Abstract

The focus of this research is on providing a foundational understanding of convolutional neural networks for its application, in particular, to the detection of moving objects. Furthermore, the paper details the functioning and interplay of convolutional layers. Manually analysing a huge dataset of video stills is now the only viable option, but this is time-consuming and requires human expertise. The algorithms included into neural networks allow for autonomous analysis and identification.

Keywords

• Video analysis,
• Convolutional Neural Networks,
• Convolutional Layers,
• Identification,
• Moving Objects

References

• Adit Deshpande. A Beginner's Guide To Understanding Convolutional Neural Networks - 2020 - Text: electronic URL: https://adeshpande3.github.io/A-Beginner's- Guide-To-Understanding-Convolutional-Neural-Networks/ -(Reference date 26.12.2020).
• Ivet Rafegas, Maria Vanrell, Luis A. Alexandre, Guillem Arias. Understanding Trained CNNs by Indexing Neuron Selectivity// Pattern Recognition Letters/ Text: electronic. –2019- URL: https://www.sciencedirect.com/science/article/abs/pii/S0167865519302909 - (Reference date 26.12.2020).
• Michael Nielsen. Neural Networks и Deep Learning Text: electronic. – 2019
• – URL: http://neuralnetworksanddeeplearning.com/chap1.html -(Reference date 26.12.2020).
• RuihengZhang, LingxiangWu, YukunYang, WannengWu, YueqiangChen, MinXu. Multi-camera multi-player tracking with deep player identification in sports video //Pattern Recognition 2020 - Text: electronic. – URL: https://www.sciencedirect.com/science/article/abs/pii/S0031320320300650 - (Reference date 26.12.2020).
• Zhi-junLu, QiQin, Hong-yinShi, HaoHuang - SAR moving target imaging based on convolutional neural network. //Digital Signal Processing- Text: electronic. – URL: https://www.sciencedirect.com/science/article/abs/pii/S1051200420301779 - (Reference date 26.12.2020).

This work is licensed under a Creative Commons Attribution 4.0 International License.