Аналіз методів та засобів комп’ютерного зору для мобільних систем пошуку вибухонебезпечних предметів

В.В. Міщук, аспірант, Г.В. Фесенко, д-р техн. наук
Національний аерокосмічний університет ім. М.Є. Жуковського
«Харківський авіаційний інститут»
Україна, 61070, Харків, вул. Чкалова, 17
тел. +38 (066) 0897423, е-mail: Ця електронна адреса захищена від спам-ботів. Вам необхідно увімкнути JavaScript, щоб побачити її.;
тел. +38 (097) 2415366, е-mail: Ця електронна адреса захищена від спам-ботів. Вам необхідно увімкнути JavaScript, щоб побачити її.

Èlektron. model. 2024, 46(1):90-111

https://doi.org/10.15407/emodel.46.01.090

АНОТАЦІЯ

Наведено результати аналізу літературних джерел з питань застосування систем комп’ютерного зору для виявлення вибухонебезпечних предметів (ВНП). Розглянуто іс­нуючі підходи до застосування комп’ютерного зору для виявлення ВНП. Значну увагу приділено джерелам, що розглядають методи виявлення об’єктів. Проаналізовано мет­ри­ки та набори даних, які використовуються при оцінюванні методів виявлення об’єктів в комп’ютерному зорі, описані тенденції розвитку цих методів. Зроблено висновки щодо можливостей застосування тих чи інших методів для виявлення ВНП з урахуванням об­межень мобільних платформ. Виділено перспективні напрямки досліджень.

КЛЮЧОВІ СЛОВА:

комп’ютерний зір, виявлення об’єктів, розмінування, мобільні платформи, вибухонебезпечні предмети.

