Human Pose Estimation in Images and Videos


  • P Reddy Gurunatha Swamy
  • B Ananth Reddy





Voronoi segmentation, box model, optical flow tracking, SURF features.


Estimation of human poses is an interesting and challenging topic in the field of Computer vision. It includes some un-noticed challenges like background effect, the color of the dress, skin tones and many other unpredictable challenges. This is a workable concept because it can be used in sign language recognition, correlating various pose styles from different parts of the world and in medical applications. A deep structure which can represent a man’s body in different models will help in improved recognition of body parts and the spatial correlation between them. For hand detection, features based on hand shape and representation of geometrical details are derived with the help of hand contour. An adaptive and unsupervised approach based on Voronoi region is primarily used for the color image segmentation problem. This process includes identification of key points of the body, which may include body joints and parts. The identification parts will be tough due to small joints and occlusions. Identification of Image features is described in this paper with the help of Box Model Based Estimation, Speed up robust features and finally with Optical flow tracking algorithm. In Optical flow tracking algorithm, we have used Horn-Schunk algorithm to determine featural changes in the images.




[1] Sharma S, Dubey SR, Singh SK, Saxena R & Singh RK, “Identity verification using shape and geometry of human handsâ€, Expert Systems with Applications, Vol.42, No.2,(2015), pp.821-832.

[2] Hettiarachchi R & Peters JF, “Voronoï region-based adaptive unsupervised color image segmentationâ€, Pattern Recognition, Vol.65, (2017), pp.119-135.

[3] Zhao L, Gao X, Tao D & Li X, “A deep structure for human pose estimationâ€, Signal Processing, Vol.108, (2015), pp.36-45.

[4] Chen Z, Qi Z, Meng F, Cui L & Shi Y, “Image segmentation via improving clustering algorithms with density and distanceâ€, Procedia Computer Science, Vol.55, (2015), pp.1015-1022.

[5] Sapp B & Tasker B, “Multimodal Decomposable Methods for Human Pose Estimationâ€, IEEE Computer Vision and Pattern Recognition, (2013).

[6] Marin-Jimenez MJ, Munoz-Salinas R & Medina-Camicer R, “Mixing body parts model for 2D Human Pose Recognitionâ€, IET Computer Vision, (2017).

[7] Eichner M, Marin-Jimenez M, Zisserman A & Ferrari V, “2D Articulated Human Pose Estimation and Retrieval in Unconstrained Still Imagesâ€, Computer Vision, (2012).

[8] Shi Q, Di H, Lu Y, Lv F & Tian X, “Video pose estimation with global motion cuesâ€, Neurocomputing, Vol.219, (2017), pp.269-279.

[9] Kishore PVV, Kumar EK, Manjula B & Kumar PR, “Sign Video Segmentation using region, Boundary based active contours with shape priorsâ€, Computer Science and Information Technology, (2012).

[10] Sedai S, Bennamoun M & Huynh DQ, “Discriminative fusion of shape and appearance features for human pose estimationâ€, Patter Recognition, Elsevier, (2013).

[11] Toshev A & Szegedy C, “Human Pose Estimation via Deep Neural Networksâ€, IEEE Conference Computer Vision and Pattern Recognition, (2014).

[12] Pishchulin L, Andriluka M, Gehler P & Schiele B, “Strong appearance and expressive spatial models for human pose estimationâ€, Proceedings of the IEEE international conference on Computer Vision, (2013), pp.3487-3494.

[13] Kishore PVV, Kumar PR, Kumar EK & Kishore SRC, “Video audio interface for recognizing gestures of indian signâ€, International Journal of Image Processing, Vol.5, No.4,(2011).

[14] Kishore PVV, Prasad MVD, Kumar DA & Sastry ASCS, “Optical flow hand tracking and active contour hand shape features for continuous sign language recognition with artificial neural networksâ€, Proceedings of the 6th International Advanced Computing Conference, IACC, (2016), pp.346-351.

[15] G, Abikhanova, A Ahmetbekova, E Bayat, A Donbaeva, G Burkitbay (2018). International motifs and plots in the Kazakh epics in China (on the materials of the Kazakh epics in China), Opción, Año 33, No. 85. 20-43.

[16] Lei Y, Jiang X, Shi Z, Chen D & Li Q, “Face recognition method based on SURF featureâ€, International Symposium on Computer Network and Multimedia Technology, (2009), pp.1-4.

[17] Lucena MJ, Fuertes JM, Gomez JI, de la Blanca NP & Garrido A, “Tracking from optical flowâ€, Proceedings of the 3rd International Symposium on Image and Signal Processing and Analysis, (2003), pp.651-655).

[18] Illeperuma GD & Sonnadara UJ, “An autonomous robot navigation system based on optical flowâ€, 6th Int. Conf. Ind. Inf. Syst, (2011), pp.489-492.

View Full Article: