Human Body Posture Estimation Method Research Articles

Application of Human Posture Recognition Based on the Convolutional Neural Network in Physical Training Guidance.

The application of sports game video analysis in athlete training and competition analysis feedback has attracted extensive attention, but the traditional sports human body posture estimation method has a large error between the athlete's human body posture estimation results and the actual results in the complex environment and the athlete's body parts are blocked. Therefore, this study proposes a convolutional neural network for athlete pose estimation in sports game video. Based on the improved model, multiscale model, and large perception model, a superimposed hourglass network is constructed, and the gradient disappearance problem of the convolutional neural network is solved using intermediate supervision. The experimental results show that the athlete pose estimation model based on the convolutional neural network can improve the accuracy of athlete pose estimation and reduce the negative impact of occlusion environment on athlete pose estimation to a certain extent. In addition, compared with other athletes' standing posture estimation methods, the model has competitive advantages and high accuracy under widely used standard conditions.

P-BIO-03 REMARKS ON HUMAN BODY POSTURE ESTIMATION FROM SILHOUETTE IMAGE USING 3D ARTICULATED HUMAN CG MODEL(Bio-medical Equipments,Technical Program of Poster Session)

This paper proposes a human body posture estimation method using a 3D articulated human body CG model. The estimation method is based on 2D matching between the human silhouettes extracted from camera images and the model silhouettes projected onto corresponded camera planes. The candidates of the human model silhouette is generated by using Monte Carlo filter and the XOR distance is introduced to calculate the likelihood rate between silhouettes. Experimental results confirmed the feasibility of the estimation method.

Markerless Human Motion Capture from Voxel Reconstruction with Simple Human Model

This paper investigates a human body posture estimation method based on the back projection of human silhouette images extracted from multi-camera images. The multi-camera system is based on a server-client system with local network of 1000Base-T to achieve a voxel 3D reconstruction of human body posture in real-time. In order to extract significant points of the human body such as head, neck, shoulders, elbow joints, hands, waist, knee joints, and toes in 3D, an articulated cylindrical human model is applied to the voxel reconstruction of human body. To evaluate the proposed human body posture estimation method, 3D reconstruction experiments of human body posture and extraction experiments of human body's significant points are carried out. The system runs in approximately real time (9 frames/sec with 50×50×50 voxel resolution) and the experimental results confirm both the feasibility and effectiveness of the proposed system in 3D human body posture estimation.

Remarks on Human Body Posture Estimation From Silhouette Image

This paper proposes a human body posture estimation method using neural network. The input feature vector of the neural network is composed with the result of analyzing a human silhouette extracted from camera image and the output vector of the neural network indicates the 2D coordinates of the human body's significant points. The proposed method is implemented on a personal computer and runs in real-time. Experimental results show the feasibility of the proposed method for estimating human body postures.

シルエット画像からのニューラルネットワークによる人物姿勢推定に関する一考察(情報・知能・精密機器II)

This paper proposes a human body posture estimation method using neural network. The input feature vector of the neural network is composed with the result of analyzing a human silhouette extracted from camera image and the output vector of the neural network indicates the 2D coordinates of the human body’s significant points. The proposed method is implemented on a personal computer and runs in real-time. Experimental results show both the feasibility and the effectiveness of the proposed method for estimating human body postures.

Real-Time Human Body Posture Estimation Using Neural Networks.

This paper proposes a real-time human body posture estimation method using ANNs. The network is composed of three ANNs and a decision logic unit. The ANNs’ input is the result of a function analysis on a human silhouette’s contour extracted from camera images and the ANNs’ output indicates the feature points’ positions on the contour. The decision logic unit synthesizes each of the ANNs’ output vectors and then the 2D coordinates of the human body’s feature points are calculated. The proposed method is implemented on a personal computer and runs in real-time (17-20 frames/sec). Experimental results confirm both the feasibility and the effectiveness of the proposed method for estimating human body postures. By applying the proposed estimation method to a stereo vision system, real-time 3D human body posture estimation can also be achieved.

Remarks on a real‐time, noncontact, nonwear, 3D human body posture estimation method

Remarks on a real‐time, noncontact, nonwear, 3D human body posture estimation method

Remarks on a real-time, noncontact, nonwear, 3D human body posture estimation method

This paper proposes a new real-time method of estimating human postures in three dimensions from trinocular images. The proposed method extracts feature points of the human body by analyzing contours of human silhouettes. The feature points are extracted by using the subtraction images when self-occlusions occur in the silhouette images. Dynamic compensation is carried out with a Kalman filter so that all feature points are tracked. The 3D coordinates of the feature points are reconstructed by considering the geometrical relationship between the three cameras. Experimental results confirm both the feasibility and the effectiveness of the proposed method. © 2000 Scripta Technica, Syst Comp Jpn, 31(14): 1–10, 2000