Abstract
The paper considers the issues of trajectory tracking of a large number of objects on video images in modes close to real time. To implement such support, a combination of algorithms based on the YOLO v3 convolutional neural network (CNN), doubly stochastic filters and pseudo-gradient procedures for aligning image fragments is proposed. The obtained numerical performance characteristics show the consistency of such a combination and the possibility of its application in real video processing systems.
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
Bouman, C.: Model Based Imaging Processing. Purdue University 414 (2013)
Jensen, J.: Introductory digital image processing: a remote sensing perspective. Pearson Educ. 659 (2015)
Basener, W., Ientilucci, E., Messinger, D.: Anomaly detection using topology. Algorithms Technol. Multispectral Hyperspectral Ultraspectral Imagery XIII SPIE 6565, 22–34 (2007)
Denisova, A., Myasnikov, V.: Detection of anomalies in hyperspectral images. Comput. Opt. 38(2), 287–296 (2013)
Krasheninnikov, V., Vasil’ev, K.: Multidimensional image models and processing. Intell. Syst. Ref. Lib. 135, 11–64 (2018)
Vasiliev, K., Pavlygin, E., Gutorov, A.: Multi-model algorithms of data processing of the mobile radar system. Autom. Control Processes 4, 6–13 (2013)
Andriyanov, N., Vasil’ev, K., Dement’ev, V.: Investigation of filtering and objects detection algorithms for a multizone image sequence. Int. Arch. Photogrammetry Remote Sens. Spat. Inf. Sci.—ISPRS Arch. 42, 7–10. (2019). doi: https://doi.org/10.5194/isprs-archives-XLII-2-W12-7-2019
Kondrat’ev, D.: Primary detection of elements on the radar image. Radioelectronic Equipment 1(7), 135–136 (2015)
Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference Proceedings, 1, 6517–6525 (2017)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv, pp. 1–11 (2018)
Vasiliev, K., Dementyev, V.: Doubly stochastic filtration of spatially inhomogeneous images. J. Commun. Technol. Electron. 65(5), 524–531 (2020)
Andriyanov, N., Dementiev, V., Vasiliev, K.: Developing a filtering algorithm for doubly stochastic images based on models with multiple roots of characteristic equations. Patt. Recogn. Image Anal. 29(1), 10–20 (2019). https://doi.org/10.1134/S1054661819010048
Magdeev, R., Tashlinskii, A.: Efficiency of object identification for binary images. Comput. Opt. 2, 277–281 (2019)
Tashlinskii, A.: Pseudogradient Estimation of Digital Images Interframe Geometrical Deformations. Vision Syst.: Segmentation Pattern Recogn. 1, 465–494 (2007)
Krasheninnikov, V., Kuvayskova, Y.., Subbotin, A.: Pseudo-gradient algorithm for identification of doubly stochastic cylindrical image model. Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 24th International Conference KES-2020. Procedia Computer Science, vol. 176, pp. 1858–1867 (2020)
Acknowledgements
The reported study was funded by RFBR grants, Projects No. 19-29-09048 and No. 18-47-730009.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Andriyanov, N., Dementiev, V., Kondratiev, D. (2021). Tracking of Objects in Video Sequences. In: Czarnowski, I., Howlett, R.J., Jain, L.C. (eds) Intelligent Decision Technologies. Smart Innovation, Systems and Technologies, vol 238. Springer, Singapore. https://doi.org/10.1007/978-981-16-2765-1_21
Download citation
DOI: https://doi.org/10.1007/978-981-16-2765-1_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2764-4
Online ISBN: 978-981-16-2765-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)