A Key Pose Frame Extraction Approach Combined with Trajectory from Weightlifting Video

A Key Pose Frame Extraction Approach Combined with Trajectory from Weightlifting Video

Abstract: In this paper, a trajectory guided scheme is proposed to extract the key poses#br# frame automatically. First, the barbell trajectory is extracted from the weight lifting sport video.#br# Then the barbell trajectory and poselet are combined for pose extraction. Some key poses are#br# extracted from the extreme point of the barbell trajectory. But the other poses are extracted by#br# using the poselet based algorithm. SVM(Support Vector Machine) classifiers based#br# HOG(Histogram of Gradient) is trained for each pose. Then the pose is detected in the multi-scale#br# images. Statistical similarity is computed in multi-scale to measure the possibility and determine#br# which is the best key frame. It resolves the problem of higher inter-frame similarity. The#br# experimental results show that the proposed scheme can improve both the precision and#br# performance of pose extraction.#br# Key words: trajectory; pose; key frame; support vector machine

Online:2015-04-30 Published:2015-03-30

Abstract

Abstract: In this paper, a trajectory guided scheme is proposed to extract the key poses
frame automatically. First, the barbell trajectory is extracted from the weight lifting sport video.
Then the barbell trajectory and poselet are combined for pose extraction. Some key poses are
extracted from the extreme point of the barbell trajectory. But the other poses are extracted by
using the poselet based algorithm. SVM(Support Vector Machine) classifiers based
HOG(Histogram of Gradient) is trained for each pose. Then the pose is detected in the multi-scale
images. Statistical similarity is computed in multi-scale to measure the possibility and determine
which is the best key frame. It resolves the problem of higher inter-frame similarity. The
experimental results show that the proposed scheme can improve both the precision and
performance of pose extraction.

Key words: trajectory, pose, key frame, support vector machine

Wang Xiangdong, Zhang Jingwen, Wu Lifang, Xu Wenquan. A Key Pose Frame Extraction Approach Combined with Trajectory from Weightlifting Video[J]. Journal of Graphics.

[1]	CAI Xing-quan, HUO Yu-qing, LI Fa-jian, SUN Hai-yan. Human pose estimation and similarity calculation for Tai Chi learning [J]. Journal of Graphics, 2022, 43(4): 695-706.
[2]	HUANG Jie, WEI Xin, YANG Zi-yuan, MIN Wei-dong. Finger-knuckle-print recognition based on multi-dimensional matching distances fusion [J]. Journal of Graphics, 2022, 43(2): 279-287.
[3]	LIU Yu-jie, ZHANG Min-jie, LI Zong-min, LI Hua. Lightweight human pose estimation with global pose perception [J]. Journal of Graphics, 2022, 43(2): 333-341.
[4]	REN Hao-pan, WANG Wen-ming, WEI De-jian, GAO Yan-yan, KANG Zhi-hui, WANG Quan-yu. Human pose estimation based on high-resolution net [J]. Journal of Graphics, 2021, 42(3): 432-438.
[5]	XU Shi-pu, LI Lin-yi, JIA Jin-yuan, WANG Yun-sheng, LIU Chang, LIU Yong, MA Chao . AR-assisted intelligent analysis and identification system for mobile rice diseases based on HOG-SVM [J]. Journal of Graphics, 2021, 42(3): 454-461.
[6]	LI Jun , YANG Ya-zhi. Locally adjusted age estimation based on deep learning and directed acyclic graph SVM [J]. Journal of Graphics, 2021, 42(1): 1-7.
[7]	LIU Chang, XU Chao-yuan, ZHANG Xin, XUE Lei. A combined classifier based on CNN and SVM for LCD character recognition [J]. Journal of Graphics, 2021, 42(1): 15-22.
[8]	SU Peng, LU Da , LUN Qing-long , LI Jian , XU Xiao-zhong , FAN Yu-bo, . Design of aided mechanism configuration for human body turning-over based on motion trajectory fitting [J]. Journal of Graphics, 2020, 41(6): 993-1000.
[9]	LI Gui, LI Teng. Pose-guided scene-preserving person video generation algorithm [J]. Journal of Graphics, 2020, 41(4): 539-547.
[10]	SHI Zhi-liang, ZHANG Peng-fei, LI Xiao-yao. Classification of engine main bearing cap parts using SIFT-SVM method [J]. Journal of Graphics, 2020, 41(3): 390-398.
[11]	LIU Tao1, WANG Ning-ning1, ZHANG Yi1, AI Shang-mao2 . Three-Dimensional Trajectory Visual Measurement Method for Underwater Moving Objects [J]. Journal of Graphics, 2019, 40(5): 908-914.
[12]	CHEN Guo-jun, YANG Jing, CHENG Yan, YIN Peng . Real-Time Head Pose Estimation Based on RGBD [J]. Journal of Graphics, 2019, 40(4): 681-688.
[13]	CHEN Guo-jun, CHENG Yan, CAO Yue, LI Sheng . Plant Depth Maps Recovery Based on Target Features [J]. Journal of Graphics, 2019, 40(3): 460-465.
[14]	SU Peng1, YIN Meng-xiao1,2, WANG Yu-pan3, HAN Yan-ru1, YANG Feng1,2, LI Gui-qing3 . Spectral Pose Transfer Based on Deformation Graph [J]. Journal of Graphics, 2019, 40(2): 282-289.
[15]	LI Qi1,2, YANG Wen-hao3, HOU Ya-li4, WANG Xiang-dong4, LI Hua1,2 . Trajectory Modeling in Short Track Speed Skating [J]. Journal of Graphics, 2019, 40(1): 8-14.

A Key Pose Frame Extraction Approach Combined with Trajectory from Weightlifting Video

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments