Abstract
The progress on human pose estimation by deep neural networks has been significantly advanced in recent years. However, the problem of precision loss caused by the prediction of the coordinates back to the original image has been neglected. In this paper, we propose a simple but effective method using Heatmap and Offset for Pose Estimation (HOPE). In order to solve the human pose estimation problem, firstly a general top-down method is used in HOPE to generate the human detection box based on a detector, and then the keypoints in each cropped box image are located. To alleviate the precision loss of mapping process, HOPE embeds the coordinate offset into the structure of the neural network, allowing the network to self-learn the slight offset in the mapping process in an end-to-end manner, which improves the accuracy in the current field of pose estimation. Experimental results on the multi-person pose estimation dataset MSCOCO, the single-person pose estimation dataset MPII and CrowdPose Pose Estimation dataset indicate that our method achieves state-of-the-art performance in terms of accuracy and computational complexity.
Similar content being viewed by others
References
Alyammahi S, Bhaskar H, Ruta D, Al-Mualla M (2017) People detection and articulated pose estimation framework for crowded scenes. Knowl Based Syst 131:83–104
Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 2D human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp 3686–3693. https://doi.org/10.1109/CVPR.2014.471
Belagiannis V, Zisserman A (2017) Recurrent human pose estimation. In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). IEEE, pp 468–475. https://doi.org/10.1109/FG.2017.64
Cai Y, Wang Z, Luo Z, Yin B, Du A, Wang H, Zhou X, Zhou E, Zhang X, Sun J (2020) Learning delicate local representations for multi-person pose estimation. arXiv:200304030
Cao Z, Simon T, Wei SE, Sheikh Y (2017) Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7291–7299. https://doi.org/10.1109/CVPR.2017.143
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans Pattern Anal Mach Intell 40(4):834–848
Chen X, Yuille AL (2014) Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in neural information processing systems, pp 1736–1744. https://papers.nips.cc/paper/2014/file/8b6dd7db9af49e67306feb59a8bdc52c-Paper.pdf
Chen Y, Wang Z, Peng Y, Zhang Z, Yu G, Sun J (2018) Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7103–7112
Cheng B, Xiao B, Wang J, Shi H, Huang TS, Zhang L (2019) Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. arXiv:190810357
Cho E, Kim D (2014) Accurate human pose estimation by aggregating multiple pose hypotheses using modified kernel density approximation. IEEE Signal Process Lett 22(4):445–449
Dong R, Pan X, Li F (2019) Denseu-net-based semantic segmentation of small objects in urban remote sensing images. IEEE Access 7:65347–65356
Duan P, Wang T, Cui M, Sang H, Sun Q (2019) Multi-person pose estimation based on a deep convolutional neural network. J Vis Commun Image Represent 63:245–252
Ghaneizad M, Kavehvash Z, Mehrany K, Hosseini SAT (2017) A fast bottom-up approach toward three-dimensional human pose estimation using an array of cameras. Opt Lasers Eng 95:69–77
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961–2969. https://doi.org/10.1109/TPAMI.2018.2844175
Insafutdinov E, Pishchulin L, Andres B, Andriluka M, Schiele B (2016) Deepercut: a deeper, stronger, and faster multi-person pose estimation model. In: European Conference on Computer Vision. Springer, pp 34–50. https://doi.org/10.1007/978-3-319-46466-4_3
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167
Jammalamadaka N, Zisserman A, Jawahar C (2017) Human pose search using deep networks. Image Vis Comput 59:31–43
Kang B, Nguyen TQ (2019) Random forest with learned representations for semantic segmentation. IEEE Trans Image Process 28(7):3542–3555
Kuo P, Makris D, Nebel JC (2011) Integration of bottom-up/top-down approaches for 2d pose estimation using probabilistic Gaussian modelling. Comput Vis Image Underst 115(2):242–255
Li J, Wang C, Zhu H, Mao Y, Fang HS, Lu C (2019a) Crowdpose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 10863–10872
Li R, Liu Z, Tan J (2019b) A survey on 3d hand pose estimation: Cameras, methods, and datasets. Pattern Recogn 93:251–272
Li R, Zou K, Wang W (2020) Application of human body gesture recognition algorithm based on deep learning in non-contact human body measurement. J Ambient Intell Humani Comput. https://doi.org/10.1007/s12652-020-01993-1
Liang G, Lan X, Wang J, Wang J, Zheng N (2017) A limb-based graphical model for human pose estimation. IEEE Trans Syst Man Cybern Syst 48(7):1080–1092
Liang S, Sun X, Wei Y (2018) Compositional human pose regression. Comput Vis Image Underst 176:1–8
Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European Conference on Computer Vision. Springer, pp 740–755. https://doi.org/10.1007/978-3-319-10602-1_48
Liu Y, Wang Q, Jiang Y, Lei Y (2014) Supervised locality discriminant manifold learning for head pose estimation. Knowl Based Syst 66:126–135
Liu Z, Zhu J, Bu J, Chen C (2015) A survey of human pose estimation: the body parts parsing based methods. J Vis Commun Image Represent 32:10–19
Liu Z, Li X, Luo P, Loy CC, Tang X (2017) Deep learning Markov random field for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 40(8):1814–1828
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60(2):91–110
Luo Y, Xu Z, Liu P, Du Y, Guo JM (2018) Multi-person pose estimation via multi-layer fractal network and joints kinship pattern. IEEE Trans Image Process 28(1):142–155
MSCOCO (2015) Keypoints evaluation metric. http://mscoco.org/dataset/keypoints-eval
Neubeck A, Van Gool L (2006) Efficient non-maximum suppression. In: International Conference on Pattern Recognition, vol 3. IEEE, pp 850–855. https://doi.org/10.1109/ICPR.2006.479
Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision. Springer, pp 483–499. https://doi.org/10.1007/978-3-319-46484-8_29
Papandreou G, Zhu T, Kanazawa N, Toshev A, Tompson J, Bregler C, Murphy K (2017) Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4903–4911. https://doi.org/10.1109/CVPR.2017.395
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91–99. https://doi.org/10.1109/TPAMI.2016.2577031
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y
Shamsafar F, Ebrahimnezhad H (2020) Uniting holistic and part-based attitudes for accurate and robust deep human pose estimation. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-020-02347-7
Silva LJS, da Silva DLS, Raposo A, Velho L, Lopes H (2019) Tensorpose: real-time pose estimation for interactive applications. Comput Gr 85:1–14
Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9. https://doi.org/10.1109/CVPR.2015.7298594
Tang Y, Wang J, Wang X, Gao B, Dellandréa E, Gaizauskas R, Chen L (2017) Visual and semantic knowledge transfer for large scale semi-supervised object detection. IEEE Trans Pattern Anal Mach Intell 40(12):3045–3058
Xiao B, Wu H, Wei Y (2018) Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 466–481. https://doi.org/10.1007/978-3-030-01231-1_29
Yu F, Wang D, Shelhamer E, Darrell T (2018) Deep layer aggregation. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition. pp 2403–2412
Zhang Q, Lin J, Zhuge J, Yuan W (2019) Multi-level and multi-scale deep saliency network for salient object detection. J Vis Commun Image Represent 59:415–424
Zhang X, Chen Z, Wu QJ, Cai L, Lu D, Li X (2018) Fast semantic segmentation for scene perception. IEEE Trans Ind Inf 15(2):1183–1192
Acknowledgements
We would like to thank the anonymous reviewers to improve the quality of this paper. This work was partially supported by the National Natural Science Foundation of China project No. 61702126, the Natural Science Foundation of Guangdong Province project No. 2018A030313318 and the Key-Area Research and Development Program of Guangdong Province project No. 2019B111101001.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xiao, J., Li, H., Qu, G. et al. Hope: heatmap and offset for pose estimation. J Ambient Intell Human Comput 13, 2937–2949 (2022). https://doi.org/10.1007/s12652-021-03124-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-021-03124-w