SYSTEM FOR COLLECTING AND ANALYZING PHOTOS FROM STREET CAMERAS USING MACHINE LEARNING

Authors

  • Aleksandar Nikolić Autor
  • Dragan Ivanovic Fakultet Tehnickih Nauka Supervisor

DOI:

https://doi.org/10.24867/08BE34Nikolic

Keywords:

Elasticsearch, machine learning, microservices, object detection

Abstract

This paper describes the distributed architecture and implementation of the system for collecting and analyzing photos from street cameras using machine learning model for object detection based on convolutional neural networks.

References

[1] J. Rowley, „The wisdom hierarchy: representations of the DIKW hierarchy,“ Journal of Information Science, 2007.
[2] „Object Detection: An End to End Theoretical Perspective,“ [Na mreži]. Available: https://towardsdatascience.com/object-detection-using-deep-learning-approaches-an-end-to-end-theoretical-perspective-4ca27eee8a9a. [Poslednji pristup Novembar 2019].
[3] R. Girshick, „Rich feature hierarchies for accurate object detection and semantic segmentation,“ 2014.
[4] R. Girshick, „Fast R-CNN,“ 2015.
[5] S. Ren, „Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,“ 2016.
[6] „The C4 model for visualising software architecture,“ [Na mreži]. Available: https://c4model.com/. [Poslednji pristup Novembar 2019].
[7] „Common objects in context,“ [Na mreži]. Available: http://cocodataset.org/. [Poslednji pristup Novembar 2019].
[8] „Webcams.travel,“ [Na mreži]. Available: https://www.webcams.travel/. [Poslednji pristup Novembar 2019].

Published

2020-05-31

Issue

Section

Electrotechnical and Computer Engineering