REAL TIME PEDESTRIAN ALERT SYSTEM FOR VEHICLES

Year 2020, Volume: 21 Issue: 3, 446 - 453, 30.09.2020

Şahin Işık , Göksu Vatansever Yıldıran Anagun , Mehmet Çelikhan Kemal Özkan

https://doi.org/10.18038/estubtda.629701

Abstract

In this study, we have developed a pre-collision alert
system for vehicles in terms of detection pedestrians in road. The system is
consisting from deep learning models and transfer learning methodologies. For
this purpose, pre-trained convolutional models was considered to detect
pedestrian and road.  Finally, the
segmented road mask and pedestrian mask was utilized to reveal the intersection
of these two masks. The system generates an alert if the number of pixels is
higher than predefined threshold value. By considering the visual results, the
proposed system gives valuable detection results to avoid collision.

Keywords

Deep Learning Models, Pedestrian Alert System, Road Detection

References

• [1] 'Ford, Https://Www.Ford.Com/Technology/Driver-Assist-Technology/Pre-Collision-Assist/, Accessed 09.27.2019'.
• [2] 'Qualcom, Https://Www.Qualcomm.Com/Videos/Honda-V2p-Overview, Accessed 27.09.2019'.
• [3] 'Bosch, Https://St-Tpp.Resource.Bosch.Com/Media/Technology_Partner_Programm/10_Public/ Application_Notes/Iss_Ipp_Application_Note_210x280_Final_Lowres_Hyperlinks.Pdf, Accessed 09.27.2019'.
• [4] Said YF. and Barr M. Pedestrian Detection for Advanced Driver Assistance Systems Using Deep Learning Algorithms, International Journal of Computer Science and Network Security, 2019; 19, (9), p. 10.
• [5] Xu C, Wang G, Yan S, Yu J, Zhang B, Dai S, Li Y and Xu L. Fast Vehicle and Pedestrian Detection Using Improved Mask R-Cnn. Mathematical Problems in Engineering, 2020.
• [6] Zhang S, Abdel-Aty M, Yuan J and Li P. Prediction of Pedestrian Crossing Intentions at Intersections Based on Long Short-Term Memory Recurrent Neural Network. Transportation Research Record, 2020; p. 0361198120912422.
• [7] Fuentes A, Jun I, Yoon S and Dong S. Pedestrian Detection for Driving Assistance Systems Based on Faster-Rcnn, in, International Symposium on Information Technology Convergence Isitc, 2016.
• [8] Long J, Shelhamer E and Darrell T. Fully Convolutional Networks for Semantic Segmentation', in, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
• [9] Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, and Adam H.J.a.p.a. Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications, 2017.
• [10] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y and Berg AC. Ssd: Single Shot Multibox Detector, in, European Conference on Computer Vision, Springer, 2016.
• [11] Tensorflow, Https://Www.Tensorflow.Org/, Accessed 09.27.2019.
• [12] Simonyan K and Zisserman A.J.a.p.a., Very Deep Convolutional Networks for Large-Scale Image Recognition, 2014.
• [13] He K, Zhang X, Ren S and Sun J. Deep Residual Learning for Image Recognition, in, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
• [14] 'Medium, Https://Medium.Com/@Jonathan_Hui/Object-Detection-Speed-and-Accuracy-Comparison-Faster-R-Cnn-R-Fcn-Ssd-and-Yolo-5425656ae359, Accessed 10.03.2019'.