Real-Time Scalable System For Face Tracking In Multi-Camera

Mehmet Fatih Ozdemır; Davut Hanbay

Makale detayları

Real-Time Scalable System For Face Tracking In Multi-Camera

Yazarlar:

Mehmet Fatih Ozdemır | Davut Hanbay

Yayıncı:

Gazi University

Ana Başlıklar:

Derin Öğrenme | Yapay Görme

Dergi:

Politeknik Dergisi Vol.27 Issue 6, pp.2215-2224

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001333508

pISSN:

2147-9429

Anahtar kelimeler:

Özet:

 Face detection and tracking have become increasingly popular in recent years. It has critical importance in security, defense, and robotics applications uses encountered in everyday life. For this purpose, many decision support or expert systems have been developed using artificial intelligence and machine learning. Thanks to the developments in the field of deep learning and hardware many effective and reliable face tracking systems have been realized. However there are still very few real-time scalable end-to-end systems. Also, the realization of this system on multiple cameras is a real challenge. In this study, a real-time, multi-camera, deep learning-based face tracking system has been developed. In the realized system, SCRFD model is used for face detection, ArcFace model is used for face recognition, and an updated DeepSORT algorithm is used for more stable face tracking. In addition, Apache Kafka stream processing system and Socket.IO bidirectional communication library were used to process multi-camera data in real-time and scalable. In the proposed system, when an image is input into the system, it can be displayed on the web page after approximately 127 ms.

 Face detection and tracking have become increasingly popular in recent years. It has critical importance in security, defense, and robotics applications uses encountered in everyday life. For this purpose, many decision support or expert systems have been developed using artificial intelligence and machine learning. Thanks to the developments in the field of deep learning and hardware many effective and reliable face tracking systems have been realized. However there are still very few real-time scalable end-to-end systems. Also, the realization of this system on multiple cameras is a real challenge. In this study, a real-time, multi-camera, deep learning-based face tracking system has been developed. In the realized system, SCRFD model is used for face detection, ArcFace model is used for face recognition, and an updated DeepSORT algorithm is used for more stable face tracking. In addition, Apache Kafka stream processing system and Socket.IO bidirectional communication library were used to process multi-camera data in real-time and scalable. In the proposed system, when an image is input into the system, it can be displayed on the web page after approximately 127 ms.

 Face detection and tracking have become increasingly popular in recent years. It has critical importance in security, defense, and robotics applications uses encountered in everyday life. For this purpose, many decision support or expert systems have been developed using artificial intelligence and machine learning. Thanks to the developments in the field of deep learning and hardware many effective and reliable face tracking systems have been realized. However there are still very few real-time scalable end-to-end systems. Also, the realization of this system on multiple cameras is a real challenge. In this study, a real-time, multi-camera, deep learning-based face tracking system has been developed. In the realized system, SCRFD model is used for face detection, ArcFace model is used for face recognition, and an updated DeepSORT algorithm is used for more stable face tracking. In addition, Apache Kafka stream processing system and Socket.IO bidirectional communication library were used to process multi-camera data in real-time and scalable. In the proposed system, when an image is input into the system, it can be displayed on the web page after approximately 127 ms.

 Yüz algılama ve izleme son yıllarda giderek daha popüler hale geldi. Günlük hayatta karşılaşılan güvenlik, savunma ve robotik uygulama kullanımlarında kritik öneme sahiptir. Bu amaçla yapay zeka ve makine öğrenmesi kullanılarak birçok karar destek veya uzman sistem geliştirilmiştir. Derin öğrenme ve donanım alanındaki gelişmeler sayesinde birçok etkin ve güvenilir yüz takip sistemi gerçekleştirilmiştir. Ancak hala çok az gerçek zamanlı ölçeklenebilir uçtan uca sistem var. Ayrıca, böyle bir sistemin birden çok kamerada gerçekleştirilmesi gerçek bir zorluktur. Bu çalışmada gerçek zamanlı, çok kameralı, derin öğrenme tabanlı yüz takip sistemi geliştirilmiştir. Gerçekleştirilen sistemde yüz tespiti için SCRFD modeli, yüz tanıma için ArcFace modeli ve daha kararlı yüz takibi için güncellenmiş DeepSORT algoritması kullanılmıştır. Ayrıca, çoklu kamera verilerini gerçek zamanlı ve ölçeklenebilir olarak işlemek için Apache Kafka akış işleme sistemi ve Socket.IO çift yönlü iletişim kütüphanesi kullanılmıştır. Önerilen sistemde girdi olarak görüntü verildiğinde yaklaşık 127 ms sonra web sayfasında görüntülenebilmektedir.

Makale detayları

Real-Time Scalable System For Face Tracking In Multi-Camera

Yazarlar:

Mehmet Fatih Ozdemır | Davut Hanbay

Yayıncı:

Gazi University

Ana Başlıklar:

Derin Öğrenme | Yapay Görme

Dergi:

Politeknik Dergisi Vol.27 Issue 6, pp.2215-2224

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001333508

pISSN:

2147-9429

Face Recognition

Face Tracking

Deep Learning

Multi-CameraYüz Tanıma

Yüz Takibi

Derin Öğrenme

Çoklu Kamera

Sayı

Makale detayları

Yazarlar: Mehmet Fatih Ozdemır | Davut Hanbay

Yayıncı: Gazi University

Ana Başlıklar: Derin Öğrenme | Yapay Görme

Dergi: Politeknik Dergisi Vol.27 Issue 6, pp.2215-2224

Belge Tipi: Makale

Yayın Tarihi: 12/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001333508

pISSN: 2147-9429

Sayı

Yazarlar:

Mehmet Fatih Ozdemır | Davut Hanbay

Yayıncı:

Gazi University

Ana Başlıklar:

Derin Öğrenme | Yapay Görme

Dergi:

Politeknik Dergisi Vol.27 Issue 6, pp.2215-2224

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001333508

pISSN:

2147-9429