Abstract
The problem of detecting objects in images is solved by training the classifier by the descriptors constructed based on the local Radon transform of the gradient field of the image. The space of the Radon transform is considered as the Hough space accumulator in which projections are constructed. The set of local projections forms a descriptor of the region related to the object that is a generalization of the known histogram of oriented gradients (HOG) descriptor. The issues of the effect of the approximation of the Radon transform contribution function, the form of local normalization, and the number of directions in the projection histograms on the results of detecting pedestrians are investigated. The results produced by the proposed descriptor are compared with the results obtained using the HOG descriptor and convolutional neural networks (CNN) based on the ResNext and MobileNet architectures on the INRIA and CityScapes databases.
Similar content being viewed by others
REFERENCES
G. G. Sebryakov, V. N. Soshnikov, I. S. Kikin, and A. A. Ishutin, “Algorithm for automatic recognition of ground objects in optoelectronic images, based on evaluation of feature covariance matrices built for image gradient functions,” Vestn. Komp. Inform. Tekhnol. 109 (7), 14–19 (2013).
Yu. V. Vizilter and S. Yu. Zheltov, “The use of projective morphologies for object detection and identification in images,” J. Comput. Syst. Sci. Int. 48, 282 (2009).
A. N. Gneushev, “Construction and optimization of a texture–geometric model of a face image in the space of basic Gabor functions,” J. Comput. Syst. Sci. Int. 46, 418 (2007).
A. N. Gneushev, “Optimization of the texture-geometric image model for estimation of the face parameters,” Autom. Remote Control 73, 144 (2012).
L. Zhang, L. Lin, X. Liang, and K. He, “Is faster R-CNN doing well for pedestrian detection?,” in Proceedings of the 14th European Conference on Computer Vision (Amsterdam, Netherlands, 2016), pp. 443–457.
Z. Cai, Q. Fan, R. S. Feris, and N. Vasconcelos, “A unified multi-scale deep convolutional neural network for fast object detection,” in Proceedings of the 14th European Conference on Computer Vision (Amsterdam, Netherlands, 2016), pp. 354–370.
J. Li, X. Liang, and S. Shen, “Scale-aware fast R-CNN for pedestrian detection,” IEEE Trans. Multimedia 20, 985–996 (2017).
X. Du, M. El-Khamy, J. Lee, and L. S. Davis, “Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection,” in Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA,2017, pp. 953–961.
P. Viola and M. J. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proceedings of the 2001 IEEE Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA,2001, Vol. 1, pp. 511–518.
P. Viola, M. J. Jones, and D. Snow, “Detecting pedestrians using patterns of motion and appearance,” in Proceedings of the 9th International Conference on Computer Vision, Nice, France,2003, Vol. 1, pp. 734–741.
N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA,2005, Vol. 1, pp. 886–893.
P. Felzenszwalb, D. McAllester, and D. Ramanan, “A discriminatively trained, multiscale, deformable part model,” in Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA,2008, pp. 1–8.
P. F. B. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part based models,” IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627–1645 (2010).
D. Sun and J. Watanada, “Detecting pedestrians and vehicles in traffic scene based on boosted HOG features and SVM,” in Proceedings of the IEEE 9th International Symposium on Intelligent Signal Processing, Siena, Italy,2015, pp. 1–4.
T. Watanabe, S. Ito, and K. Yokoi, “Co-occurrence histograms of oriented gradients for pedestrian detection,” Adv. Image Video Technol. 5414, 37–47 (2009).
S. Tabbone, L. Wendling, and J. P. Salmon, “A new shape descriptor defined on the Radon transform,” Comput. Vision Image Understand. 102, 42–51 (2006).
N. Nacereddine, S. Tabbone, D. Ziou, and L. Hamami, “Shape-based image retrieval using a new descriptor based on the radon and wavelet transforms,” in Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Turkey,2010, pp. 1997–2000.
H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recogn. 13, 111–122 (1981).
I. E. Svetov, “Inversion formulas for recovering the harmonic 2D-vector field by known ray transforms,” Sib. Elektron. Mat. Izv. 12, 436–446 (2015).
A. N. Gneushev and A. B. Murynin, “Adaptive gradient method for extracting contour features of objects in images of real-world scenes,” J. Comput. Syst. Sci. Int. 42, 973 (2003).
A. N. Gneushev and N. A. Samsonov, “Textural descriptor in the Hough accumulator space of the gradient field for detecting pedestrians,” Mashin. Obuchen. Anal. Dannykh. 3, 203–215 (2017).
INRIA Person Dataset. http://pascal.inrialpes.fr/data/human/. Accessed June 4, 2017.
S. Zhang, R. Benenson, and B. Schiele, “CityPersons: A diverse dataset for pedestrian detection,” in Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA,2017, pp. 4457–4465.
M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The cityscapes dataset for semantic urban scene understanding,” in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA,2016, pp. 3213–3223.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA,2016, pp. 770–778.
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” https://arxiv.org/abs/1704.04861. Available June 23, 2019.
Funding
This work was supported by the Ministry for Science and Higher Education of the Russian Federation, project no. RFMEFI60719X0312.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Translated by A. Klimontovich
Rights and permissions
About this article
Cite this article
Samsonov, N.A., Gneushev, A.N. & Matveev, I.A. Training a Classifier by Descriptors in the Space of the Radon Transform. J. Comput. Syst. Sci. Int. 59, 415–429 (2020). https://doi.org/10.1134/S1064230720030053
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064230720030053