深度学习的二维人体姿态估计综述

doi:10.3778/j.issn.1673-9418.2008088

摘要/Abstract

摘要：

近年来人体姿态估计作为计算机视觉领域的热点，在视频监控、人机交互、智慧校园等领域具有广泛的应用前景。随着神经网络的快速发展，采用深度学习方法进行二维人体姿态估计，相较于传统需要人工设定特征的方法，更能充分地提取图像信息，获取更具有鲁棒性的特征，因此基于深度学习的方法已成为二维人体姿态估计算法研究的主流方向。然而，深度学习尚在发展中，仍存在训练规模大等问题，研究者们主要从设计网络以及训练方式入手对人体姿态估计算法进行改进。首先，将二维人体姿态估计分为单人与多人两大类进行论述；根据真值类型不同将单人姿态估计分为基于坐标回归与基于热图检测两类，根据算法步骤不同将多人姿态估计分为二步法与一步法两类，对近年来先进的算法进行总结分类介绍，并分析它们的优缺点以及适用范围；然后，介绍了相关的国际标准数据集以及相应的评价指标，并对几种经典算法进行实验数据对比；最后，对当前研究所存在的问题以及未来发展趋势进行了总结概述。

关键词: 人体姿态估计, 深度学习, 神经网络, 关节点检测

Abstract:

In recent years, as a hot spot in the field of computer vision, human pose estimation has broad application prospects in video surveillance, human-computer interaction, and intelligent campus. With the rapid development of neural networks, the use of deep learning methods for 2D human pose estimation, compared with traditional methods that require manual setting of features, can more fully extract image information, and obtain more robust characteristics, so deep learning based methods have become the mainstream of 2D human pose estimation algorithm research. However, deep learning is still developing, there are still problems such as large training scale, and researchers mainly start with designing networks and training methods to improve the human pose estimation algorithm. Fristly, the two-dimensional human pose estimation is divided into two categories: single person and multiple persons. Secondly, single-person pose estimation is divided into coordinate regression and heat map detection according to different ground truth types, and multi-person pose estimation is divided into two-step and single-step method according to different algorithm steps, to summarize and classify the advanced algorithms in recent years, and their advantages and disadvantages as well as scope of application are analyzed. Then, the international standard datasets and the corresponding evaluation indices are introduced, and some classical algorithms are compared experimentally. Finally, the current research problems and the future development trends are summarized.

Key words: human pose estimation, deep learning, neural networks, joints detection

周燕, 刘紫琴, 曾凡智, 周月霞, 陈嘉文, 罗粤. 深度学习的二维人体姿态估计综述[J]. 计算机科学与探索, 2021, 15(4): 641-657.

ZHOU Yan, LIU Ziqin, ZENG Fanzhi, ZHOU Yuexia, CHEN Jiawen, LUO Yue. Survey on Two-Dimensional Human Pose Estimation of Deep Learning[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(4): 641-657.

