DÜZENSİZ GÖÇ, KAÇAKÇILIK VE TERÖRE KARŞI İKİNCİ SAVUNMA HATTINDA YAPAY ZEKA DESTEKLİ GÖZETLEME SİSTEMİ ÖNERİSİ: JANDARMA DEGERLENDİRMESİ

Öz

Sınır birliklerince korunmakta olan hudut hattındaki fiziksel ve teknolojik tedbirlere rağmen, ikinci hat olarak tasvir edilen jandarma sorumluluk alanında Jandarma unsurlarınca çok sayıda düzensiz göçmen yakalanmaktadır. Bu durum, düzensiz göç hareketleri, kaçakçılık ve benzeri suçların önlenmesi ile terörle mücadele bağlamında Jandarma için önemli bir sorumluluk oluşturmaktadır. Bu nedenle, hudut hattının gerisinde Jandarma sorumluluk sahasında yapay zekâ destekli teknolojik keşif ve gözetleme tedbirlerinin alınması önerilmektedir. Bu teknolojik önlemlerin, düzensiz göç hareketlerini engelleme, kaçakçılık faaliyetlerini sınırlandırma ve terörle mücadelede etkinlik sağlama konusunda faydalı olabileceği düşünülmektedir. Bu tedbirlerin uygulanması, emniyet ve asayişi artırarak toplum güvenliğine de katkı sağlayabilir. Bu çalışma kapsamında, güneş enerjisi ile çalışan, kablosuz iletişim özellikleri taşıyan ve yapay zekâ analiz yeteneğine sahip termal kamera ağı sistemi tarif edilmektedir. Ayrıca, söz konusu sisteminin teknik mimari özellikleri, kurulum gereksinimleri ile sistem kapsamında kullanılacak yapay zekâ algoritmalarının kabiliyetleri ve muhtemel algoritmaların detayları açıklanmaktadır. Önerilen sistemin uygulanması ile kesif ve gözetleme kabiliyetlerinin artırılacağı değerlendirilmektedir.

Anahtar Kelimeler

• Yapay zekâ
• makine öğrenmesi
• jandarma
• kolluk kuvvetleri
• düzensiz göç
• suç engelleme

Destekleyen Kurum

maddi bir destek veya fon kullanilmamistir.

Etik Beyan

calisma kapsaminda herhangi etik kurul iznine gerek yoktur.

Teşekkür

Yazarlar, Düzensiz Göç, Kaçakçılık ve Terörizmle ilgili zorlukları ele almak için yapay zeka ve termal kamera teknolojilerini kullanma vizyonları ve sistem tasarım sürecine dair değerli görüşleri için Tümgeneral Aykut Tanrıverdi ve Tuğgeneral Adem Şen'e minnettarlıklarını ifade ederler.

AN AI-BASED SURVEILLANCE SYSTEM PROPOSAL FOR THE SECOND LINE OF DEFENSE AGAINST IRREGULAR MIGRATION, SMUGGLING, AND TERRORISM: GENDARMERIE ASSESSMENT

Öz

Despite the physical and technological measures in place along the border protected by border forces, a significant number of irregular migrants are being apprehended by gendarmerie (Jandarma) elements in the area designated as the second line of defense. This situation poses a crucial responsibility for the Jandarma in the context of preventing irregular migration movements, curbing smuggling activities, and combating terrorism. Therefore, it is proposed that artificial intelligence-supported technological discovery and surveillance measures be implemented in the Jandarma responsibility area behind the border. It is believed that these technological measures could be beneficial in preventing irregular migration movements, restricting smuggling activities, and enhancing effectiveness in the fight against terrorism. The implementation of these measures could contribute to public safety by increasing security and maintaining order. Within the scope of this study, a thermal camera network system powered by solar energy, featuring wireless communication capabilities, and equipped with artificial intelligence analysis, is described. Additionally, the technical architectural features of the system, installation requirements, and details of the artificial intelligence algorithms to be utilized within the system, along with their capabilities and potential algorithm specifics, are explained. The implementation of the proposed system is anticipated to enhance reconnaissance and surveillance capabilities.

