Real-Time Vehicle and Pedestrian Detection Through SSD in Indian Traffic Conditions

Object detection is a standout amongst the most vital segment of self-driving cars. It is very challenging especially in the case of Indian roads which possess numerous issues including non-standard vehicles, unskilled drivers, lower visibility due to pollution and despicable path division. In this paper, we have to test our algorithm for Indian traffic conditions through Single Shot Multi-box Detection (SSD) method. For this, we have run our algorithm on the live feed video captured by the camera (30fps) for 25 km stretch and approximately 8000 image datasets on the Noida-Greater Noida Expressway. The implemented algorithm furnishes an accuracy of 96% with a high obvious positive rate of 94.23% and a minor false positive of 4%.

[1]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[2]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Dumitru Erhan,et al.  Scalable, High-Quality Object Detection , 2014, ArXiv.

[4]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[5]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[8]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[11]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[14]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .