Abstract
This paper proposes a crowd counting method using higher order auto-correlation (HLAC) feature between cells of histogram oriented gradient (HOG). Although HOG feature is effective for human detection, it depends on the object position and is not suitable for crowd counting. To apply HOG feature to crowd counting, we extract the first-order HLAC feature from cells of HOG feature. Our new feature has shift invariance and additive properties of HLAC feature as well as the robustness to illumination variation of HOG feature. We predict the number of humans in an image using partial least squares regression (PLSR) from our feature. We evaluate our method using the Mall dataset, and we confirmed that our method gives the state-of-art performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Loy, C.C., Chen, K., Gong, S., Xiang, T.: Crowd counting and profiling: Methodology and evaluation. In: Modeling, Simulation and Visual Analysis of Crowds, pp. 347–382. Springer (2013)
Chen, K., Loy, C.C., Gong, S., Xiang, T.: Feature mining for localised crowd counting. In: British Machine Vision Conference, pp. 1–11 (2012)
Chen, K., Gong, S., Xiang, T., Loy, C.C.: Cumulative attribute space for age and crowd density estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2467–2474. IEEE (2013)
Kumagai, S., Hotta, K.: Counting in intracellular images using partial least squares regression and correlation between features. In: International Symposium on Computing and Networking, pp. 275–280. IEEE (2013)
Arteta, C., Lempitsky, V., Noble, J.A., Zisserman, A.: Learning to detect partially overlapping instances. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 3230–3237. IEEE (2013)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 886–893. IEEE (2005)
Otsu, N., Kurita, T.: A new scheme for practical flexible and intelligent vision systems. In: IAPR International Conference on Machine Vision Applications, pp. 431–435 (1988)
Kobayashi, T., Otsu, N.: Image feature extraction using gradient local auto-correlations. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 346–358. Springer, Heidelberg (2008)
Herman, W.: Soft modeling by latent variables: the nonlinear iterative partial least squares approach. In: Perspectives in Probability and Statistics (1975)
Kobayashi, T., Hosaka, T., Mimura, S., Hayashi, T., Otsu, N.: Hlac approach to automatic object counting. In: ECSIS Symposium on Bio-inspired Learning and Intelligent Systems for Security, BLISS 2008, pp. 40–45. IEEE (2008)
Toyoda, T.: Texture classification using extended higher order local autocorrelation features. In: Texture 2005: 4th International Workshop on Texture Analysis and Synthesis. Citeseer (2005)
Suzuki, M.T.: Texture image classification using extended 2d hlac feature. In: International Conference on Kansei Engineering and Emotion Research (2014)
Schwartz, W.R., Kembhavi, A., Harwood, D., Davis, L.S.: Human detection using partial least squares analysis. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 24–31. IEEE (2009)
Kembhavi, A., Harwood, D., Davis, L.S.: Vehicle detection using partial least squares. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 1250–1265 (2011)
Wold, H.: Estimation of principal components and related models by iterative least squares. Journal of Multivariate Analysis (1966)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kumagai, S., Hotta, K. (2014). HLAC between Cells of HOG Feature for Crowd Counting. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2014. Lecture Notes in Computer Science, vol 8887. Springer, Cham. https://doi.org/10.1007/978-3-319-14249-4_66
Download citation
DOI: https://doi.org/10.1007/978-3-319-14249-4_66
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14248-7
Online ISBN: 978-3-319-14249-4
eBook Packages: Computer ScienceComputer Science (R0)