20May 2018

INVESTIGATION OF CONVOLUTIONAL NEURAL NETWORKS FOR VISUAL TRACKING OF PEDESTRIANS.

  • Department of Electronics, Vilnius Gediminas Technical University.
Crossref Cited-by Linking logo

  • Abstract
  • Keywords
  • References
  • Cite This Article as
  • Corresponding Author

The problem of human detection in an image or video sequence is still a hot topic nowadays. It has been actively researched and still, the accurate and fast detection remains an issue. This paper aims to provide additional insights into existing solutions for pedestrian detection. The proposed method is to only use a part of video frames for object detection showed that it is possible to receive 88 % processing speed increase without accuracy lost when using every second frame. However, skipping more frames introduces tracking latency of approximated location of a pedestrian.

  1. Bernardin, K., Elbs, A. & Stiefelhagen, R., 2006. Multiple object tracking performance metrics and evaluation in a smart room environment. Sixth IEEE International Workshop on Visual Surveillance, in conjunction with ECCV, 90, p.91. Available at: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.69.7070&rep=rep1&type=pdf.
  2. Bewley, A. et al., 2016. Simple Online and Realtime Tracking. Proceedings - International Conference on Image Processing, ICIP, 2016?Augus, pp.3464?3468.
  3. Doll?r, P. et al., 2009. Pedestrian detection: A benchmark. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, pp.304?311.
  4. Doll?r, P. et al., 2012. Pedestrian detection: An evaluation of the state of the art. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(4), pp.743?761.
  5. Hubara, I. et al., 2016. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. , pp.1?29. Available at: http://arxiv.org/abs/1609.07061.
  6. Iandola, F.N. et al., 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. , pp.1?13. Available at: http://arxiv.org/abs/1602.07360.
  7. Milan, A. et al., 2016. MOT16: A Benchmark for Multi-Object Tracking. , pp.1?12. Available at: http://arxiv.org/abs/1603.00831.
  8. Munkres, J., 1957. Algorithms for the Assignment and Transportation Problems. Journal of the Society for Industrial and Applied Mathematics, 5(1), pp.32?38. Available at: http://epubs.siam.org/doi/10.1137/0105003.
  9. Park, E., Ahn, J. & Yoo, S., 2017. Weighted-Entropy-Based Quantization for Deep Neural Networks. Cvpr, pp.5456?5464. Available at: http://openaccess.thecvf.com/content_cvpr_2017/papers/Park_Weighted-Entropy-Based_Quantization_for_CVPR_2017_paper.pdf%0Ahttp://openaccess.thecvf.com/content_cvpr_2017/html/Park_Weighted-Entropy-Based_Quantization_for_CVPR_2017_paper.html.
  10. Redmon, J. et al., 2015. You Only Look Once: Unified, Real-Time Object Detection. Available at: http://arxiv.org/abs/1506.02640.
  11. Redmon, J. & Farhadi, A., 2016. YOLO9000: Better, Faster, Stronger. Available at: http://arxiv.org/abs/1612.08242.
  12. Smith, K. et al., 2005. Evaluating Multi-Object Tracking.

[Artūras Jonkus, Paulius Tumas and Artūras Serackis. (2018); INVESTIGATION OF CONVOLUTIONAL NEURAL NETWORKS FOR VISUAL TRACKING OF PEDESTRIANS. Int. J. of Adv. Res. 6 (May). 668-674] (ISSN 2320-5407). www.journalijar.com

Art?ras Jonkus

DOI:

Article DOI: 10.21474/IJAR01/7082      
DOI URL: https://dx.doi.org/10.21474/IJAR01/7082

Download Full Paper

Download PDF No. of Downloads: 15 | No. of Views: 62