A visual servo robot for pose estimation

doi:10.13474/j.cnki.11-2246.2020.0244

Abstract

Abstract: In order to solve the problem of people's non-standard pose and unsupervised guidance, a visual servo robot for pose estimation is designed in this paper. The robot tracks the moving target through a target tracking algorithm with attention mechanism, and works with the robot's servo motor structure to adjust the camera angle, so as to track and record the moving target in a specific area. Then, the target pose is extracted by robot's pose evaluation system and compared with the standard pose. It has been verified that the robot has a high degree of discrimination of the quality of the human pose, and can effectively evaluate the user's pose, so as to achieve the purpose of sports assistance and rehabilitation training guidance.

Key words: visual servo, object tracking, spatial attention mechanism, pose estimation, sports assistance

CLC Number:

P237

HU Jianlang, LUO Yarong, GUO Chi. A visual servo robot for pose estimation[J]. Bulletin of Surveying and Mapping, 2020, 0(8): 33-38.

References

[1] PIWEK L, ELLIS D A, ANDREWS S, et al. The Rise of consumer health wearables:promises and barriers[J]. PLOS Medicine, 2016, 13(2):1-6.
[2] 李少聪,马德,李少琼.运动损伤与运动强度的关系建模仿真分析[J].现代电子技术,2017,40(24):37-39.
[3] 杨桂其,史传华,朱小军,等.大学生体育运动损伤的预防与处理[J].体育世界(学术版),2018(11):176,171.
[4] ZHOU X, COLLINS R T, KANADE T, et al. A master-slave system to acquire biometric imagery of humans at distance[C]//Proceedings of the 1st ACM SIGMM International Workshop on Video Surveillance. New York:ACM, 2003:113-120.
[5] GHIDONI S, PRETTO A, MENEGATTI E. Cooperative tracking of moving objects and face detection with a dual camera sensor[C]//Proceedings of 2010 IEEE International Conference on Robotics and Automation. Piscataway:IEEE, 2010:2568-2573.
[6] PAN K Y, CHUANG Y Y. Continuous zoom with two fixed-focal-length lens[C]//Proceedings of SIGGRAPH ASIA 2016 Posters. New York:ACM, 2016:14.
[7] ZHANG H, DONG W, GUO C, et al. A visual servo control system combining parallel structure with dual-lens zoom[J]. International Journal of Robotics and Automation, 2019, 34(6):244-251.
[8] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2010:2544-2550.
[9] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE transactions on pattern analysis and machine intelligence, 2014, 37(3):583-596.
[10] WANG N, YEUNG D Y. Learning a deep compact image representation for visual tracking[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Cambridge, Commonwealth of Massachusetts:MIT Press, 2013:809-817.
[11] 鲁凯翔,田鹏辉,隋立春.基于二维灰度直方图的均值漂移红外运动目标跟踪[J].测绘通报,2014(3):29-31.
[12] 王宇鹏.网球训练机器人中人体动作实时评估算法及其实现[D].北京:北京邮电大学,2018:19-28.
[13] 张梦营.基于Kinect的电子瑜伽教学系统的研究与实现[D].哈尔滨:黑龙江大学,2017:26-38.
[14] 张利英.基于Kinect运动捕捉的太极拳辅助训练系统研究[D].石家庄:河北科技大学,2016:27-46.
[15] 郑轩宇,史畅,崔文成.基于Kinect的运动训练辅助系统[J].计算机与现代化,2019(8):12-16,56.
[16] 谢蕾.基于目标跟踪算法的高尔夫挥杆分析系统研制[D].北京:北京邮电大学,2015:17-18.
[17] 陈学梅.基于人体三维姿态的动作评价系统[D].杭州:浙江大学,2018:56-57.
[18] CAO Z, SIMON T, WEI S E, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:7291-7299.
[19] PAVLLO D, FEICHTENHOFER C, GRANGIER D, et al. 3D human pose estimation in video with temporal convolutions and semi-supervised training[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2019:7753-7762.