Научная визуализация

Scientific Visualization

Электронный журнал открытого доступа

Национальный Исследовательский Ядерный Университет "МИФИ"

      ISSN 2079-3537      

 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                                                                                             

Научная визуализация, 2021, том 13, номер 2, страницы 1 - 9, DOI: 10.26583/sv.13.2.01

Visualization System for Fire Detection in the Video Sequences

Авторы: N.V. Laptev1, V.V. Laptev2, O. M. Gerget3, A.A. Kravchenko4, D.Yu. Kolpashchikov5

National Research Tomsk Polytechnic University

1 ORCID: 0000-0003-0709-9974, nikitalaptev77@gmail.com

2 ORCID: 0000-0001-8639-8889, vvl39@tpu.ru

3 ORCID: 0000-0002-6242-9502, olgagerget@mail.ru

4 ORCID: 0000-0001-6828-3279, aak224@tpu.ru

5 ORCID: 0000-0001-8915-0918, Dyk1@tpu.ru

 

Аннотация

The paper deals with the analysis of the visual images obtained from fire detection systems. We review the existing approaches to the analysis of video surveillance data and propose a tool for data labeling and visualization. The proposed solution for visual image analysis is based on a neural network (object detection technology). Recognition of hazard locations was carried out using the EfficientDet-D1 model. Video pre- and post-processing algorithms were implemented to improve visual image classification. The pre-processing was used to generate a frame preserving the features of objects that dynamically change over time. The post-processing combines the results of sequential detection of characteristic features on each frame, in particular, features of a smoke cloud. The results of the system operation are presented: visual image classification accuracy was 81%, while localization accuracy was 87%.

 

Ключевые слова: computer vision, neural network, object detection, video analysis, image visualization, machine learning, algorithm.