СПИСОК ЛІТЕРАТУРИ

1. Landmine monitor. 2022 | reports | monitor. Landmine and Cluster Munition Monitor | URL: http://www.the-monitor.org/en-gb/reports/2022/landmine-monitor-2022.aspx (date of access: 08.10.2023).
2. 30 % території України заміновано. За масштабами це як дві території держави Австрія, ― Сергій Крук. Державна служба України з надзвичайних ситуацій. URL: https://dsns.gov.ua/uk/news/ostanni-novini/30-teritoriyi-ukrayini-zaminovano-za-masstabami- ce-yak-dvi-teritoriyi-derzavi-avstriya-sergii-kruk (дата звернення: 08.10.2023).
3. Robotic-biological systems for detection and identification of explosive ordnance: concept, general structure, and models / G. Fedorenko et al. Radioelectronic and computer systems. 2023. Vol. 106 No. 2. P. 143–159. URL: https://doi.org/10.32620/reks.2023.2.12 (date of access: 08.10.2023).
4. Olson C.F., Matthies L.H. Visual ordnance recognition for clearing test ranges. Aerospace/Defense sensing and controls, Orlando, FL / ed. by A. C. Dubey, J.F. Harvey, J.T. Broach. 1998. URL: https://doi.org/10.1117/12.324184 (date of access: 08.10.2023).
5. Geo-Mapping and visual stitching to support landmine detection using a low-cost UAV / J. Colorado et al. International journal of advanced robotic systems. 2015. Vol. 12, no. 9. P. 125. URL: https://doi.org/10.5772/61236 (date of access: 08.10.2023).
6. Achkar R. Implementation of a vision system for a landmine detecting robot using artificial neural network. International journal of artificial intelligence & applications. 2012. Vol. 3, no. 5. P. 73–92. URL: https://doi.org/10.5121/ijaia.2012.3507 (date of access: 08.10.2023).
7. Harvey A., LeBrun E. Computer vision detection of explosive ordnance: A high-performance 9N235/9N210 cluster submunition detector. The journal of conventional weapons destruction. 2023. Vol. 27, no. 2. URL: https://commons.lib.jmu.edu/cisr-journal/ vol27/iss2/9 (date of access: 08.10.2023).
8. Alternatives for landmine detection. RAND Corporation, 2003. URL: https://doi.org/ 10.7249/mr1608 (date of access: 08.10.2023).
9. Optical detection of buried explosive hazards: a longitudinal comparison of three types of imagery / J.J. Staszewski et al. SPIE defense, security, and sensing, Baltimore, Maryland, USA / ed. by J.T. Broach, J.C. Isaacs. 2013. URL: https://doi.org/10.1117/12.2018092 (date of access: 08.10.2023).
10. Optical cues for buried landmine detection / C.A. Hibbitts et al. SPIE defense, security, and sensing, Orlando, Florida, USA / ed. by R. S. Harmon, J. T. Broach, J. H. Holloway, Jr. 2009. URL: https://doi.org/10.1117/12.818753 (date of access: 08.10.2023).
11. Kaya S., Leloglu U.M. Buried and surface mine detection from thermal image time series. IEEE journal of selected topics in applied earth observations and remote sensing. 2017. Vol. 10, no. 10. P. 4544–4552. URL: https://doi.org/10.1109/jstars.2016.2639037 (date of access: 08.10.2023).
12. Applying deep learning to automate UAV-based detection of scatterable landmines / J. Baur et al. Remote sensing. 2020. Vol. 12, no. 5. P. 859. URL: https://doi.org/10.3390/ rs12050859 (date of access: 08.10.2023).
13. Joint fusion and detection via deep learning in UAV-borne multispectral sensing of scatterable landmine / Z. Qiu et al. Sensors. 2023. Vol. 23, no. 12. P. 5693. URL: https://doi.org/10.3390/s23125693 (date of access: 08.10.2023).
14. Keypoint-based image processing for landmine detection in GPR data / R.T. Sakaguchi et al. SPIE defense, security, and sensing, Baltimore, Maryland, USA / ed. by J.T. Broach, J.H. Holloway. 2012. URL: https://doi.org/10.1117/12.918361 (date of access: 08.10.2023).
15. Histograms of oriented gradients for landmine detection in ground-penetrating radar data / P.A. Torrione et al. IEEE transactions on geoscience and remote sensing. 2014. Vol. 52, no. 3. P. 1539-1550. URL: https://doi.org/10.1109/tgrs.2013.2252016 (date of access: 08.10.2023).
16. Gauss gradient and SURF features for landmine detection from GPR images / F.M. El-Ghamry et al. Computers, materials & continua. 2022. Vol. 71, no. 3. P. 4457-4487. URL: https://doi.org/10.32604/cmc.2022.022328 (date of access: 08.10.2023).
17. Ground penetrating radar for buried explosive devices detection: a case studies review / A. Machado Brito-da-Costa et al. Australian journal of forensic sciences. 2021. P. 1-20. URL: https://doi.org/10.1080/00450618.2020.1865453 (date of access: 08.10.2023).
18. A comprehensive review of conventional and deep learning approaches for ground-penetrating radar detection of raw data / X. Bai et al. Applied sciences. 2023. Vol. 13, no. 13. 7992. URL: https://doi.org/10.3390/app13137992 (date of access: 08.10.2023).
19. Tellez O. L.L., Scheers B. Ground‐Penetrating radar for close‐in mine detection. Mine action ― the research experience of the royal military academy of belgium. 2017. URL: https://doi.org/10.5772/67007 (date of access: 08.10.2023).
20. Dorn A.W. Eliminating hidden killers: how can technology help humanitarian demining?. Stability: international journal of security and development. 2019. Vol. 8, no. 1. URL: https://doi.org/10.5334/sta.743 (date of access: 08.10.2023).
21. Object detection in 20 years: a survey / Z. Zou et al. Proceedings of the IEEE. 2023. P. 1–20. URL: https://doi.org/10.1109/jproc.2023.3238524 (date of access: 08.10.2023).
22. Paniego S., Sharma V., Cañas J.M. Open source assessment of deep learning visual object Sensors. 2022. Vol. 22, no. 12. P. 4575. URL: https://doi.org/10.3390/s22124575 (date of access: 08.10.2023).
