Trafik Yoğunluk Harita Görüntülerinin Görüntü İşleme Yöntemleriyle İşlenmesi

Year 2017, Volume: 5 Issue: 2, 22 - 28, 31.05.2017

G. Çiğdem Çavdaroğlu

https://doi.org/10.21541/apjes.289448

Abstract

Bu çalışmada, “Akıllı Şehirler” konulu uluslararası
bir Ar-Ge projesi olan INSIST projesi kapsamında geliştirilen, yaygın olarak
kullanılan trafik yoğunluk haritası uygulamalarından elde edilen görüntüleri
işleyerek yoğunluk verisi üreten bir yöntem sunulmaktadır. INSIST projesi,
akıllı şehirlere yönelik olarak güvenlik – reklam – şehir aydınlatması
uygulamalarını barındırmayı ve bu uygulamalara veri sağlamayı adreslemektedir.
Akıllı Şehirler konusunun en önemli unsurlarından birisi olan akıllı ulaşım
sistemlerinin kilit verilerinden birisi de trafik yoğunluk verileridir. Şehirde
yaşayan ve trafikte aktif olarak var olan kişilerin akıllı yöntemler ile trafik
hakkında bilgilendirilmesi, öncelikli araçlara hem en kısa hem de en uygun olan
rotaların önerilmesi için trafik yoğunluk verileri çok önemli bir veri
kaynağıdır. Şehrin çeşitli konumlarına farklı kamu kurumları tarafından
yerleştirilen kameralar yardımıyla bu verinin elde edilmesi mümkündür, ancak bu
hem maliyetli hem de kamera konum ve sayılarına bağımlı olması nedeniyle
sınırlı bir yöntemdir. Bu çalışmada, bu yönteme bir alternatif olarak
geliştirilen ve internet üzerinden trafik yoğunluk verilerini sunan
uygulamalardan elde edilen görüntülerin işlenmesi ile trafik yoğunluk
verilerini üreten bir yöntem sunulmuştur.

Keywords

görüntü işleme, trafik yoğunluğu

Processing of Traffic Density Map Images Using Image Processing Techniques

Abstract

This paper presents a method which is developed in an international
R&D project called INSIST on the subject “Smart Cities”, to extract traffic
density information from traffic density maps by implementing image processing
techniques. INSIST project addresses hosting security – advertisement –
lighting applications developed for smart cities and providing required data to
this applications. Intelligent transport systems is a very important key
feature of smart cities. One of the key data source of intelligent transport
systems is traffic density data. Traffic density data is required for
navigating active drivers in the traffic using smart methods and suggesting
alternative routes to the emergency vehicles.Although this required data can be
gathered from the video cameras located at various locations around the city,
this method is very expensive and limited to the camera locations and count.
This paper presents an alternative method in order to gather traffic density
data. The presented method uses the screenshots of traffic density maps and
processes them by image processing algorithms.

Keywords

Smart cities, intelligent transport, traffic density

References

• [1] http://www.ibm.com/smarterplanet/tr/tr/traffic_congestion/visions/?re=sph, Son Erişim Tarihi: 10 Mayıs 2016.
• [2] https://itea3.org/project/insist.html, Son Erişim Tarihi: 25 Mayıs 2016.
• [3] Bajcsy R, Tavakoli M. Computer recognition of roads from satellite pictures. IEEE Transactions on Systems, Man, and Cybernetics 6 623–637; 1976.
• [4] Laptev I, Mayer H, Lindeberg T, Eckstein W, Steger C, Baumgartner A. Automatic extraction of roads from aerial images based on scale space and snakes. Machine Vision and Applications 12 23–31; 2000.
• [5] Mena JB, Malpica JA. An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery. Pattern Recognition Letters 26 1201–1220; 2005.
• [6] Geman D, Geman D, Jedynak B, Jedynak B, Syntim P. An active testing model for tracking roads in satellite images. IEEE Transactions on Pattern Analysis and Machine Intelligence 18 1–14; 1995.
• [7] Hu J, Razdan A, Femiani JC, Cui M, Wonka P. Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints. IEEE Transactions on Geoscience and Remote Sensing 45 4144–4157; 2007.
• [8] Boggess JE. Identification of roads in satellite imagery using artificial neural networks: A contextual approach. Technical report, Mississippi State University; 1993.
• [9] Bhattacharya U, Parui SK: An improved backpropagation neural network for detection of road-like features in satellite imagery. International Journal of Remote Sensing 18 3379–3394; 1997.
• [10] Mokhtarzade M, Zoej MJV. Road detection from high-resolution satellite images using artificial neural networks. International Journal of Applied Earth Observation and Geoinformation 9 32–40; 2007.
• https://itea3.org/project/insist.html, Son Erişim Tarihi: 25 Mayıs 2016.
• Bajcsy R, Tavakoli M. Computer recognition of roads from satellite pictures. IEEE Transactions on Systems, Man, and Cybernetics 6 623–637; 1976.
• Laptev I, Mayer H, Lindeberg T, Eckstein W, Steger C, Baumgartner A. Automatic extraction of roads from aerial images based on scale space and snakes. Machine Vision and Applications 12 23–31; 2000.
• Mena JB, Malpica JA. An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery. Pattern Recognition Letters 26 1201–1220; 2005.
• Geman D, Geman D, Jedynak B, Jedynak B, Syntim P. An active testing model for tracking roads in satellite images. IEEE Transactions on Pattern Analysis and Machine Intelligence 18 1–14; 1995.
• Hu J, Razdan A, Femiani JC, Cui M, Wonka P. Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints. IEEE Transactions on Geoscience and Remote Sensing 45 4144–4157; 2007.
• Boggess JE. Identification of roads in satellite imagery using artificial neural networks: A contextual approach. Technical report, Mississippi State University; 1993.
• Bhattacharya U, Parui SK: An improved backpropagation neural network for detection of road-like features in satellite imagery. International Journal of Remote Sensing 18 3379–3394; 1997.
• Mokhtarzade M, Zoej MJV. Road detection from high-resolution satellite images using artificial neural networks. International Journal of Applied Earth Observation and Geoinformation 9 32–40; 2007.