Abstract
This paper proposes a neural network-based monocular vision ranging method for the situation of large camera calibration and distance variation in monocular vision ranging. The imaging size of the corresponding target under different distances of the same camera is recorded, and the distance variation is recorded according to the change of the imaging size, and a dataset is made accordingly. The ranging network model is established by referring to the neural network and trained on the dataset. The yolov7 target detection network is combined with the ranging network, and real-time ranging is performed according to the real-time target frame output by the target detection network. The monocular vision ranging method in this paper avoids the complex calibration of the camera’s internal parameters, has a simple structure, fast operation speed, low cost and easy implementation. The training results of this paper’s ranging method show that the average distance error is 0.1m within 20m range, which meets the accuracy requirements and verifies the feasibility and effectiveness of this method by real-time ranging experiment.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Du, Y., Chen, M.: Research on vehicle distance detection algorithm with single and double camera switching. Control Eng. China 26(2), 327–335 (2019). https://doi.org/10.14107/j.cnki.kzgc.161359
Hu, J., Zhang, F., Li, Z., Huang, H.: Research on indoor 3D measurement algorithm based on binocular technology. Comput. Meas. Control 27(9), 66–70 (2019). https://doi.org/10.16526/j.cnki.11-4762/tp.2019.09.015
Yang, P.: Forward vehicle detection and ranging algorithm based on deep learning. Xi’an University of Electronic Science and Technology, pp. 37–54 (2019). https://doi.org/10.27389/d.cnki.gxadu/2019.002695
Yang, W., Wei, L., Gong, J., Zhang, Q.: The research of longitudinal vehicle spacing detection based on monocular vision. Comput. Meas. Control 20(08), 2039–2041 (2012). https://doi.org/10.16526/j.cnki.11-4762/tp.2012.08.061
Ki, P., Sun, H.: Robust range estimation with a monocular camera for vision-based forward collision warning system. Sci. World J. (2014). http://dx.doi.org/10.1155/2014/923632
Deng, B., Hao, L.: Survey of target detection based on neural network. J. Phys.: Conf. Ser. 1952(2) (2021). https://doi.org/10.1088/1742-6596/1952/2/022055
Lin, C., Su, F., Wang, H., Gao, J.: A camera calibration method for obstacle distance measurement based on monocular vision. In: 4th International Conference on Communication Systems & Network Technologies, pp. 1148–1151. IEEE Computer Society, India (2014). https://doi.org/10.1109/CSNT.2014.233
Chen, X., Zhang, M., Ruan, K., Gong, C., Zhang, Y., Yang, S.: A ranging model based on bp neural network. Intell. Autom. Soft Comput. 22(2), 325–329 (2015). https://doi.org/10.1080/10798587.2015.1095484
Han, Y., Zhang, Z., Dai, M., Gong, C., Zhang, Y., Yang, S.: Monocular vision measurement method for target ranging. Opt. Precis. Eng. 19(05), 1110–1117 (2011). https://doi.org/10.3788/OPE.20111905.1110
Qu, Y., Liu, Z., Jiang, Y., Zhou, D., Wang, Y.: Adaptive variable scale feature point extraction method. Opt. Precis. Eng. 25(1), 188–197 (2017). https://doi.org/10.3788/OPE.20172501.0188
Guo, L., Xu, Y., Li, K., Lian, X.: Research on real-time ranging method based on monocular vision. China J. Image Graph. 1, 74–81 (2006). https://doi.org/10.3969/j.issn.1006-8961.2006.01.012
Kehtarnavaz, N., Oh, H.J.: Development and real-time implementation of a rule-based auto-focus algorithm. Real-Time Imaging 9(3), 197–203 (2015). https://doi.org/10.1016/S1077-2014(03)00037-8
Li, Y., Yuan, H., Wang, Y., Xiao, C.: GGT-YOLO: a novel object detection algorithm for drone-based maritime cruising. Drones 6(11), 335 (2022). https://doi.org/10.3390/drones6110335
Jia, S., Peng, W., Qin, Z., Hong, Q.: Overview of camera calibration for computer vision. In: Proceeding of the 11th World Congress on Intelligent Control & Automation, pp. 86–92 IEEE, Shenyang (2015). https://doi.org/10.1109/WCICA.2014.7052692
Zhang, Y., Lao, W., Yu, X., Li, J.: Weight and structure determination of forward neural network with two-input power excitation. Comput. Eng. Appl. 48(15), 102–106+122 (2012). https://doi.org/10.3778/j.issn.1002-8331.2012.15.022
Li, Y., Fan, N., Jiang, W., Yang, J., Song, T., Zhao, Q.: Research on intelligent desk area recognition method based on BP neural network. Electr. Meas. Instrum. 54(3), 25–30 (2017). CNKI:SUN:DCYQ.0.2017-03-005
Ketkar, N., Moolayil, J.: Introduction to PyTorch. In: Deep Learning with Python, pp. 27–91. Apress, Berkeley (2021). http://hdl.handle.net/1853/58786
Xu, X., Ma, Y., Qian, X.: Scale-aware real-time pedestrian detection in auto-driving scenes. China J. Image Graph. 26(1), 93–100 (2021)
Wu, X.: Research on image labeling algorithm based on convolution neural network. Suzhou University, Suzhou (2019). https://doi.org/10.27351/d.cnki.gszhu.2019.001284
Wang, C.Y., Bochkovskiy, A., Liao, H.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv e-prints (2022). https://doi.org/10.48550/arXiv.2207.02696
Acknowledgments
Thank you to the anonymous reviewers for their detailed suggestions and the editors for their hard work in this meeting. The research is Partially funded by the Applied Basic Research Program of Liaoning Province (grant no. 2022JH2/101300254) and the Postgraduate Education Reform Project of Liaoning Province (LNYJG2022101). Thank you very much again for the funding from these funds.In addition, the successful completion of this article is inseparable from the guidance and assistance of Professor Zeng Pengfei. Here, I would also like to thank Professor Hao Yongping, brothers Bu Guoliang, and brothers Cao Zhaorui for their guidance and assistance.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, X., Zeng, P., Cao, Z., Bu, G., Hao, Y. (2023). A Monocular Vision Ranging Method Related to Neural Networks. In: Fujita, H., Wang, Y., Xiao, Y., Moonis, A. (eds) Advances and Trends in Artificial Intelligence. Theory and Applications. IEA/AIE 2023. Lecture Notes in Computer Science(), vol 13925. Springer, Cham. https://doi.org/10.1007/978-3-031-36819-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-36819-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36818-9
Online ISBN: 978-3-031-36819-6
eBook Packages: Computer ScienceComputer Science (R0)