Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree Search
Autonomous systems can help firefighting operations by detecting and locating the fire spot from surveillance images and videos. Similar to many other areas of computer vision, Convolutional Neural Networks (CNNs) have achieved state-of-the-art results for fire and smoke detection and segmentation....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/5/1701 |
| _version_ | 1797473854414651392 |
|---|---|
| author | Gonçalo Perrolas Milad Niknejad Ricardo Ribeiro Alexandre Bernardino |
| author_facet | Gonçalo Perrolas Milad Niknejad Ricardo Ribeiro Alexandre Bernardino |
| author_sort | Gonçalo Perrolas |
| collection | DOAJ |
| description | Autonomous systems can help firefighting operations by detecting and locating the fire spot from surveillance images and videos. Similar to many other areas of computer vision, Convolutional Neural Networks (CNNs) have achieved state-of-the-art results for fire and smoke detection and segmentation. In practice, input images to a CNN are usually downsized to fit into the network to avoid computational complexities and restricted memory problems. Although in many applications downsizing is not an issue, in the early phases of fire ignitions downsizing may eliminate the fire regions since the incident regions are small. In this paper, we propose a novel method to segment fire and smoke regions in high resolution images based on a multi-resolution iterative quad-tree search algorithm , which manages the application of classification and segmentation CNNs to focus the attention on informative parts of the image. The proposed method is more computationally efficient compared to processing the whole high resolution input, and contains parameters that can be tuned based on the needed scale precision. The results show that the proposed method is capable of detecting and segmenting fire and smoke with higher accuracy and is useful for segmenting small regions of incident in high resolution aerial images in a computationally efficient way. |
| first_indexed | 2024-03-09T20:22:32Z |
| format | Article |
| id | doaj.art-a14700596ec54a6ca46a7d0476bcea10 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T20:22:32Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a14700596ec54a6ca46a7d0476bcea102023-11-23T23:44:45ZengMDPI AGSensors1424-82202022-02-01225170110.3390/s22051701Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree SearchGonçalo Perrolas0Milad Niknejad1Ricardo Ribeiro2Alexandre Bernardino3Instituto de Sistemas e Robótica, Instituto Superior Tecnico, University of Lisbon, 1049-001 Lisbon, PortugalInstituto de Sistemas e Robótica, Instituto Superior Tecnico, University of Lisbon, 1049-001 Lisbon, PortugalInstituto de Sistemas e Robótica, Instituto Superior Tecnico, University of Lisbon, 1049-001 Lisbon, PortugalInstituto de Sistemas e Robótica, Instituto Superior Tecnico, University of Lisbon, 1049-001 Lisbon, PortugalAutonomous systems can help firefighting operations by detecting and locating the fire spot from surveillance images and videos. Similar to many other areas of computer vision, Convolutional Neural Networks (CNNs) have achieved state-of-the-art results for fire and smoke detection and segmentation. In practice, input images to a CNN are usually downsized to fit into the network to avoid computational complexities and restricted memory problems. Although in many applications downsizing is not an issue, in the early phases of fire ignitions downsizing may eliminate the fire regions since the incident regions are small. In this paper, we propose a novel method to segment fire and smoke regions in high resolution images based on a multi-resolution iterative quad-tree search algorithm , which manages the application of classification and segmentation CNNs to focus the attention on informative parts of the image. The proposed method is more computationally efficient compared to processing the whole high resolution input, and contains parameters that can be tuned based on the needed scale precision. The results show that the proposed method is capable of detecting and segmenting fire and smoke with higher accuracy and is useful for segmenting small regions of incident in high resolution aerial images in a computationally efficient way.https://www.mdpi.com/1424-8220/22/5/1701fire detectionsmoke detectionaerial imageswildfireconvolutional neural networks |
| spellingShingle | Gonçalo Perrolas Milad Niknejad Ricardo Ribeiro Alexandre Bernardino Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree Search Sensors fire detection smoke detection aerial images wildfire convolutional neural networks |
| title | Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree Search |
| title_full | Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree Search |
| title_fullStr | Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree Search |
| title_full_unstemmed | Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree Search |
| title_short | Scalable Fire and Smoke Segmentation from Aerial Images Using Convolutional Neural Networks and Quad-Tree Search |
| title_sort | scalable fire and smoke segmentation from aerial images using convolutional neural networks and quad tree search |
| topic | fire detection smoke detection aerial images wildfire convolutional neural networks |
| url | https://www.mdpi.com/1424-8220/22/5/1701 |
| work_keys_str_mv | AT goncaloperrolas scalablefireandsmokesegmentationfromaerialimagesusingconvolutionalneuralnetworksandquadtreesearch AT miladniknejad scalablefireandsmokesegmentationfromaerialimagesusingconvolutionalneuralnetworksandquadtreesearch AT ricardoribeiro scalablefireandsmokesegmentationfromaerialimagesusingconvolutionalneuralnetworksandquadtreesearch AT alexandrebernardino scalablefireandsmokesegmentationfromaerialimagesusingconvolutionalneuralnetworksandquadtreesearch |