Anahtar Kelimeler

• Artificial intelligence
• machine learning
• gendarmerie
• law enforcement
• irregular migration
• crime prevention

Kaynakça

1. A. B. Sargano, X. Wang, P. Angelov, Z. Habib. (2017). Human action recognition using transfer learning with deep representations. International joint conference on neural networks (IJCNN), IEEE, pp. 463–469.
2. Akhilesh Shrestha and Liudong Xing. (2007). A Performance Comparison of Different Topologies for Wireless Sensor Networks. IEEE Conference on Technologies for Homeland Security.
3. Ayush Baral, Deepa Gupta, Lavanya Sharma. Motion based Object Detection based on Background Subtraction: A Review. 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA).
4. Dawoud ALshukri. (2019). Intelligent Border Security Intrusion Detection using IoT and Embedded systems. 4th Mec International Conference on Big Data and Smart City.
5. Dumpert Dwight T. (2006). Networked thermal Imaging and intelligent video technology for border security applications. Conference on Optics and Photonics in Global Homeland Security.
6. Gutin Mikhail. (2006). Thermal infrared panoramic imaging sensor. 32nd Conference on Infrared Technology and Applications.
7. Hazar Mliki, Fatma Bouhlel, Mohamed Hammami. (2020). Human activity recognition from UAV-captured video sequences. Pattern Recognition, 107140.
8. Heyman JM. (2008). Constructing a virtual wall: Race and citizenship in US–Mexico border policing. Journal of the Southwest, 50(3), 305–333.

9. Jaya S. Kulchandani. (2015). Moving Object Detection: Review of Recent Research Trends. International Conference on Pervasive Computing (ICPC).
10. Juan Terven, Diana-Margarita Córdova-Esparza, Julio-Alejandro Romero González. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision. Machine learning & knowledge extraction, 5(4), 1680-1716. https://doi.org/10.3390/make5040083
11. Kruno Lenac, Ivan Maurovi´c, Ivan Petrovi´c. (2015). Moving Objects Detection Using a Thermal Camera and IMU on a Vehicle. International Conference on Electrical Drives and Power Electronics (EDPE).
12. O’Grady N (2021) Automating security infrastructures: Practices, imaginaries, politics. Security Dialogue 52(3), 231–248.
13. Lei Pang et al. Real-time Concealed Object Detection from Passive Millimeter Wave Images Based on the YOLOv3 Algorithm. Sensors 2020, 20, 1678; https://doi:10.3390/s20061678
14. Lenac Kruno, Maurović Ivan, Petrovic Ivan. (2015). Moving objects detection using a thermal Camera and IMU on a vehicle. 2015 International Conference on Electrical Drives and Power Electronics (EDPE).
15. Manish K. Sharma et al. (2021). INTERVENOR: Intelligent Border Surveillance using Sensors and Drones. 6th International Conference for Convergence in Technology (I2CT).
16. N. AlDahoul, M. Sabri, A. Qalid, A.M. Mansoor. (2018). Real-time human detection for aerial captured video sequences via deep models. Computational Intelligence and Neuroscience.
17. Nguyen, H.-C., Nguyen, T.-H., Scherer, R., & Le, V.-H. (2023). YOLO Series for Human Hand Action Detection and Classification from Egocentric Videos, Sensors 2023.
18. Sanam Narejo et al. (2021). Weapon Detection Using YOLO V3 for Smart Surveillance System. Mathematical Problems in Engineering.
19. Sanja Milivojevic. (2022). Artificial intelligence, illegalized mobility and lucrative alchemy of border utopia. Criminology & Criminal Justice, 1–19.
20. Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning & Knowledge Extraction.
21. UN refugee agency, global trends forced displacement. Accessed on 15th March 2023. https://www.unhcr.org/global-trends-report-2022.
22. The total number of people forcibly displaced is calculated using UNHCR, UNRWA, and IDMC statistics. Accessed on 15th March 2023. https://www.unhcr.org/refugee-statistics/insights/explainers/forcibly-displaced-pocs.html
23. T.C. İçişleri Bakanlığı Göç İdaresi Başkanlığı. Accessed on 15th March 2023. https://www.goc.gov.tr/giris-cikis
24. Wang, M., Yang, B., Wang, X., Yang, C., Xu, J., Mu, B., Xiong, K., & Li, Y. (2022). YOLO-T: Multitarget Intelligent Recognition Method for X-ray Images Based on the YOLO and Transformer Models. Applied Sciences.
25. Warsi A. et al. (2019). Gun detection system using YOLOv3. Proceedings of the 2019 IEEE International Conference on Smart Instrumentation, Measurement and Application (ICSIMA).
26. Wen, Chih-Hao et al. (2012). Identifying Smuggling Vessels with Artificial Neural Network and Logistics Regression in Criminal Intelligence Using Vessels Smuggling Case Data. 4th International Scientific Asian Conference (ACIIDS).