Abstract
Based on the advantage of deep learning in object extraction, in this paper we design a deep network that adds Batch-Normalization to the convolution layer. Batch-Normalization has three main advantages. Firstly, it normalizes the input data, which can speed up the fitting of parameters. Secondly, Batch-Normalization can reconstruct the distribution of the input data, so that the feature of input data will not be lost. Thirdly, Batch-Normalization is able to prevent over-fitting, so it can replace Dropout, Local Response Normalization to simplify the network. The network in this paper adopted region proposal to get region of interests. Training classification and position adjustment at the same time to improve accuracy. Comprehensive experimental results have demonstrated the efficacy of the proposed network for objects detection.
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 subscriptionsReferences
Zeng, B., Wang, G., Lin, X.: Real-time pedestrian detection based on color self-similarity. J. Tsinghua Univ. (Sci. Technol.) 52(04), 571–574 (2012)
Mu, Y., Yan, S., Liu, Y., et al.: Discriminative local binary patterns for human detection in personal album. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8. DBLP (2008)
Wu, J., Geyer, C., Rehg, J.M.: Real-time human detection using contour cues. In: IEEE International Conference on Robotics and Automation, pp. 860–867. IEEE (2011)
Zhou, Z., Yu, S., Zhang, R., Yang, X.: A method of face recognition based on SIFT operator. J. Image Graph. 13(10), 1882–1885 (2008)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893. IEEE Xplore (2005)
Lienhart, R., Maydt, J.: An extended set of Haar-like features for rapid object detection. In: 2002 Proceedings of International Conference on Image Processing, vol.1, pp. I-900-I-903. IEEE (2002)
Yang, X., Yang, Y.: A high efficiency vehicle detection method based on HOG-LBP. Comput. Eng. 09, 210–214 (2014)
Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004, vol. 2, pp. II-506-II-513. IEEE (2004)
Walk, S., Majer, N., Schindler, K., et al.: New features and insights for pedestrian detection. In: Computer Vision and Pattern Recognition, pp. 1030–1037. IEEE (2010)
Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8. DBLP (2008)
Freund, Y., Schapire, R.E.: A desicion-theoretic generalization of on-line learning and an application to boosting. In: Vitányi, P. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 23–37. Springer, Heidelberg (1995). https://doi.org/10.1007/3-540-59119-2_166
Girshick, R., Donahue, J., Darrell, T., et al.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142–158 (2016)
He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
Girshick R.: Fast R-CNN. In: IEEE International Conference on Computer Vision, pp. 1440–1448. IEEE Computer Society (2015)
Ren, S., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: nternational Conference on Neural Information Processing Systems, pp. 91–99. MIT Press (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015). JMLR.org
He, K., Gkioxari, G., Dollár, P., et al.: Mask R-CNN (2017)
Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: ICLR (2017)
Zhao, J., et al.: Energy-based generative adversarial networks. In: ICLR (2017)
Zhou, Y., Zeng, F.: 2D compressive sensing and multi-feature fusion for effective 3D shape retrieval. Inf. Sci. 101–120 (2017)
Gai, K., Qiu, M., Ming, Z., Zhao, H., Qiu, L.: Spoofing-jamming attack strategy using optimal power distributions in wireless smart grid networks. IEEE Trans. Smart Grid 8(5), 2431–2439 (2017)
Gai, K., Qiu, M., Tao, L., Zhu, Y.: Intrusion detection techniques for mobile cloud computing in heterogeneous 5G. Secur. Commun. Netw. 9(16), 3049–3058 (2016)
Acknowledgements
The authors would like to thank the editors and the anonymous reviewers for their constructive comments to further improve the quality of this paper. This work is partially supported by the following projects in china: National Natural Science Foundation of China (No. 61602116), Natural Science Foundation of Guangdong Province (No. 2015A030313635, No. 2017A030313388), Science and Technology Project of Guangdong Province (No. 2014A010103037), Special Found for Science and Technology Innovation of Foshan City (No. 2015AG10008, No. 2016GA10156, No. 2014AG10001), Education Department of Guangdong Province (No. 2015KTSCX153) and Outstanding Youth Teacher Training Program of Foshan University (No. FSYQ201411).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Zhou, Y., Yuan, C., Zeng, F., Qian, J., Wu, C. (2018). An Object Detection Algorithm for Deep Learning Based on Batch Normalization. In: Qiu, M. (eds) Smart Computing and Communication. SmartCom 2017. Lecture Notes in Computer Science(), vol 10699. Springer, Cham. https://doi.org/10.1007/978-3-319-73830-7_43
Download citation
DOI: https://doi.org/10.1007/978-3-319-73830-7_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-73829-1
Online ISBN: 978-3-319-73830-7
eBook Packages: Computer ScienceComputer Science (R0)