IMAGE MATCHING BASED HAZARDOUS MATERIAL DETECTION AND WARNING SYSTEM

Öz

Transportation of dangerous goods involves many critical situations that require safety and special precautions. In accordance with the regulations, hazardous materials, which include international standards, should be closely monitored and precautions should be taken in advance according to the situation. Artificial intelligence, image processing and data analysis techniques can be used to recognize and classify the labels of dangerous goods. This is important for early action in case of an emergency. If hazardous materials are not properly stored or transported according to safety precautions and rules, they can cause both material and moral damage. In this study, a hazardous material detection and warning system using AKAZE, ORB and SIFT image feature matching techniques is developed. To test the system, a dataset of multiple hazardous material labels with different scenes and conditions was created. The performances of feature matching techniques including image processing algorithms are examined through comparative analysis. As a result of image matching, label-related features and intervention information were retrieved from the database and displayed on the system interface. Experimental results show that the ORB technique is the best method for feature matching and accurate matching, and the AKAZE technique is the fastest feature detection method.

Anahtar Kelimeler

• Image processing
• image matching techniques
• AKAZE
• ORB
• SIFT
• hazardous materials

GÖRÜNTÜ EŞLEŞTİRME TABANLI TEHLİKELİ MADDE TESPİT VE UYARI SİSTEMİ

Öz

Tehlikeli maddelerin taşınması güvenlik ve özel önlemler gerektiren birçok kritik durumu içermektedir. Mevzuatlar gereğince uluslararası standartları içeren tehlikeli maddeler yakından takip edilmeli ve duruma göre önceden önlemler alınmalıdır. Yapay zeka, görüntü işleme ve veri analizi teknikleri, tehlikeli maddelerin etiketlerini tanıma ve sınıflandırma konusunda kullanılabilmektedir. Bu durum acil müdahale anında erken hareket etmek için önemlidir. Eğer tehlikeli maddeler güvenlik önlemlerine ve kurallarına göre uygun depolanmazsa veya taşınmazsa hem maddi hem de manevi zarara yol açabilmektedir. Bu çalışmada AKAZE, ORB ve SIFT görüntü özellik eşleştirme tekniklerini kullanan tehlikeli madde tespit ve uyarı sistemi geliştirilmiştir. Sistemi test etmek için farklı sahneleri ve koşulları içeren birden fazla tehlikeli madde etiketinden elde edilen bir veri seti oluşturulmuştur. Karşılaştırmalı analizler ile görüntü işleme algoritmalarını içeren özellik eşleştirme tekniklerinin performansları incelenmiştir. Görüntü eşleştirmesi sonucunda veri tabanından, etiketle ilgili özellikler ve müdahale bilgileri alınarak sistemin arayüzünde görüntülenmesi sağlanmıştır. Deneysel sonuçlar ORB tekniğinin özellik eşleştirmesi ve doğru eşleme konusunda en iyi yöntem olduğunu ve AKAZE tekniğinin en hızlı özellik bulan yöntem olduğunu göstermektedir.

Anahtar Kelimeler

• Görüntü işleme
• AKAZE
• ORB
• SIFT
• tehlikeli maddeler
• görüntü özellik eşleştirme teknikleri

Kaynakça

1. Alcantarilla, P. F., Bartoli, A., & Davison, A. J. (2012). KAZE features. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VI 12 (pp. 214-227). Springer Berlin Heidelberg.
2. Alcantarilla, P., Nuevo, J., & Bartoli, A. (2013). Fast explicit diffusion for accelerated features in nonlinear scale spaces. Procedings of the British Machine Vision Conference 2013.
3. Bay, H., Tuytelaars, T., & Van Gool, L. (2006). Surf: Speeded up robust features. In Computer Vision–ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part I 9 (pp. 404-417). Springer Berlin Heidelberg.
4. Brylka, R., Bierwirth, B., & Schwanecke, U. (2021). AI-based recognition of dangerous goods labels and metric package features. In Adapting to the Future: How Digitalization Shapes Susta-inable Logistics and Resilient Supply Chain Management. Proceedings of the Hamburg Inter-national Conference of Logistics (HICL), Vol. 31 (pp. 245-272). Berlin: epubli GmbH.
5. Calonder, M., Lepetit, V., Strecha, C., & Fua, P. (2010). Brief: Binary robust independent elemen-tary features. In Computer Vision–ECCV 2010: 11th European Conference on Computer Vi-sion, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV 11 (pp. 778-792). Springer Berlin Heidelberg.
6. Dalal, N., & Triggs, B. (2005, June). Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) (Vol. 1, pp. 886-893). IEEE.
7. Ellena, L. M., Olampi, S., & Guarnieri, F. (2004). Technological risks management: Automatic detection and identification of hazardous material transportation trucks. WIT Transactions on Ecology and the Environment, 77.
8. Fingas, M. F. (2002). The handbook of hazardous materials spills technology (pp. 35-1). McG-raw-Hill.

