DETECTION OF LPG VEHICLES IN RISKY AREAS WITH COMPUTER VISION TECHNIQUES

Öznur Suçeken; Gül Fatma Türker

Makale detayları

DETECTION OF LPG VEHICLES IN RISKY AREAS WITH COMPUTER VISION TECHNIQUES

Yazarlar:

Öznur Suçeken | Gül Fatma Türker

Yayıncı:

Isparta University of Applied Sciences

Ana Başlıklar:

Yazılım Mühendisliği (Diğer)

Dergi:

Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 1, pp.26-43

Belge Tipi:

Makale

Yayın Tarihi:

6/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001320509

pISSN:

2618-6055

Anahtar kelimeler:

Özet:

 Vehicle use is becoming more widespread day by day due to the world population growth. Within the scope of intelligent transportation systems, the information technologies sector and the transportation sector work in an integrated manner to solve the problems caused by the increasing number of vehicles. Data obtained with sensors and cameras are analyzed with artificial intelligence-based information technologies and used in autonomous vehicles, security, traffic management, navigation and passenger information systems. Computer vision enables machines to extract meaningful patterns and relationships from images by combining image processing and deep learning technologies. Computer vision techniques are applied in many fields such as tourism, health, industry, defense, transportation, service, e-commerce, etc. The applications developed provide solutions to various challenges in the transportation sector. For vehicles using Liquified Petroleum Gas LPG fuel, the gases in LPG tanks are flammable and pose a potential explosion hazard, especially in certain areas in cities. Entry of LPG vehicles is prohibited in institutions and organizations such as hospitals, shopping malls, hotels that have indoor parking services. The control method of the ban is carried out by assigning a personnel and checking the vehicle trunks. In this study, LPG fueled vehicles were automatically detected using computer vision techniques. Vehicle image data captured by mobile cameras in different provinces in Turkey were trained and compared with four different deep learning models. As a result of training and performance tests on the models, the YOLOv8 model was more effective than the other models with an accuracy of 0.994 mAP and a speed of 11.6 ms. It has been shown to be a stable model in terms of real-time monitoring in real life. It is envisaged that the developed system can contribute to the applications of computer vision techniques as well as benefit the national economy, public life safety and environmental protection.

 Vehicle use is becoming more widespread day by day due to the world population growth. Within the scope of intelligent transportation systems, the information technologies sector and the transportation sector work in an integrated manner to solve the problems caused by the increasing number of vehicles. Data obtained with sensors and cameras are analyzed with artificial intelligence-based information technologies and used in autonomous vehicles, security, traffic management, navigation and passenger information systems. Computer vision enables machines to extract meaningful patterns and relationships from images by combining image processing and deep learning technologies. Computer vision techniques are applied in many fields such as tourism, health, industry, defense, transportation, service, e-commerce, etc. The applications developed provide solutions to various challenges in the transportation sector. For vehicles using Liquified Petroleum Gas LPG fuel, the gases in LPG tanks are flammable and pose a potential explosion hazard, especially in certain areas in cities. Entry of LPG vehicles is prohibited in institutions and organizations such as hospitals, shopping malls, hotels that have indoor parking services. The control method of the ban is carried out by assigning a personnel and checking the vehicle trunks. In this study, LPG fueled vehicles were automatically detected using computer vision techniques. Vehicle image data captured by mobile cameras in different provinces in Turkey were trained and compared with four different deep learning models. As a result of training and performance tests on the models, the YOLOv8 model was more effective than the other models with an accuracy of 0.994 mAP and a speed of 11.6 ms. It has been shown to be a stable model in terms of real-time monitoring in real life. It is envisaged that the developed system can contribute to the applications of computer vision techniques as well as benefit the national economy, public life safety and environmental protection.

 Vehicle use is becoming more widespread day by day due to the world population growth. Within the scope of intelligent transportation systems, the information technologies sector and the transportation sector work in an integrated manner to solve the problems caused by the increasing number of vehicles. Data obtained with sensors and cameras are analyzed with artificial intelligence-based information technologies and used in autonomous vehicles, security, traffic management, navigation and passenger information systems. Computer vision enables machines to extract meaningful patterns and relationships from images by combining image processing and deep learning technologies. Computer vision techniques are applied in many fields such as tourism, health, industry, defense, transportation, service, e-commerce, etc. The applications developed provide solutions to various challenges in the transportation sector. For vehicles using Liquified Petroleum Gas LPG fuel, the gases in LPG tanks are flammable and pose a potential explosion hazard, especially in certain areas in cities. Entry of LPG vehicles is prohibited in institutions and organizations such as hospitals, shopping malls, hotels that have indoor parking services. The control method of the ban is carried out by assigning a personnel and checking the vehicle trunks. In this study, LPG fueled vehicles were automatically detected using computer vision techniques. Vehicle image data captured by mobile cameras in different provinces in Turkey were trained and compared with four different deep learning models. As a result of training and performance tests on the models, the YOLOv8 model was more effective than the other models with an accuracy of 0.994 mAP and a speed of 11.6 ms. It has been shown to be a stable model in terms of real-time monitoring in real life. It is envisaged that the developed system can contribute to the applications of computer vision techniques as well as benefit the national economy, public life safety and environmental protection.

