featurebased technique. These features include time, wavelet, and time-frequency domains, respectively. Stochastic gradient descent (SGD) is then introduced to optimize selective features. The selected features with optimized patterns are further processed by multi-layered kernel sliding perceptron to develop adaptive learning for the classification of physical human activities. Our proposed model was experimentally evaluated and applied on three benchmark datasets: IM-WSHA, a self-annotated dataset, PAMAP2 dataset which is comprised of daily living activities, and an HuGaDB, a dataset which contains physical activities for aging people. The experimental results show that the proposed method achieves better results and outperforms others in terms of recognition accuracy, achieving an accuracy rate of 83.18%, 94.16%, and 92.50% respectively, when IM-WSHA, PAMAP2, and HuGaDB datasets are applied.INDEX TERMS body-worn sensors, kernel sliding perceptron, real-time personal locomotion behaviors (RPLB), stochastic gradient descent

show abstract

Section: A Vision Sensor-based Rplb Analysismentioning

confidence: 99%

Monitoring Real-Time Personal Locomotion Behaviors Over Smart Indoor-Outdoor Environments Via Body-Worn Sensors

et al. 2021

View full text Add to dashboard Cite

show abstract

“…They used multinomial kernel logistic regression to evaluate HIR using Set I of UT-Interaction dataset. In [ 43 ], X. Ji et al presented a vision based HIR system using multiple stage probability fusion. They divided interaction between two persons into the start state, execution state and the end state.…”

Section: Related Workmentioning

confidence: 99%

Automatic Recognition of Human Interaction via Hybrid Descriptors and Maximum Entropy Markov Model Using Depth Sensors

Jalal

Khalid

Kim

2020

Entropy

108

View full text Add to dashboard Cite

Automatic identification of human interaction is a challenging task especially in dynamic environments with cluttered backgrounds from video sequences. Advancements in computer vision sensor technologies provide powerful effects in human interaction recognition (HIR) during routine daily life. In this paper, we propose a novel features extraction method which incorporates robust entropy optimization and an efficient Maximum Entropy Markov Model (MEMM) for HIR via multiple vision sensors. The main objectives of proposed methodology are: (1) to propose a hybrid of four novel features—i.e., spatio-temporal features, energy-based features, shape based angular and geometric features—and a motion-orthogonal histogram of oriented gradient (MO-HOG); (2) to encode hybrid feature descriptors using a codebook, a Gaussian mixture model (GMM) and fisher encoding; (3) to optimize the encoded feature using a cross entropy optimization function; (4) to apply a MEMM classification algorithm to examine empirical expectations and highest entropy, which measure pattern variances to achieve outperformed HIR accuracy results. Our system is tested over three well-known datasets: SBU Kinect interaction; UoL 3D social activity; UT-interaction datasets. Through wide experimentations, the proposed features extraction algorithm, along with cross entropy optimization, has achieved the average accuracy rate of 91.25% with SBU, 90.4% with UoL and 87.4% with UT-Interaction datasets. The proposed HIR system will be applicable to a wide variety of man–machine interfaces, such as public-place surveillance, future medical applications, virtual reality, fitness exercises and 3D interactive gaming.

show abstract

“…Wearable data gloves are not only inconvenient to use, and shifts in the data glove can easily cause errors in the system [ 1 , 3 ]. The vision-based gesture interaction method, in addition to certain requirements for light and background, are of relatively high computational complexity, perform poorly in real-time, and have other shortcomings in terms of target recognition and processing; for example, very complex feature representations and inaccurate feature extractions caused by incorrect human segmentation [ 6 ]. For an accuracy of 90% or higher, the average processing time is longer than 30 ms [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

Real-Time Hand Position Sensing Technology Based on Human Body Electrostatics

Tang

Wang

et al. 2018

Sensors

View full text Add to dashboard Cite

Non-contact human-computer interactions (HCI) based on hand gestures have been widely investigated. Here, we present a novel method to locate the real-time position of the hand using the electrostatics of the human body. This method has many advantages, including a delay of less than one millisecond, low cost, and does not require a camera or wearable devices. A formula is first created to sense array signals with five spherical electrodes. Next, a solving algorithm for the real-time measured hand position is introduced and solving equations for three-dimensional coordinates of hand position are obtained. A non-contact real-time hand position sensing system was established to perform verification experiments, and the principle error of the algorithm and the systematic noise were also analyzed. The results show that this novel technology can determine the dynamic parameters of hand movements with good robustness to meet the requirements of complicated HCI.

show abstract

A New Framework of Human Interaction Recognition Based on Multiple Stage Probability Fusion

Cited by 15 publications

References 26 publications

Monitoring Real-Time Personal Locomotion Behaviors Over Smart Indoor-Outdoor Environments Via Body-Worn Sensors

Monitoring Real-Time Personal Locomotion Behaviors Over Smart Indoor-Outdoor Environments Via Body-Worn Sensors

Automatic Recognition of Human Interaction via Hybrid Descriptors and Maximum Entropy Markov Model Using Depth Sensors

Real-Time Hand Position Sensing Technology Based on Human Body Electrostatics

Contact Info

Product

Resources

About