23. Ceccarelli A., Montecchi L. Evaluating object (mis)detection from a safety and reliability perspective: discussion and measures. IEEE access. 2023. P. 1. URL: https://doi.org/ 10.1109/access.2023.3272979 (date of access: 08.10.2023).
24. Risk ranked recall: collision safety metric for object detection systems in autonomous vehicles / A. Bansal et al. 2021 10th mediterranean conference on embedded computing (MECO), Budva, Montenegro, 7-10 June 2021. 2021. URL: https://doi.org/10.1109/ meco52532.2021.9460196 (date of access: 08.10.2023).
25. Object detection with deep learning: a review / Z.-Q. Zhao et al. IEEE transactions on neural networks and learning systems. 2019. Vol. 30, no. 11. P. 3212-3232. URL: https://doi.org/10.1109/tnnls.2018.2876865 (date of access: 08.10.2023).
26. Deep learning vs. traditional computer vision / N. O’Mahony et al. Advances in intelligent systems and computing. Cham, 2019. P. 128-144. URL: https://doi.org/10.1007/978-3-030-17795-9_10 (date of access: 08.10.2023).
27. Viola P., Jones M. Rapid object detection using a boosted cascade of simple features. 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, Kauai, HI, USA. URL: https://doi.org/10.1109/cvpr.2001.990517 (date of access: 08.10.2023).
28. Dalal N., Triggs B. Histograms of oriented gradients for human detection. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), San Diego, CA, USA. URL: https://doi.org/10.1109/cvpr.2005.177 (date of access: 08.10.2023).
29. Lowe D. G. Distinctive image features from scale-invariant keypoints. International journal of computer vision. 2004. Vol. 60, no. 2. P. 91-110. URL: https://doi.org/10.1023/ b:visi.0000029664.99615.94 (date of access: 08.10.2023).
30. Tareen S.A.K., Saleem Z.A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK. 2018 international conference on computing, mathematics and engineering technologies (icomet), Sukkur, 3-4 March 2018. 2018. URL: https://doi.org/10.1109/ icomet.2018.8346440 (date of access: 08.10.2023).
31. Krizhevsky A., Sutskever I., Hinton G. E. ImageNet classification with deep convolutional neural networks. Communications of the ACM. 2017. Vol. 60, no. 6. P. 84-90. URL: https://doi.org/10.1145/3065386 (date of access: 08.10.2023).
32. Rich feature hierarchies for accurate object detection and semantic segmentation / R. Girshick et al. 2014 IEEE conference on computer vision and pattern recognition (CVPR), Columbus, OH, USA, 23-28 June 2014. 2014. URL: https://doi.org/10.1109/cvpr.2014.81 (date of access: 08.10.2023).
33. Deep learning for generic object detection: a survey / L. Liu et al. International journal of computer vision. 2019. Vol. 128, no. 2. P. 261-318. URL: https://doi.org/10.1007/s11263-019-01247-4 (date of access: 08.10.2023).
34. Super sparse 3D object detection / L. Fan et al. IEEE transactions on pattern analysis and machine intelligence. 2023. P. 1-16. URL: https://doi.org/10.1109/tpami.2023.3286409 (date of access: 08.10.2023).
35. Transformer-based stereo-aware 3D object detection from binocular images / H. Sun et al. IEEE transactions on intelligent transportation systems. 2023. Vol. XX. URL: https://arxiv.org/abs/2304.11906v2 (date of access: 08.10.2023).
36. TransVOD: end-to-end video object detection with spatial-temporal transformers / Q. Zhou et al. IEEE transactions on pattern analysis and machine intelligence. 2022. P. 1-16. URL: https://doi.org/10.1109/tpami.2022.3223955 (date of access: 08.10.2023).
37. AlDahoul N., Md Sabri A.Q., Mansoor A.M. Real-Time human detection for aerial captured video sequences via deep models. Computational intelligence and neuroscience. 2018. Vol. 2018. P. 1-14. URL: https://doi.org/10.1155/2018/1639561 (date of access: 08.10.2023).
38. Faster R-CNN: towards real-time object detection with region proposal networks / S. Ren et al. IEEE transactions on pattern analysis and machine intelligence. 2017. Vol. 39, no. 6. P. 1137-1149. URL: https://doi.org/10.1109/tpami.2016.2577031 (date of access: 08.10.2023).
39. You only look once: unified, real-time object detection / J. Redmon et al. 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, 27-30 June 2016. 2016. URL: https://doi.org/10.1109/cvpr.2016.91 (date of access: 08.10.2023).
40. An image is worth 16x16 words: transformers for image recognition at scale / A. Dosovitskiy et al. ICLR 2021 — 9th international conference on learning representations. 2020. URL: https://arxiv.org/abs/2010.11929v2 (date of access: 08.10.2023).
41. End-to-End object detection with transformers / N. Carion et al. Computer vision — ECCV 2020. Cham, 2020. P. 213-229. URL: https://doi.org/10.1007/978-3-030-58452-8_13 (date of access: 08.10.2023).
42. A survey on vision transformer / K. Han et al. IEEE transactions on pattern analysis and machine intelligence. 2022. P. 1. URL: https://doi.org/10.1109/tpami.2022.3152247 (date of access: 08.10.2023).
43. Are transformers more robust than CNNs? / Y. Bai et al. Advances in neural information processing systems. 2021. Vol. 32. P. 26831-26843. URL: https://arxiv.org/abs/2111. 05464v1.
44. Maurício J., Domingues I., Bernardino J. Comparing vision transformers and convolutional neural networks for image classification: a literature review. Applied sciences. 2023. Vol. 13, no. 9. P. 5521. URL: https://doi.org/10.3390/app13095521 (date of access: 08.10.2023).
45. Towards large-scale small object detection: survey and benchmarks / G. Cheng et al. IEEE transactions on pattern analysis and machine intelligence. 2023. P. 1-20. URL: https://doi.org/10.1109/tpami.2023.3290594 (date of access: 08.10.2023).

Повний текст: PDF