参考文献

[1] WANG X W, XIE L B, PENG L. Double residual network recognition method for falling abnormal behavior[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(9): 1580-1589.
王新文, 谢林柏, 彭力. 跌倒异常行为的双重残差网络识别方法[J]. 计算机科学与探索, 2020, 14(9): 1580-1589.
[2] ZHANG R P, YU Y X, ZHANG K, et al. Research on human action recognition model based on OI-LSTM neural network structure[J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(12): 1926-1939.
张儒鹏, 于亚新, 张康, 等. 基于OI-LSTM神经网络结构的人类动作识别模型研究[J]. 计算机科学与探索, 2018, 12(12): 1926-1939.
[3] SONG Y F, ZHANG P, LIU L B. Human-machine interaction system with vision-based gesture recognition[J]. Computer Science, 2019, 46(S2): 570-574.
宋一凡, 张鹏, 刘立波. 基于视觉手势识别的人机交互系统[J]. 计算机科学, 2019, 46(S2): 570-574.
[4] INSAFUTDINOV E, ANDRILUKA M, PISHCHULIN L, et al. ArtTrack: articulated multi-person tracking in the wild[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1293-1301.
[5] MA M, LI Y B, WU X Q, et al. Human pose tracking based on multi-feature fusion in videos[J]. Journal of Image and Graphics, 2020, 25(7): 1459-1472.
马淼, 李贻斌, 武宪青, 等. 视频中多特征融合人体姿态跟踪[J]. 中国图象图形学报, 2020, 25(7): 1459-1472.
[6] FISCHLER M A, ELSCHLAGER R A. The representation and matching of pictorial structures[J]. IEEE Transactions on Computers, 1973, 22(1): 67-92.
[7] FELZENSZWALB P F, HUTTENLOCHER D P. Pictorial structures for object recognition[J]. International Journal of Computer Vision, 2005, 61(1): 55-79.
[8] YANG Y, RAMANAN D. Articulated pose estimation with flexible mixtures-of-parts[C]//Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, Jun 20-25, 2011. Washington: IEEE Com-puter Society, 2011: 1385-1392.
[9] JOHNSON S, EVERINGHAM M. Learning effective human pose estimation from inaccurate annotation[C]//Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, Jun 20-25, 2011. Washing-ton: IEEE Computer Society, 2011: 1465-1472.
[10] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the 2005 IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition, San Diego, Jun 20-26, 2005. Washington: IEEE Computer Society, 2005: 886-893.
[11] LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the 1999 International Confer-ence on Computer Vision, Kerkyra, Sep 20-25, 1999. Wash-ington: IEEE Computer Society, 1999: 1150-1157.
[12] EICHNER M, FERRARI V. We are family: joint pose estima-tion of multiple persons[C]//LNCS 6311: Proceedings of the 11th European Conference on Computer Vision, Heraklion, Sep 5-11, 2010. Berlin, Heidelberg: Springer, 2010: 228-242.
[13] TOSHEV A, SZEGEDY C. DeepPose: human pose estima-tion via deep neural networks[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recogni-tion, Columbus, Jun 23-28, 2014. Washington: IEEE Com-puter Society, 2014: 1653-1660.
[14] KRIZHEVSKY A, SUTSKEVER I, HINTON G E, et al. ImageNet classification with deep convolutional neural net-works[C]//Proceedings of the 26th Annual Conference on Neural Information Processing Systems, Lake Tahoe, Dec 3-6, 2012. Red Hook: Curran Associates, 2012: 1097-1105.
[15] CARREIRA J, AGRAWAL P, FRAGKIADAKI K, et al. Human pose estimation with iterative error feedback[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 4733-4742.
[16] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with con-volutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-12, 2015. Washington: IEEE Computer Society, 2015: 1-9.
[17] SUN X, SHANG J, LIANG S, et al. Compositional human pose regression[C]//Proceedings of the 2017 IEEE Interna-tional Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 2621-2630.
[18] TOMPSON J, JAIN A, LECUN Y, et al. Joint training of a convolutional network and a graphical model for human pose estimation[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2014, Montreal, Dec 8-13, 2014. Red Hook: Curran Associates, 2014: 1799-1807.
[19] JAIN A, TOMPSON J, ANDRILUKA M, et al. Learning human pose estimation features with convolutional networks [C]//Proceedings of the 2nd International Conference on Learning Representations, Banff, Apr 14-16, 2014: 1-14.
[20] TOMPSON J, GOROSHIN R, JAIN A, et al. Efficient ob-ject localization using convolutional networks[C]//Proceed-ings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-12, 2015. Washington: IEEE Computer Society, 2015: 648-656.
[21] ISACK H, HAENE C, KESKIN C, et al. RePose: learning deep kinematic priors for fast human pose estimation[J]. arXiv:2002.03933, 2020.
[22] YANG W, OUYANG W, LI H, et al. End-to-end learning of deformable mixture of parts and deep convolutional neural networks for human pose estimation[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Re-cognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 3073-3082.
[23] LAFFERTY J, MCCALLUM A, PEREIRA F, et al. Condi-tional random fields: probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning, Williamstown, Jun 28-Jul 1, 2001. San Mateo: Morgan Kaufmann, 2001: 282-289.
[24] WEI S E, RAMAKRISHNA V, KANADE T, et al. Convolu-tional pose machines[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 4724-4732.
[25] RAMAKRISHNA V, MUNOZ D, HEBERT M, et al. Pose machines: articulated pose estimation via inference machines [C]//LNCS 8690: Proceedings of the 13th European Con-ference on Computer Vision, Zurich, Sep 6-12, 2014. Berlin, Heidelberg: Springer, 2014: 33-47.
[26] NEWELL A, YANG K, DENG J, et al. Stacked hourglass networks for human pose estimation[C]//LNCS 9912: Pro-ceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Berlin, Heidelberg: Springer, 2016: 483-499.
[27] LONG J, SHELHAMER E, DARRELL T, et al. Fully con-volutional networks for semantic segmentation[C]//Proceed-ings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, Jun 7-12, 2015. Washington: IEEE Computer Society, 2015: 3431-3440.
[28] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learn-ing for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 770-778.
[29] CHU X, YANG W, OUYANG W L, et al. Multi-context attention for human pose estimation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 5669-5678.
[30] YANG W, LI S, OUYANG W L, et al. Learning feature pyr-amids for human pose estimation[C]//Proceedings of the 2017 International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 1290-1299.
[31] KE L P, CHANG M C, QI H G, et al. Multi-scale structure-aware network for human pose estimation[C]//LNCS 11206: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Berlin, Heidelberg: Springer, 2018: 731-746.
[32] NING G, ZHANG Z, HE Z, et al. Knowledge-guided deep fractal neural networks for human pose estimation[J]. IEEE Transactions on Multimedia, 2018, 20(5): 1246-1259.
[33] SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, Feb 4-9, 2017. Menlo Park: AAAI, 2016: 4278-4284.
[34] ZHANG F, ZHU X T, YE M, et al. Fast human pose estima-tion[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 3517-3526.
[35] BULAT A, KOSSAIFI J, TZIMIROPOULOS G, et al. Toward fast and accurate human pose estimation via soft-gated skip connections[J]. arXiv:2002.11098, 2020.
[36] RONNEBERGER O, FISCHER P, BROX T, et al. U-Net: convolutional networks for biomedical image segmentation[C]//LNCS 9351: Proceedings of the 18th International Con-ference on Medical Image Computing and Computer Assisted Intervention, Munich, Oct 5-9, 2015. Berlin, Heidelberg: Springer, 2015: 234-241.
[37] BELAGIANNIS V, ZISSERMAN A. Recurrent human pose estimation[C]//Proceedings of the 12th IEEE International Conference on Automatic Face & Gesture Recognition, Washington, May 30-Jun 3, 2017. Washington: IEEE Com-puter Society, 2017: 468-475.
[38] CHEN Y, SHEN C H, WEI X S, et al. Adversarial PoseNet: a structure-aware convolutional network for human pose estimation[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 1221-1230.
[39] SALIMANS T, GOODFELLOW I, ZAREMBA W, et al. Improved techniques for training GANs[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2016, Barcelona, Dec 5-10, 2016. Red Hook: Curran Associates, 2016: 2234-2242.
[40] CHOU C J, CHIEN J T, CHEN H T, et al. Self adversarial training for human pose estimation[C]//Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Honolulu, Nov 12-15, 2018. Piscataway: IEEE, 2018: 17-30.
[41] WU C M, HU J H, YIN J H. Using improved generative adversarial network for human pose estimation[J]. Com-puter Engineering and Applications, 2020, 56(8): 96-103.
吴春梅, 胡军浩, 尹江华. 利用改进生成对抗网络进行人体姿态识别[J]. 计算机工程与应用, 2020, 56(8): 96-103.
[42] XIAO B, WU H P, WEI Y C, et al. Simple baselines for human pose estimation and tracking[C]//LNCS 11210: Pro-ceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Berlin, Heidelberg: Springer, 2018: 472-487.
[43] SUN K, XIAO B, LIU D, et al. Deep high-resolution re-presentation learning for human pose estimation[C]//Pro-ceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 5693-5703.
[44] PFISTER T, CHARLES J, ZISSERMAN A, et al. Flowing ConvNets for human pose estimation in videos[C]//Pro-ceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 1913-1921.
[45] SIMONYAN K, ZISSERMAN A. Two-stream convolu-tional networks for action recognition in videos[C]//Pro-ceedings of the Annual Conference on Neural Information Processing Systems 2014, Montreal, Dec 8-13, 2014. Red Hook: Curran Associates, 2014: 568-576.
[46] LUO Y, REN J S J, WANG Z X, et al. LSTM pose machines[C]//Proceedings of the 2018 IEEE Conference on Com-puter Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 5207-5215.
[47] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[48] ARTACHO B, SAVAKIS A. UniPose: unified human pose est-imation in single images and videos[J]. arXiv:2001.08095, 2020.
[49] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2015, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 91-99.
[50] HE K M, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of the 2017 IEEE International Confer-ence on Computer Vision, Venice, Oct 22-29, 2017. Wash-ington: IEEE Computer Society, 2017: 2980-2988.
[51] LIN T Y, DOLLáR P, GIRSHICK R B, et al. Feature pyr-amid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 936-944.
[52] IQBAL U, GALL J. Multi-person pose estimation with local joint-to-person associations[C]//LNCS 9914: Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 8-10 and 15-16, 2016. Berlin, Heidelberg: Springer, 2016: 627-642.
[53] FANG H S, XIE S Q, TAI Y W, et al. RMPE: regional multi-person pose estimation[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 2353-2362.
[54] PAPANDREOU G, ZHU T, KANAZAWA N, et al. Towards accurate multi-person pose estimation in the wild[C]//Pro-ceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Wash-ington: IEEE Computer Society, 2017: 3711-3719.
[55] LI J F, WANG C, ZHU H, et al. CrowdPose: efficient crowded scenes pose estimation and a new benchmark[C]// Proceedings of the 2019 IEEE/CVF Conference on Com-puter Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 10863-10872.
[56] ZHANG J, CHEN Z, TAO D. Towards high performance human keypoint detection[J]. arXiv:2002.00537, 2020.
[57] CHEN Y, WANG Z, PENG Y, et al. Cascaded pyramid net-work for multi-person pose estimation[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington:IEEE Computer Society, 2018: 7103-7112.
[58] PISHCHULIN L, INSAFUTDINOV E, TANG S, et al. Deep-Cut: joint subset partition and labeling for multi-person pose estimation[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 4929-4937.
[59] GIRSHICK R B. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision, San-tiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 1440-1448.
[60] INSAFUTDINOV E, PISHCHULIN L, ANDRES B, et al. DeeperCut: a deeper, stronger, and faster multi-person pose estimation model[C]//LNCS 9910: Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Berlin, Heidelberg: Springer, 2016: 34-50.
[61] CAO Z, SIMON T, WEI S, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1302-1310.
[62] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the 3rd International Conference on Learning Repre-sentations, San Diego, May 7-9, 2015: 1-14.
[63] NEWELL A, HUANG Z, DENG J, et al. Associative embed-ding: end-to-end learning for joint detection and grouping[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2017, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 2277-2287.
[64] SEKII T. Pose proposal networks[C]//LNCS 11217: Pro-ceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Berlin, Heidelberg: Springer, 2018: 350-366.
[65] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 6517-6525.
