Abstract
The purpose of this paper is to describe one-shot-learning gesture recognition systems developed on the ChaLearn Gesture Dataset (ChaLearn 2011). We use RGB and depth images and combine appearance (Histograms of Oriented Gradients) and motion descriptors (Histogram of Optical Flow) for parallel temporal segmentation and recognition. The Quadratic-Chi distance family is used to measure differences between histograms to capture cross-bin relationships. We also propose a new algorithm for trimming videos—to remove all the unimportant frames from videos. We present two methods that use a combination of HOG-HOF descriptors together with variants of a Dynamic Time Warping technique. Both methods outperform other published methods and help narrow the gap between human performance and algorithms on this task. The code is publicly available in the MLOSS repository.
Editors: Isabelle Guyon, Vassilis Athitsos, and Sergio Escalera.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The code is available at https://mloss.org/software/view/448.
- 2.
Details and website: http://gesture.chalearn.org/.
- 3.
An example is batch devel12, video 23.
- 4.
An example is batch devel39, particularly video 18.
- 5.
Using an algorithm bgremove provided in sample code of the Challenge (ChaLearn 2011).
- 6.
Available at http://www.microsoft.com/en-us/kinectforwindows/develop/.
References
H. Bay, T. Tuytelaars, L. Van Gool, Surf: speeded up robust features, in Computer Vision–ECCV 2006 (Springer, Berlin, 2006), pp. 404–417
D.J. Berndt, J. Clifford, Using dynamic time warping to find patterns in time series. KDD Workshop 10, 359–370 (1994)
ChaLearn. ChaLearn Gesture Dataset (CGD2011), ChaLearn, California, (2011), http://gesture.chalearn.org/data
S.P. Chatzis, D.I. Kosmopoulos, P. Doliotis, A conditional random field-based model for joint sequence segmentation and classification. Pattern Recognit. 46, 1569–1578 (2012)
N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1 (IEEE, 2005), pp. 886–893
P. Dollár, Piotr’s Image and Video Matlab Toolbox (PMT), http://vision.ucsd.edu/~pdollar/toolbox/doc/index.html
S.R. Fanello, I. Gori, G. Metta, F. Odone, One-shot Learning for Real-time Action Recognition (Springer, Berlin, 2013)
I. Guyon, V. Athitsos, P. Jangyodsuk, B. Hamner, H.J. Escalante, Chalearn gesture challenge: design and first results, in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (IEEE, 2012), pp. 1–6
I. Guyon, V. Athitsos, P. Jangyodsuk, H.J. Escalante, B. Hamner, Results and analysis of the chalearn gesture challenge 2012 (2013)
A. Hernández-Vela, M.Á. Bautista, X. Perez-Sala, V. Ponce, X. Baró, O. Pujol, C. Angulo, S. Escalera, BoVDW: Bag-of-visual-and-depth-words for gesture recognition, in International Conference on Pattern Recognition (2012), pp. 449–452
N. Ikizler, D. Forsyth, Searching video for complex activities with finite state models, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2007), pp. 1–8
T. Kanade, B.D. Lucas, An iterative image registration technique with an application to stereo vision, in Proceedings of the 7th International Joint Conference on Artificial Intelligence (1981)
A. Klaser, M. Marszalek, A spatio-temporal descriptor based on 3d-gradients (2008)
I. Laptev, On space-time interest points. Int. J. Comput. Vis. 64(2–3), 107–123 (2005)
I. Laptev, M. Marszalek, C. Schmid, B. Rozenfeld, Learning realistic human actions from movies, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2008), pp. 1–8
D.D. Lewis, Naive (bayes) at forty: the independence assumption in information retrieval, in Machine Learning: ECML-98 (Springer, Berlin, 1998), pp. 4–15
D.G. Lowe, Object recognition from local scale-invariant features, in The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, vol. 2 (IEEE, 1999), pp. 1150–1157
B.D. Lucas, Generalized Image Matching by the Method of Differences. Ph.D. thesis, Robotics Institute, Carnegie Mellon University, July 1984
Y.M. Lui, Human gesture recognition on product manifolds. J. Mach. Learn. Res. 13, 3297–3321 (2012)
M.R. Malgireddy, I. Inwogu, V. Govindaraju. A temporal bayesian model for classifying, detecting and localizing activities in video sequences, in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (IEEE, 2012), pp. 43–48
O. Pele, M. Werman, The quadratic-chi histogram distance family. Comput. Vis.-ECCV 2010, 749–762 (2010)
J. Wan, Q. Ruan, W. Li, S. Deng, one-shot learning gesture recognition from RGB-D data using bag of features. J. Mach. Learn. Res. 14, 2549–2582 (2013), http://jmlr.org/papers/v14/wan13a.html
H. Wang, M.M. Ullah, A. Klaser, I. Laptev, C. Schmid, et al., Evaluation of local spatio-temporal features for action recognition, in BMVC 2009-British Machine Vision Conference (2009)
S.B. Wang, A. Quattoni, L-P, Morency, D. Demirdjian, T. Darrell, Hidden conditional random fields for gesture recognition, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2 (IEEE, 2006), pp. 1521–1527
D. Wu, F. Zhu, L. Shao, One shot learning gesture recognition from RGBD images, in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (IEEE, 2012), pp. 7–12
T. Xia, D. Tao, T. Mei, Y. Zhang, Multiview spectral embedding. IEEE Trans. Syst. Man Cybern. Part B: Cybern. 40(6), 1438–1446 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
Appendix A
In this appendix, we analyse the computational complexity of our methods.
Let us first describe the computational complexity of the building blocks of our algorithms. Let r, c be the resolution of our videos. For this data set we have \(r = 240, c = 320\). Let P denote number of pixels (\(P = rc\)). Computing both HOG and HOF features requires performing a fixed number of iterations for every pixel. Creating histograms in spatial cells requires a fixed number of operations with respect to the size of these cells. Thus the complexity of computing HOG and HOF descriptors for one example requires \(\mathcal {O}(P)\) operations. Let m be the number of pixels used in the median filter for every pixel. Since computing the median requires ordering, the complexity of filtering an image requires \(\mathcal {O}(P m \log m)\) operations. In total, for both SM and MM, the whole training on a batch of N frames in total requires \(\mathcal {O}(N P m \log (m))\) operations.
Before evaluating a new video of F frames, we have to compute the representations of the frames, which is done in \(\mathcal {O}(F P m \log m)\) operations. In both methods we then perform a Viterbi search. In MM this is divided into several searches, but the total complexity stays the same. The most time consuming part is computing the Quadratic-Chi distances (Sect. 12.5.3) between all FN pairs of frames from the new video and model. Computing the distance needs sum over elements over sparse \(H \times H\) matrix (H being the size of the histograms used) described in Algorithm 2. The number of non-zero elements is linear in H. Thus, the overall complexity of evaluating a new video is \(\mathcal {O} (N P m \log (m) + N F H).\)
To summarize, the running time of our methods is linear in the number of training frames, number of frames of a new video, number of pixels of a single frame, and size of histogram (number of spatial cell times number of orientation bins). Dependence on size of the filtering region for every pixel is linearithmic since it requires sorting.
Appendix B
In this Appendix, we provide MATLAB algorithm for creating similarity matrix used in the Quadratic-Chi distance described in Sect. 12.5.3. We have histograms of \(h \times w\) spatial cells, and p orientation bins in each of the spatial bins. The size of the final matrix is \(H \times H\), where \(H = hwp\).
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Konečný, J., Hagara, M. (2017). One-Shot-Learning Gesture Recognition Using HOG-HOF Features. In: Escalera, S., Guyon, I., Athitsos, V. (eds) Gesture Recognition. The Springer Series on Challenges in Machine Learning. Springer, Cham. https://doi.org/10.1007/978-3-319-57021-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-57021-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57020-4
Online ISBN: 978-3-319-57021-1
eBook Packages: Computer ScienceComputer Science (R0)