Abstract
In order to solve the problem that there are few blind path data sets and a lot of manual data collection work in the current blind guide system, computer vision algorithm is used to automatically generate blind path images in different environments. Methods a blind path image generation method based on the depth convolution generative adversary network (DCGAN) is proposed. The method uses the characteristics of typical blind path, which is the combination of depression and bulge. The aim of long short memory network’ (LSTM) is to encode the depression part, and the aim of convolution neural network (CNN) is to encode the bulge part. The two aspects of information are combined to generate blind path images in different environments. It can effectively improve the blind path recognition rate of the instrument and improve the safe travel of the visually impaired. Conclusion generative adversarial networks (GANs) can be used to generate realistic blind image, which has certain application value in expanding blind channel recognition data, but it still needs to be improved in some details.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, S.: Research on the guidance system based on ultrasonic sensor array. Chongqing University of Technology (2013)
Yin, L.: Research on 3D reconstruction method of computer vision based on OpenCV. Anhui University (2011)
Lu, P., Dong, H.: Face image generation based on deep convolution antagonism generation network. Mod. Comput. (21), 56–58, 64 (2019)
Zeng, Q., Xiang, D., Li, N., Xiao, H.: Image recognition method based on semi supervised depth generation countermeasure network. Meas. Control Technol. 38(08), 37–42 (2019)
Ian, G., Jean, P.-A., Mehdi, M., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014).
Ye, C., Guan, W.: Application of generative adversary network. J. Tongji Univ. (Nat. Sci. Ed.) 48(04), 591–601 (2020)
Guo, Q.: Generation of countermeasure samples based on generation countermeasure network. Mod. Comput. 07, 24–28 (2020)
Ke, J., Xu, Z.: Research on speech enhancement algorithm based on generation countermeasure network. Inf. Technol. Netw. Secur. 37(05), 54–57 (2018)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Ke, Y., Wang, X., Zheng, Y.: Deep convolution generation countermeasure network structure. Electron. Technol. Softw. Eng. 24, 5–6 (2018)
Tang, X., Du, Y., Liu, Y., Li, J., Ma, Y.: An image recognition method based on conditional depth convolution generation countermeasure network. Acta Automatica Sinica 44(05), 855–864 (2018)
Jia, J., Li, J.: Pest image recognition algorithm based on semi supervised generation network. J. Wuhan Light Ind. Univ. 38(04), 45–52 (2019)
Ke, J.: Blind path recognition system based on image processing. Shanghai Jiaotong University (2008)
Ke, J., Zhao, Q., Shi, P.: Blind path recognition algorithm based on image processing. Comput. Eng. 35(01), 189–191, 197 (2009)
Yang, X., Yang, J., Yu, X.: Blind path recognition algorithm in image processing. Shang (15), 228, 206 (2015)
Wang, M., Li, Y., Zhang, L.: Blind path region segmentation algorithm based on texture features. Inf. Commun. 07, 23–26 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, L., Zhang, PJ., Hu, PJ., Yang, L., Chang, KC. (2021). Research Method of Blind Path Recognition Based on DCGAN. In: Hassanien, A.E., Slowik, A., Snášel, V., El-Deeb, H., Tolba, F.M. (eds) Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2020. AISI 2020. Advances in Intelligent Systems and Computing, vol 1261. Springer, Cham. https://doi.org/10.1007/978-3-030-58669-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-58669-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58668-3
Online ISBN: 978-3-030-58669-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)