[66] PAPANDREOU G, ZHU T, CHEN L, et al. PersonLab: per-son pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model[C]//LNCS 11218: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Berlin, Heidelberg: Springer, 2018: 282-299.
[67] OSOKIN D. Real-time 2D multi-person pose estimation on CPU: lightweight OpenPose[C]//Proceedings of the 8th In-ternational Conference on Pattern Recognition Applications and Methods, Prague, Feb 19-21, 2019. SciTePress, 2019: 744-748.
[68] HOWARD A, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applica-tions[J]. arXiv:1704.04861, 2017.
[69] KREISS S, BERTONI L, ALAHI A, et al. PifPaf: compo-site fields for human pose estimation[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Pisca-taway: IEEE, 2019: 11977-11986.
[70] CHENG B, XIAO B, WANG J, et al. Bottom-up higher-resolution networks for multi-person pose estimation[J]. arXiv:1908.10357, 2019.
[71] NIE X C, FENG J S, ZHANG J F, et al. Single-stage multi-person pose machines[C]//Proceedings of the 2019 Interna-tional Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 6951-6960.
[72] JOHNSON S, EVERINGHAM M. Clustered pose and non-linear appearance models for human pose estimation[C]// Proceedings of the British Machine Vision Conference, Aberystwyth, Aug 31-Sep 3, 2010. British Machine Vision Association, 2010: 1-11.
[73] SAPP B, TASKAR B. MODEC: multimodal decomposable models for human pose estimation[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, Jun 23-28, 2013. Washington: IEEE Computer Society, 2013: 3674-3681.
[74] ANDRILUKA M, PISHCHULIN L, GEHLER P V, et al. 2D human pose estimation: new benchmark and state of the art analysis[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 3686-3693.
[75] LIN T, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//LNCS 8693: Proceedings of the 13th European Conference on Computer Vision, Zurich, Sep 6-12, 2014. Berlin, Heidelberg: Springer, 2014: 740-755.
[76] WU J, ZHENG H, ZHAO B, et al. AI challenger: a large-scale dataset for going deeper in image understanding[J]. arXiv:1711.06475, 2017.
[77] ZHANG W Y, ZHU M L, DERPANIS K G, et al. From actemes to action: a strongly-supervised representation for detailed action understanding[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Dec 1-8, 2013. Washington: IEEE Computer Society, 2013: 2248-2255.
[78] JHUANG H, GALL J, ZUFFI S, et al. Towards understand-ing action recognition[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Dec 1-8, 2013. Washington: IEEE Computer Society, 2013: 3192-3199.
[79] KUEHNE H, JHUANG H, GARROTE E, et al. HMDB: a large video database for human motion recognition[C]// Proceedings of the 2011 IEEE International Conference on Computer Vision, Barcelona, Nov 6-13, 2011. Washington: IEEE Computer Society, 2011: 2556-2563.
[80] ANDRILUKA M, IQBAL U, INSAFUTDINOV E, et al. PoseTrack: a benchmark for human pose estimation and tracking[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 5167-5176.
[81] FERRARI V, MARíN-JIMéNEZ M J, ZISSERMAN A, et al. Progressive search space reduction for human pose estima-tion[C]//Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Jun 24-26, 2008. Washington: IEEE Computer Society, 2008: 1-8.
[82] YANG Y, RAMANAN D. Articulated human detection with flexible mixtures of parts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12): 2878-2890.
[83] TIAN Y, LI F D. Research review on human body gesture recognition based on depth data[J]. Computer Engineering and Applications, 2020, 56(4): 1-8.
田元, 李方迪. 基于深度信息的人体姿态识别研究综述[J]. 计算机工程与应用, 2020, 56(4): 1-8.
[84] DENG Y N, LUO J X, JIN F L. Overview of human pose estimation methods based on deep learning[J]. Computer Engineering and Applications, 2019, 55(19): 22-42.
邓益侬, 罗健欣, 金凤林. 基于深度学习的人体姿态估计方法综述[J]. 计算机工程与应用, 2019, 55(19): 22-42.
[85] YANG L P, SUN Y B, ZHANG H L, et al. Human keypoint matching network based on encoding and decoding residuals [J]. Computer Science, 2020, 47(6): 114-120.
杨连平, 孙玉波, 张红良, 等. 基于编解码残差的人体关键点匹配网络[J]. 计算机科学, 2020, 47(6): 114-120.
[86] QI T, BAYRAMLI B, ALI U, et al. Spatial shortcut network for human pose estimation[J]. arXiv:1904.03141, 2019.