9. Forero, M. G., Mambuscay, C. L., Monroy, M. F., Miranda, S. L., Méndez, D., Valencia, M. O., & Gomez Selvaraj, M. (2021). Comparative analysis of detectors and feature descriptors for multispectral image matching in rice crops. Plants, 10(9), 1791.
10. Harris, C., & Stephens, M. (1988, August). A combined corner and edge detector. In Alvey Vision Conference (Vol. 15, No. 50, pp. 10-5244).
11. Ihmeida, M., & Wei, H. (2021, December). Image registration techniques and applications: Com-parative study on remote sensing imagery. In 2021 14th International Conference on Develop-ments in eSystems Engineering (DeSE) (pp. 142-148). IEEE.
12. Kamel, M. M., Hussein, S. I., Salama, G. I., & Elhalwagy, Y. Z. (2020, July). Efficient Target Detection Technique Using Image Matching Via Hybrid Feature Descriptors. In 2020 12th In-ternational Conference on Electrical Engineering (ICEENG) (pp. 102-107). IEEE.
13. Kortli, Y., Jridi, M., Al Falou, A., & Atri, M. (2018). A comparative study of CFs, LBP, HOG, SIFT, SURF, and BRIEF for security and face recognition. In Advanced Secure Optical Image Processing for Communications (pp. 13-1). Bristol, UK: IOP Publishing.
14. Leutenegger, S., Chli, M., & Siegwart, R. Y. (2011, November). BRISK: Binary robust invariant scalable keypoints. In 2011 International Conference on Computer Vision (pp. 2548-2555). IEEE.
15. Lowe, D. G. (1999, September). Object recognition from local scale-invariant features. In Proceedings of the Seventh IEEE International Conference on Computer Vision (Vol. 2, pp. 1150-1157). IEEE.
16. Lu, X., Ruan, C., Li, R., Xie, T., & Xu, H. (2019, July). Comparative study on safe storage of dangerous goods containers in port areas. In 2019 5th International Conference on Transporta-tion Information and Safety (ICTIS) (pp. 608-610). IEEE.
17. Mohamed, M. A., Tünnermann, J., & Mertsching, B. (2018, August). Seeing Signs of Danger: Attention-Accelerated Hazmat Label Detection. In 2018 IEEE International Symposium on Sa-fety, Security, and Rescue Robotics (SSRR) (pp. 1-6). IEEE.
18. National Academies of Sciences Transportation Research Board and National Research Council. (2010). Technologies and Approaches to Reducing the Fuel Consumption of Medium- and He-avy-Duty Vehicles. Washington, DC: The National Academies Press.
19. Oad, A., Kumari, K., Hussain, I., Dong, F., Hammad, B., & Oad, R. (2022). Performance compa-rison of ORB, SURF and SIFT using Intracranial Haemorrhage CTScan Brain ima-ges. International Journal of Artificial Intelligence & Mathematical Sciences, 1(2), 26-34.
20. Ojala, T., Pietikäinen, M., & Mäenpää, T. (2001). A generalized local binary pattern operator for multiresolution gray scale and rotation invariant texture classification. In Advances in Pattern Recognition—ICAPR 2001: Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings 2 (pp. 399-408). Springer Berlin Heidelberg.
21. OpenCV. (2024a). AKAZE local features matching. Retrieved May 17, 2024, from https://docs.opencv.org/3.4/db/d70/tutorial_akaze_matching.html
22. OpenCV. (2024b). Basics of Brute-Force Matcher. Retrieved May 17, 2024, from https://docs.opencv.org/4.x/dc/dc3/tutorial_py_matcher.html
23. Rosten, E., & Drummond, T. (2006). Machine learning for high-speed corner detection. In Computer Vision–ECCV 2006: 9th European Conference on Computer Vision, Graz, Aust-ria, May 7-13, 2006. Proceedings, Part I 9 (pp. 430-443). Springer Berlin Heidelberg.
24. Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011, November). ORB: An efficient alter-native to SIFT or SURF. In 2011 International Conference on Computer Vision (pp. 2564-2571). IEEE.
25. Sharifi, A., Zibaei, A., & Rezaei, M. (2021). A deep learning based hazardous materials (HAZ-MAT) sign detection robot with restricted computational resources. Machine Learning with Applications, 6, 100104.
26. Shi, J., & Tomasi, C. (1994, June). Good features to track. In 1994 Proceedings of IEEE Confer-ence on Computer Vision and Pattern Recognition (pp. 593-600). IEEE.
27. Tareen, S. A. K., & Raza, R. H. (2023, March). Potential of SIFT, SURF, KAZE, AKAZE, ORB, BRISK, AGAST, and 7 More Algorithms for Matching Extremely Variant Image Pairs. In 2023 4th International Conference on Computing, Mathematics and Engineering Technolo-gies (iCoMET) (pp. 1-6). IEEE.
28. Tareen, S. A. K., & Saleem, Z. (2018, March). A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK. In 2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET) (pp. 1-10). IEEE.
29. UNECE. (2024). UN Recommendations on the Transport of Dangerous Goods - Model Regula-tions Nature, Purpose and Significance of the Recommendations. Retrieved May 17, 2024, from https://unece.org/about-recommendations
30. U.S. Department of Transportation Federal Motor Carrier Safety Administration. (2022). How to Comply with Federal Hazardous Materials Regulations. Retrieved May 17, 2024, from https://www.fmcsa.dot.gov/regulations/hazardous-materials/how-comply-federal-hazardous-materials-regulations U.S. Department of Transportation Pipeline and Hazardous Materials Safety Administration. (2022). U.S. Department of Transportation Announces Over $32 Million in Grants to Support Local Hazardous Materials Safety Efforts. Retrieved May 17, 2024, from https://www.phmsa.dot.gov/news/us-department-transportation-announces-over-32-million-grants-support-local-hazardous
31. U.S. Department of Transportation Pipeline and Hazardous Materials Safety Administration. (2004). Guide for Preparing Hazardous Materials Incidents Reports.
32. U.S. Environmental Protection Agency. (2024). Learn the Basics of Hazardous Waste. Retrieved May 17, 2024, from https://www.epa.gov/hw/learn-basics-hazardous-waste
33. Watcharejyothin, M., Nishimura, K., & Marinov, M. (2022). Challenges of dangerous goods transport by rail in Thailand. Sustainable Rail Transport 4: Innovate Rail Research and Educa-tion, 325-339.