Trafik Işığı Tespiti Yapan Bir Sürücü Güvenlik Destek Sistemi

Yıl 2018, Cilt: 21 Sayı: 2, 419 - 426, 01.06.2018

Çağlar Kılıkçıer , Ersen Yılmaz

https://doi.org/10.2339/politeknik.389606

Öz

Sürücü güvenlik destek sistemleri
(SGDS) sayesinde trafik kazası sayıları azaltılabilmektedir. Bu çalışmada,
trafik ışıklarını bularak sürücüyü uyaran bir sürücü güvenlik destek sistemi
önerilmiştir.  Önerilen SGDS sadece
görsel bilgilerle çalışmakta ve trafik ışığı tespiti yapmaktadır. Sistem ilk
olarak alınan imgeleri gri ölçekli imgelere dönüştürerek Otsu kriterine göre
çok seviyeli eşiklemeye tabi tutmaktadır. Eşiklenmiş olan imgeler için
sırasıyla bağlı bileşen analizi ve parça analizi yapılarak trafik ışığı
olabilecek ilgi duyulan bölgeler bulunmaktadır. Bulunan bu bölgelerden renk
bilgisini de içeren özellik vektörleri çıkartılmaktadır. Son olarak, Destek
Vektör Makinesi (DVM) ile ilgi duyulan bölgelerin trafik ışığı olup olmadığına
karar verilmektedir. Önerilen SGDS’nin başarımı şehir ortamından elde edilmiş
imgeler üzerinde incelenmiştir.  

Anahtar Kelimeler

DVM, çok seviyeli eşikleme, pso, trafik ışığı

A Driver Safety Support System Which Detects Traffic Lights

Öz

The number of traffic accidents can be decreased
through driver safety support systems (DSSS). In this study, a driver safety
support system is proposed in which the driver is warned by finding traffic
lights. The proposed DSSS works on only visual information and detects traffic
lights. The system primarily transforms the received images into gray scale
images and subject them to multi-level thresholding with Otsu criteria. The
regions of interest which can be traffic lights are found for the thresholded images
by using connected component analysis and blob analysis, respectively. Feature
vectors including the color information are extracted from the founded regions.
Finally, it is decided if the regions of interest are traffic lights by using
support vector machines (SVM). The performance of the proposed DSSS is examined
on the images obtained from urban areas.

Anahtar Kelimeler

SVM, multi-level thresholding, pso, traffic light

Kaynakça

• [1] Diaz-Cabrera, M., Cerri, P., ve Medici, P., “Robust real-time traffic light detection and distance estimation using a single camera”, Expert Systems with Applications, 42(8): 3911-3923, (2015).
• [2] Mu, G., Xinyu, Z., Deyi, L., Tianlei, Z., ve Lifeng, A., “Traffic light detection and recognition for autonomous vehicles”, The Journal of China Universities of Posts and Telecommunications, 22(1): 50-56, (2015).
• [3] Philipsen, M. P. , Jensen, M. B., Møgelmose, A., Moeslund, T. B., ve Trivedi, M. M., “Traffic Light Detection: A Learning Algorithm and Evaluations on Challenging Dataset”, IEEE 18th International Conference on Intelligent Transportation Systems, Las Palmas, 2341-2345, (2015).
• [4] Fairfield, N., ve Urmson, C., “Traffic Light Mapping and Detection”, IEEE International Conference on Robotics and Automation, Shanghai, 5421-5426, (2011).
• [5] Kılıkçıer, Ç., “Hedef Tanıma Algoritmaları ve Bir DSP Kartı Üzerinde Gerçeklenmesi”, Yüksek Lisans Tezi, Uludağ Üniversitesi, Fen Bilimleri Enstitüsü, (2012), (Danışman: E. Yılmaz).
• [6] www.lara.prd.fr/benchmarks/trafficlightsrecognition (Erişim Tarihi: 21. 08.2017).
• [7] Charette, R. d., ve Nashashibi, F., “Traffic Light Recognition using Image Processing Compared to Learning Processes”, IEEE/RSJ International Conference on Intelligent Robots and Systems, St. Louis, 333-338, (2009).
• [8] Charette, R. d., ve Nashashibi, F., “Real Time Visual Traffic Lights Recognition Basedon Spot Light Detection and Adaptive Traffic Lights Templates”, IEEE Intelligent Vehicles Symposium, Xian, Çin, 358-363, (2009).
• [9] Siogkas, G., Skodras, E., ve Dermetas, E., “Traffic Lights Detection in Adverse Conditions using Color, Symmetry and Spatiotemporal Information”, VISAPP-International Conference on Computer Vision Theory and Applications, Rome, 620-627, (2012).
• [10] Wang, C., Jin, T., Yang, M., Ve Wang, B., “Robust and Real-Time Traffic Lights Recognition in Complex Urban Environments”, International Journal of Computational Intelligence Systems, 4(6): 1383-1390, (2011).
• [11] Haltakov, V., Mayr, J., Unger, C., ve Ilic, S., “Semantic segmentation based traffic light detection at day and at night”, German Conference on Pattern Recognition, Aachen, 446-457, (2015).
• [12] Jensen, M. B., Philipsen, M. P., Mogelmose, A., Moeslund, T. B., ve Trivedi, M. M., “Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives”, IEEE Transactions on Intelligent Transportation Systems, 99: 1-16, (2016).
• [13] Otsu, N., “A threshold selection method from gray-level histograms”, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 9(1): 62-66, (1979).
• [14] Chander, A., Chatterjee, A., ve Siarry, P., “A new social and momentum component adaptive PSO algorithm for image segmentation", Expert System with Applications, 38(5): 4998-5004, (2011).
• [15] Kılıkçıer, Ç., ve Yılmaz, E., “İmge Eşiklemede Ayrık İkili PSO Temelli Yeni Bir Yaklaşım”, ELECO’2012 Elektrik - Elektronik Ve Bilgisayar Mühendisliği Sempozyumu, Bursa, 590-593, (2012).
• [16] Kennedy, J., ve Eberhart, C. R., “A discrete binary version of the particle swarm algorithm”, IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, Orlando, 4104-4108, (1997).
• [17] Rosenfeld, A., ve Pfaltz, J. L., “Sequential Operations in Digital Picture Processing”, Journal of the Association for Computing Machinery, 13(4): 471-494, (1966).
• [18] Sonka, M., Hlavac, V., ve Boyle, R., “Image Processing, Analysis; and Machine Vision” Third Edition, Cengage Learning, Stamford, (2008).
• [19] Wang, Y., ve Bhattacharya, P., “A Theory of parameter-dependent connected components of gray images and segmentation”, International Conference on Image Processing, Washington, DC, 69-72, (1995).
• [20] Westman, T., Harwood, D., Laitinen, T., ve Pietikainen, M., “Color Segmentation by Hierarchical Connected Component Analysis with image enhancement by symmetric neighborhood filter”, 10th International Conference on Pattern Recognition, Atlantic City, NJ, 796-802, (1990).
• [21] Soille, P., “Constrained Connectivity for Hierarchical Image Partitioning and Simplification”, IEEE Transaction on Pattern Analysis and Machine Intelligence, 30(7): 1132-1145, (2008).
• [22] Burges, C. J. C., “A Tutorial on Support Vecor Machines for Pattern Recognition”, Data Mining and Knowledge Discovery, 2(2): 121-167, (1998).
• [23] Suykens, J., ve Vandewalle, J., “Least Squares Support Vector Machine Classifiers”, Neural Processing Letters, 9(3): 293-300, (1999).