Abstract
Forest fires are still a large concern in several countries due to the social, environmental and economic damages caused. This paper aims to show the design and validation of a proposed system for the classification of smoke columns with object detection and a deep learning-based approach. This approach is able to detect smoke columns visible below or above the horizon. During the dataset labelling, the smoke object was divided into three different classes, depending on its distance to the horizon, a cloud object was also added, along with images without annotations. A comparison between the use of RetinaNet and Faster R-CNN was also performed. Using an independent test set, an F1-score around 80%, a G-mean around 80% and a detection rate around 90% were achieved by the two best models: both were trained with the dataset labelled with three different smoke classes and with augmentation; Faster R-CNNN was the model architecture, re-trained during the same iterations but following different learning rate schedules. Finally, these models were tested in 24 smoke sequences of the public HPWREN dataset, with 6.3 min as the average time elapsed from the start of the fire compared to the first detection of a smoke column.
Highlights
Forest fires have been one of the most devastating events in recent years, due to their uncontrollable nature, with a 2002–2016 mean annual global estimated burned area of 4,225,000 km2 [1]
The F1i denotes the F1-score of the smoke image at the position ith of the fire sequence and the FPRC, FPRE and false-positive rate (FPRT) denote the false-positive ratio for cloud, empty and all images respectively
A deep learning object detection model based on the Detectron2 platform was implemented for smoke detection in outdoor fires
Summary
Forest fires have been one of the most devastating events in recent years, due to their uncontrollable nature, with a 2002–2016 mean annual global estimated burned area of 4,225,000 km2 [1]. Applications related to the prediction, management and detection of wildfires have been improved in recent years with the use of Machine Learning methods [2]. A recent study [3] has shown that investments in detection innovations, such as fire weather services, fixed lookouts and geospatial technologies can achieve high net benefits in the medium or long term, when considering that they have a high cost investment at short term (due to the services installations), but can provide savings for each fire that was controlled at an early stage, with most of the developed system with systems ranging from signal-based to image-based [9,10,11]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