 Dünya nüfus artışına bağlı olarak araç kullanımı gün geçtikçe yaygınlaşmaktadır. Akıllı ulaşım sistemleri kapsamında artan araç sayısının neden olduğu sorunları çözmek için bilişim sektörü ile ulaşım sektörü entegre bir şekilde çalışmaktadır. Sensörler ve kameralarla elde edilen veriler, yapay zeka tabanlı bilişim teknolojileriyle analiz edilerek otonom araçlar, güvenlik, trafik yönetimi, navigasyon ve yolcu bilgilendirme sistemlerinde kullanılmaktadır. Bilgisayarlı görü, görüntü işleme ile derin öğrenme teknolojilerinin birlikte kullanılması sonucu makinelerin, görüntülerden anlamlı örüntüler ve ilişkiler çıkarmasını sağlamaktadır. Bilgisayarlı görü teknikleri turizm, sağlık, sanayi, savunma, ulaşım, hizmet, e-ticaret vb. birçok alanda uygulanmaktadır. Geliştirilen uygulamalar ulaşım sektöründe çeşitli zorluklara çözüm üretmektedir. Liquified Petroleum Gas LPG yakıtı kullanan araçlar için, LPG tanklarındaki gazların yanıcı olması ve patlama ihtimali yaratması nedeniyle, özellikle şehirlerdeki belirli alanlarda tehlike oluşturmaktadır. Kapalı otopark hizmeti bulunduran hastaneler, alışveriş merkezleri, oteller gibi kurum ve kuruluşlarda LPG li araçların girişi yasaklanmıştır. Yasağın denetim yöntemi ise bir personelin görevlendirilmesi ve araç bagajlarının kontrol edilmesiyle gerçekleştirilmektedir. Bu çalışmada LPG yakıtıyla çalışan araçların bilgisayarlı görü teknikleri kullanılarak otomatik bir şekilde tespiti yapılmıştır. Türkiyede farklı illerde mobil kameralar aracılığıyla çekilen araç görüntü verileri dört farklı derin öğrenme modeli ile eğitilerek karşılaştırılmıştır. Modeller üzerinde eğitim ve performans testleri sonucu YOLOv8 modelinde, 0.994 mAP doğruluk ve 11.6 ms hız değerleri ile diğer modellerden daha etkili sonuç elde edilmiştir. Güncel hayatta gerçek zamanlı izleme açısından kararlı bir model olduğu gösterilmiştir. Geliştirilen sistemin, bilgisayarlı görü tekniği uygulamalarına katkıda bulunmasının yanı sıra ulusal ekonomiye, toplum can güvenliğine ve çevrenin korunmasına fayda sağlayabileceği öngörülmektedir.

Makale detayları

DETECTION OF LPG VEHICLES IN RISKY AREAS WITH COMPUTER VISION TECHNIQUES

Yazarlar:

Öznur Suçeken | Gül Fatma Türker

Yayıncı:

Isparta University of Applied Sciences

Ana Başlıklar:

Yazılım Mühendisliği (Diğer)

Dergi:

Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 1, pp.26-43

Belge Tipi:

Makale

Yayın Tarihi:

6/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001320509

pISSN:

2618-6055

Computer vision

Deep learning

Image processing

LPG

VehicleAraç

Bilgisayarlı görü

Derin öğrenme

Görüntü işleme

LPG

Sayı

Makale detayları

Yazarlar: Öznur Suçeken | Gül Fatma Türker

Yayıncı: Isparta University of Applied Sciences

Ana Başlıklar: Yazılım Mühendisliği (Diğer)

Dergi: Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 1, pp.26-43

Belge Tipi: Makale

Yayın Tarihi: 6/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001320509

pISSN: 2618-6055

Sayı

Yazarlar:

Öznur Suçeken | Gül Fatma Türker

Yayıncı:

Isparta University of Applied Sciences

Ana Başlıklar:

Yazılım Mühendisliği (Diğer)

Dergi:

Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 1, pp.26-43

Belge Tipi:

Makale

Yayın Tarihi:

6/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001320509

pISSN:

2618-6055