Open Access Journal

ISSN : 2394-2320 (Online)

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

Open Access Journal

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

ISSN : 2394-2320 (Online)

Pedestrian Detection for Automotive Night Vision

Author : Ashish Kumar Mishra 1

Date of Publication :9th March 2018

Abstract: The sudden appearance of a pedestrian is a major concern for the driver particularly during the night as it could lead to an accident at night due to poor human eyesight. A pedestrian detector for vehicle night vision is added to solve the problem.In this device a NIR (Near Infrared) camera is used to take pictures of a night scene. Since there are large variations in the pedestrian poses in the intra-class, a tree-structured classifier is proposed here to handle the problem by training it with different image subsets and different sizes.This paper discusses the combination and validation of the Haar-Cascade and HOG-SVM (Histogram of Oriented Gradients Support Vector Machine).Haar-Cascade is equipped to identify the entire human body that excludes most non-pedestrian regions.A component based SVM classifier with HOG features is used to refine the pedestrians after identification. The pedestrian’s upper and lower body part HOG features are used for partly based validation of observed bounding boxes.A full body validation scheme is also implemented using HOG-SVM when particular part is not validated by any validation based on the part.

Reference :

    1. Y. Luo, J. Remillard, and D. Hoetzer, “Pedestrian detection in near-infrared night vision system,” in IEEE Intelligent Vehicles Symposium, Proceedings, 2010, doi: 10.1109/IVS.2010.5548089.
    2. D. Tomè, F. Monti, L. Baroffio, L. Bondi, M. Tagliasacchi, and S. Tubaro, “Deep Convolutional Neural Networks for pedestrian detection,” Signal Process. Image Commun., 2016, doi: 10.1016/j.image.2016.05.007.
    3. V. John, S. Mita, Z. Liu, and B. Qi, “Pedestrian detection in thermal images using adaptive fuzzy C-means clustering and convolutional neural networks,” in Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015, 2015, doi: 10.1109/MVA.2015.7153177.
    4. K. Piniarski, P. PawÅ‚owski, and A. DÄ…browski, “Pedestrian detection by video processing in automotive night vision system,” in Signal Processing - Algorithms, Architectures, Arrangements, and Applications Conference Proceedings, SPA, 2015, doi: 10.21275/v5i4.nov163154.
    5. D. F. Llorca, M. A. Sotelo, I. Parra, M. Ocaña, and L. M. Bergasa, “Error analysis in a stereo vision-based pedestrian detection sensor for collision avoidance applications,” Sensors, 2010, doi: 10.3390/s100403741.
    6. C. Wojek, S. Walk, S. Roth, and B. Schiele, “Monocular 3D scene understanding with explicit occlusion reasoning,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, doi: 10.1109/CVPR.2011.5995547.
    7. S. Silberstein, D. Levi, V. Kogan, and R. Gazit, “Vision-based pedestrian detection for rear-view cameras,” in IEEE Intelligent Vehicles Symposium, Proceedings, 2014, doi: 10.1109/IVS.2014.6856399.
    8. D. O. Pop, A. Rogozan, F. Nashashibi, and A. Bensrhair, “Fusion of stereo vision for pedestrian recognition using convolutional neural networks,” in ESANN 2017 - Proceedings, 25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2017.
    9. S. D. Casey, “Adaptive signal processing,” in Applied and Numerical Harmonic Analysis, 2015.
    10. S. Wager, S. Wang, and P. Liang, “Dropout training as adaptive regularization,” in Advances in Neural Information Processing Systems, 2013.

Recent Article