Person Registration in CCTV
Abstract
The problem of suppressing false detections in video is relevant for large video surveillance systems, since it leads to an increase in the load on equipment and operators in situational centers. Also, due to the peculiarities of face recognition algorithms, false detections often lead to false positives of identification algorithms. Since in most systems, unique faces are counted through optical tracking of faces, it is important not to count twice one person when the trajectory is lost due to tracking algorithm errors or obstructions in scene. The paper proposes an approach that allows you to register the passage of people under the condition of overlap in the scene, which is important both for solving statistical problems and for face identification systems, where duplicate faces lead to an increased load on system operators and equipment. The proposed algorithm insignificantly increases the computational load, so it can be used on on-board devices with limited computing resources and increase the effectiveness of utilization of network connections.
References
[2] Zhou D., He Q. Cascaded Multi-Task Learning of Head Segmentation and Density Regression for RGBD Crowd Counting. IEEE Access. 2020; 8:101616-101627. (In Eng.) DOI: https://doi.org/10.1109/ACCESS.2020.2998678
[3] Liciotti D., Cenci A., Frontoni E., Mancini A., Zingaretti P. An Intelligent RGB-D Video System for Bus Passenger Counting. In: Chen W., Hosoda K., Menegatti E., Shimizu M., Wang H. (ed.) Intelligent Autonomous Systems 14. IAS 2016. Advances in Intelligent Systems and Computing. 2017; 531:473-484. Springer, Cham. (In Eng.) DOI: https://doi.org/10.1007/978-3-319-48036-7_34
[4] Liu W. et al. SSD: Single Shot MultiBox Detector. In: Leibe B., Matas J., Sebe N., Welling M. (ed.) Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science. 2016; 9905:21-37. Springer, Cham. (In Eng.) DOI: https://doi.org/10.1007/978-3-319-46448-0_2
[5] Shi J., Tomasi Good features to track. In: 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA; 1994. p. 593-600. (In Eng.) DOI: https://doi.org/10.1109/CVPR.1994.323794
[6] Li H., Li Y., Porikli F. Robust Online Visual Tracking with a Single Convolutional Neural Network. In: Cremers D., Reid I., Saito H., Yang MH. (ed.) Computer Vision - ACCV 2014. ACCV 2014. Lecture Notes in Computer Science. 2015; 9007:194-209. Springer, Cham. (In Eng.) DOI: https://doi.org/10.1007/978-3-319-16814-2_13
[7] Lin C., Hung Y. A Prior-Less Method for Multi-face Tracking in Unconstrained Videos. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA; 2018. p. 538-547. (In Eng.) DOI: https://doi.org/10.1109/CVPR.2018.00063
[8] Munkres J. Algorithms for the Assignment and Transportation Problems. Journal of the Society for Industrial and Applied Mathematics. 1957; 5(1):32-38. (In Eng.) DOI: https://doi.org/10.1137/0105003
[9] Deng J., Guo J., Xue N., Zafeiriou S. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA; 2019. p. 4685-4694. (In Eng.) DOI: https://doi.org/10.1109/CVPR.2019.00482
[10] Chen T. et al. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. arXiv:1512.01274, 2015. Available at: https://arxiv.org/abs/1512.01274 (accessed 11.08.2020). (In Eng.)
[11] Bagrov N.Y., Konushin A.S., Konushin V.S. A Semi-Automatic Method of Collecting Samples for Learning a Face Identification Algorithm. Programming and Computer Software. 2019; 45(3):133-139. (In Eng.) DOI: https://doi.org/10.1134/S0361768819030022
[12] Guo Y., Zhang L., Hu Y., He X., Gao J. MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition. In: Leibe B., Matas J., Sebe N., Welling M. (ed.) Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science. 2016; 9907:87-102. Springer, Cham. (In Eng.) DOI: https://doi.org/10.1007/978-3-319-46487-9_6
[13] Yi D., Lei Z., Liao S., Li S.Z. Learning Face Representation from Scratch. arXiv:1411.7923, 2014. Available at: https://arxiv.org/abs/1411.7923 (accessed 11.08.2020). (In Eng.)
