This research addresses the problem of early detection of smoke and open fire on the observed territory by unmanned aerial vehicles. We solve the tasks of improving the quality of incoming video data by removing motion blur and stabilizing the video stream; detecting the horizon line in the frame; and identifying fires using semantic segmentation with Euclidean–Mahalanobis distance and the modified convolutional neural network YOLO. The proposed horizon line detection algorithm allows for cutting off unnecessary information such as cloud-covered areas in the frame by calculating local contrast, which is equivalent to the pixel informativeness indicator of the image. Proposed preprocessing methods give a delay of no more than 0.03 s due to the use of a pipeline method for data processing. Experimental results show that the horizon clipping algorithm improves fire and smoke detection accuracy by approximately 11%. The best results with the neural network were achieved with YOLO 5m, which yielded an F1 score of 76.75% combined with a processing speed of 45 frames per second. The obtained results differ from existing analogs by utilizing a comprehensive approach to early fire detection, which includes image enhancement and alternative real-time video processing methods.
В работе представлен обзор современных методов обработки данных дистанционного зондирования Земли. Дан анализ работ, посвященных решению задач предварительного анализа снимков, выделения и распознавания целевых объектов для их дальнейшего мониторинга. Сделаны акценты на гибридные методы анализа снимков с применением, в том числе, технологий высокопроизводительной обработки и искусственных нейронных сетей. Показаны особенности, проблемы и тенденции развития технологий обработки больших данных в различных прикладных задачах дистанционного зондирования.
Рассмотрены методы когнитивно/графического представления телеметрической информации. Выполнен анализ применимости существующих методов визуализации многомерных данных для мониторинга динамических систем реального времени со сложной иерархической структурой. В заключительной части работы представлена таблица, обобщающая результаты анализа исследуемых методов.
It is considered an analytic least squares approximation of function of several variables that participate in the description of control object models and optimization algorithms. As examples of...
1 December 2011 in Scientific and Technical Information Processing
The paper summarizes the experience of developing the PS ANN image recognition software system based on artificial neural networks (ANNs). The real abilities of neural networks to solve image...
1 January 2015 in Program Systems: Theory and Applications