Point cloud human posture estimation using single RGB image

Singu, Poojitha; Lakshmi, V. S. Ramya; Raajan, N. R.

doi:10.1016/j.matpr.2020.06.247

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, it can provide technical support for human-computer interaction. Poojitha Sing obtained data of various components of each parts of the human body by measuring the point cloud data of human posture in RGB images, which avoids the ambiguity of features and thus shows better detection performance [2]. Xinwei Li estimated the human joint moment by analyzing the dynamic human-computer interaction between the human elbow torque and the exoskeleton output [3].…”

Section: Related Workmentioning

confidence: 99%

Research on Methods of Physical Aided Education Based on Deep Learning

Su¹,

Feng

2022

Scientific Programming

View full text Add to dashboard Cite

In order to better meet the training needs of sports and improve the standardization of sports training, an openpose-based sports posture estimation method and assisted training system are proposed, combining the basic structure and principle of openpose network. Firstly, the human posture estimation algorithm is constructed by combining with the openpose network; secondly, the overall framework, specific operation process, image acquisition, posture estimation, and other modules of the sports assistance system are designed in detail; finally, the openpose posture estimation method constructed above is validated. The results show that the value of the loss function obtained by the algorithm gradually stabilizes after 250 iterations. By using the COCO dataset as the training base and comparing it with the standard posture, it is found that the algorithm can correctly identify different badminton action postures, and the recognition rate can reach up to 94%. This shows that the algorithm is feasible and can be used for posture estimation and training of badminton sports movements.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on Methods of Physical Aided Education Based on Deep Learning

Su¹,

Feng

2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…human-robot motion mapping [1][2][3], health rehabilitation image data. Singu et al [11] used RGB images, measurement point clouds, and convolutional neural networks to recognize human-postures. Visual detection requires high frame rate image acquisition system, and a large number of algorithms will amplify the estimated noise.…”

Section: Introductionmentioning

confidence: 99%

Optical fiber Bragg grating based sensing system of flexible wearable smart sleeve for tracking human arm joint movements

Feng

Wang

Liu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Optical fiber Bragg sensor (FBG) has great potential in the field of flexible wearable device for tracking human gestures. Due to the different human size, different wearable tensions cause errors inevitably during tracking joint movements. We have designed a flexible wearable smart sleeve with four heads of FBG and spandex polyurethane fibers. The spandex polyurethane fibers sewed with the Optical fiber Bragg sensor (FBG) has great potential in the field of flexible wearable device for tracking human gestures. Due to the different human size, different wearable tensions cause errors inevitably during tracking arm joint movements. We have designed a flexible wearable smart sleeve with four heads of FBG and spandex polyurethane fibers. The spandex polyurethane fibers sewed with the flexible fabric sleeve convert the elbow yawing, wrist pitching and rolling into the axial strain of FBG. The measuring system has been developed to deduce the personalized sensitivity by a dynamic calibration method. For a male and a female, the dynamic calibration, verification and tracking tests were carried out. From the male’s experimental data, the relative errors between the verification sensitivity and the personalized sensitivity are 1.93%, 5.85% and 7.16%, and the average relative errors between the tracking sensitivity and the personalized sensitivity are 7.09%, 5.58% and 2.52%, respectively. And from the data of the female’s experiment, the relative errors between the verification sensitivity and the personalized sensitivity are 0.25%, 5.0% and 6.75%, and the average relative errors between the tracking sensitivity and the personalized sensitivity are 0.99%, 5.56% and 6.95%, respectively. The experimental data have showed this wearable smart sleeve and the measuring system work well. The research results can be used to develop FBG sensing system of monitoring joint movements for different human size on-line.

show abstract

Estimation for Human Motion Posture and Health Using Improved Deep Learning and Nano Biosensor

Zhu

2023

Int J Comput Intell Syst

View full text Add to dashboard Cite

To improve the technical level of human motion posture and health estimation, a human motion posture and health estimation algorithm based on Nano biosensor and improved deep learning is proposed. First, we use Nano biological acceleration sensor and Nano biological angular velocity sensor to obtain human motion posture and health data. Second, after the fusion processing of human motion posture and health data, we use the motion posture coordinate system conversion unit and the physiological information recognition unit to convert the coordinate system of human motion angular velocity and acceleration data and recognize the physiological information of blood pressure and heart rhythm. Finally, the convolution neural networks (CNN) in deep learning is improved to obtain the deformable CNN. The transformed angular velocity, physiological information recognition results and other human posture data are input into the deformable CNN, and the human posture estimation results are output. Experiments show that proposed algorithm can accurately obtain human posture data, can quickly and accurately estimate human posture, and has a good application effect. It has important application value in identity recognition and sports performance analysis.

show abstract

Point cloud human posture estimation using single RGB image

Cited by 3 publications

References 8 publications

Research on Methods of Physical Aided Education Based on Deep Learning

Research on Methods of Physical Aided Education Based on Deep Learning

Optical fiber Bragg grating based sensing system of flexible wearable smart sleeve for tracking human arm joint movements

Estimation for Human Motion Posture and Health Using Improved Deep Learning and Nano Biosensor

Contact Info

Product

Resources

About