[14] Lisin N., Gromov A., Konushin V., Konushin A. Improving the Neural Network Algorithm for Assessing the Quality of Facial Images. CEUR Workshop Proceedings. 2020; 2744. Article 28. Available at: http://ceur-ws.org/Vol-2744/paper28.pdf (accessed 11.08.2020). (In Eng.)
[15] Nasrollahi K., Moeslund T.B. Face Quality Assessment System in Video Sequences. In: Schouten B., Juul N.C., Drygajlo A., Tistarelli M. (ed.) Biometrics and Identity Management. BioID 2008. Lecture Notes in Computer Science. 2008; 5372:10-18. Springer, Berlin, Heidelberg. (In Eng.) DOI: https://doi.org/10.1007/978-3-540-89991-4_2
[16] Wong Y., Chen S., Mau S., Sanderson C., Lovell B.C. Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition. In: CVPR 2011 WORKSHOPS. Colorado Springs, CO, USA; 2011. p. 74-81. (In Eng.) DOI: https://doi.org/10.1109/CVPRW.2011.5981881
[17] Nikitin M.Yu., Konushin V.S., Konushin A.S. Neural network model for video-based face recognition with frames quality assessment. Computer Optics. 2017; 41(5):732-742. (In Russ., abstract in Eng.) DOI: https://doi.org/10.18287/2412-6179-2017-41-5-732-742
[18] Vignesh S., Priya K. V. S. N. L. M., Channappayya S.S. Face image quality assessment for face selection in surveillance video using convolutional neural networks. In: 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP). Orlando, FL, USA; 2015. p. 577-581. (In Eng.) DOI: https://doi.org/10.1109/GlobalSIP.2015.7418261
[19] Koide K., Menegatti E., Carraro M., Munaro M., Miura J. People tracking and re-identification by face recognition for RGB-D camera networks. In: 2017 European Conference on Mobile Robots (ECMR). Paris, France; 2017. p. 1-7. (In Eng.) DOI: https://doi.org/10.1109/ECMR.2017.8098689
[20] Wang Y., Shen J., Petridis S., Pantic M. A real-time and unsupervised face re-identification system for human-robot interaction. Pattern Recognition Letters. 2019; 128:559-568. (In Eng.) DOI: https://doi.org/10.1016/j.patrec.2018.04.009
[21] Kalaiselvi P., Nithya S. Face Recognition System under Varying Lighting Conditions. IOSR Journal of Computer Engineering. 2013; 14(3):79-88. (In Eng.) DOI: https://doi.org/10.9790/0661-1437988
[22] Adini Y., Moses Y., Ullman S. Face recognition: the problem of compensating for changes in illumination direction. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997; 19(7):721-732. (In Eng.) DOI: https://doi.org/10.1109/34.598229
[23] Nikitin M.Yu., Konushin V.S., Konushin A.S. Face anti-spoofing with joint spoofing medium detection and eye blinking analysis. Computer Optics. 2019; 43(4):618-626. (In Eng.) DOI: https://doi.org/10.18287/2412-6179-2019-43-4-618-626
[24] Bradski G., Kaehler A. Learning OpenCV. O'Reilly Media, Inc.; 2008. (In Eng.)
[25] Yu Q., Cheng H.H., Cheng W.W., Zhou X. Ch OpenCV for interactive open architecture computer vision. Advances in Engineering Software. 2004; 35(8-9):527-536. (In Eng.) DOI: https://doi.org/10.1016/j.advengsoft.2004.05.003
This work is licensed under a Creative Commons Attribution 4.0 International License.
Publication policy of the journal is based on traditional ethical principles of the Russian scientific periodicals and is built in terms of ethical norms of editors and publishers work stated in Code of Conduct and Best Practice Guidelines for Journal Editors and Code of Conduct for Journal Publishers, developed by the Committee on Publication Ethics (COPE). In the course of publishing editorial board of the journal is led by international rules for copyright protection, statutory regulations of the Russian Federation as well as international standards of publishing.
Authors publishing articles in this journal agree to the following: They retain copyright and grant the journal right of first publication of the work, which is automatically licensed under the Creative Commons Attribution License (CC BY license). Users can use, reuse and build upon the material published in this journal provided that such uses are fully attributed.
