Figure 6 - uploaded by Pedro Gamboa
Content may be subject to copyright.
Source publication
![Figure 1: Receiver Operating Characteristics (ROC) curve Source: [13]](profile/Pedro-Gamboa/publication/341872500/figure/fig1/AS:898320742510595@1591187763587/Receiver-Operating-Characteristics-ROC-curve-Source-13_Q320.jpg)
In recent years, large patches of forest have been destroyed by fires, bringing tragic consequences for the environment and small settlements established around these regions. In this context, it is essential that fire fighting teams possess an increased situational awareness about the fire propagation, in order to promptly act in the extinguishing...
Similar publications
To meet the needs of embedded intelligent forest fire monitoring systems using an unmanned aerial vehicles (UAV), a deep learning fire recognition algorithm based on model compression and lightweight requirements is proposed in this study. The algorithm for the lightweight MobileNetV3 model was developed to reduce the complexity of the conventional...
In recent years, the frequent occurrence of forest fires has caused serious impact on the environment and economy. Fire detection has become a hot research direction. Despite the remarkable achievements, the unmanned aerial vehicle (UAV) still has some problems such as insufficient precision and excessive parameters. In order to improve the applica...
Citations
... As artificial intelligence advances within the realm of computer vision, deep learning [15] has emerged as the mainstream approach, leveraging its ability to automatically extract required features. Deep learning is a multi-layer neural network algorithm capable of automatically learning data features from datasets, and it has been applied to analyze and extract information from images captured by drones [16][17][18][19][20]. Lecun first proposed the use of convolutional neural networks (CNN) in 1998 with LeNet [21], which employed weight sharing to reduce the computational load of neural networks, greatly advancing the application of deep learning in image recognition. ...
Wildfires usually lead to a large amount of property damage and threaten life safety. Image recognition for fire detection is now an important tool for intelligent fire protection, and the advancement of deep learning technologies has enabled an increasing number of cameras to possess functionalities for fire detection and automatic alarm triggering. To address the inaccuracies in extracting texture and positional information during intelligent fire recognition, we have developed a novel network called DCP-Net based on UNet, which excels at capturing flame features across multiple scales. We conducted experiments using the Corsican Fire Dataset produced by the “Environmental Science UMR CNRS 6134 SPE” laboratory at the University of Corsica and the BoWFire Dataset by Chino et al. Our algorithm was compared with networks such as SegNet, UNet, UNet++, and PSPNet, demonstrating superior performance across three metrics: mIoU, F1-score, and OA. Our proposed deep learning model achieves the best mIoU (78.9%), F1-score (76.1%), and OA (96.7%). These results underscore the robustness of our algorithm, which accurately identifies complex flames, thereby making a significant contribution to intelligent fire recognition. Therefore, the proposed DCP-Net model offers a viable solution to the challenges of wildfire monitoring using cameras, with hardware and software requirements typical of deep learning setups.
... This approach has potential to gain fine-grained parameter information (such as flame height, width, and area) in complex fire scenarios. De et al. proposed a rule-based color model, which employed the RGB and YCbCr color spaces to allow the simultaneous detection of multiple fires [7]. Wang et al. introduced an attention-guided optical satellite video smoke segmentation network that effectively suppresses the ground background and extracts the multi-scale features of smoke [8]. ...
The accurate analysis of multi-scale flame development plays a crucial role in improving firefighting decisions and facilitating smart city establishment. However, flames’ non-rigid nature and blurred edges present challenges in achieving accurate segmentation. Consequently, little attention is paid to extracting further flame situation information through fire segmentation. To address this issue, we propose Flame-SeaFormer, a multi-scale flame situation detection model based on the pixel-level segmentation of visual images. Flame-SeaFormer comprises three key steps. Firstly, in the context branch, squeeze-enhanced axial attention (SEA attention) is applied to squeeze fire feature maps, capturing dependencies among flame pixels while reducing the computational complexity. Secondly, the fusion block in the spatial branch integrates high-level semantic information from the contextual branch with low-level spatial details, ensuring a global representation of flame features. Lastly, the light segmentation head conducts pixel-level segmentation on the flame features. Based on the flame segmentation results, static flame parameters (flame height, width, and area) and dynamic flame parameters (change rates of flame height, width, and area) are gained, thereby enabling the real-time perception of flame evolution behavior. Experimental results on two datasets demonstrate that Flame-SeaFormer achieves the best trade-off between segmentation accuracy and speed, surpassing existing fire segmentation methods. Flame-SeaFormer enables precise flame state acquisition and evolution exploration, supporting intelligent fire protection systems in urban environments.
... Acquiring data regarding Earth has been an utterly important task, from the construction of the rst maps to the implementation of more complex surveillance algorithms as happens today. The development of Unmanned Aerial Vehicles (UAV's), also known as drones, permitted the observation of the Earth in diverse applications, such as target location [2], agriculture [3] and re monitoring [8]. The Eye in the Sky project [1] is an example of this latter application. ...
High-altitude balloons (HAB), allied with flying-wing unmanned aerial vehicles (UAV), may play an important role in fire monitoring. Due to their aerostatic lift, a HAB may effortlessly carry an UAV to reach higher altitudes and therefore survey a wider area. Considering high-altitude UAV acquired imagery, this work presents a direct georeferencing method based on the geolocation algorithm, that consists on computing the pose of the camera with respect to the ground followed by the mapping between a 3D point and a 2D image pixel using the projection equation. Real-flight data covering diverse situations is used for evaluating the algorithm performance. The complementary filter is used on the measurements from the payload sensors to compute the necessary parameters for the direct georeferencing.KeywordsDirect georeferencingAerial imageryHigh altitude balloon
... UAVs collected real-time images with flexible mobility and variable views and were able to enter dangerous areas and communicate heterogeneous environments in [9]. Furthermore, similar methods have been explored detecting forest fires in aerial images in [10][11][12][13]. However, recognizing forest fires using aerial imagery is challenging due to the fires' various shapes, sizes, and spectral overlaps. ...
... Celik et al. [15] introduced a background subtraction method for segmenting fire candidate pixels and a generalized statistical model for enhanced fire-pixel detection. De et al. [10] utilized a rule-based color model that used RGB and YCbCr color spaces, allowing the detection of multiple fires simultaneously. In addition, they created a geolocation-based algorithm to estimate the fire location in terms of latitude, longitude, and altitude. ...
Forest fires are among the most critical natural tragedies threatening forest lands and resources. The accurate and early detection of forest fires is essential to reduce losses and improve firefighting. Conventional firefighting techniques, based on ground inspection and limited by the field-of-view, lead to insufficient monitoring capabilities for large areas. Recently, due to their excellent flexibility and ability to cover large regions, unmanned aerial vehicles (UAVs) have been used to combat forest fire incidents. An essential step for an autonomous system that monitors fire situations is first to locate the fire in a video. State-of-the-art forest-fire segmentation methods based on vision transformers (ViTs) and convolutional neural networks (CNNs) use a single aerial image. Nevertheless, fire has an inconsistent scale and form, and small fires from long-distance cameras lack salient features, so accurate fire segmentation from a single image has been challenging. In addition, the techniques based on CNNs treat all image pixels equally and overlook global information, limiting their performance, while ViT-based methods suffer from high computational overhead. To address these issues, we proposed a spatiotemporal architecture called FFS-UNet, which exploited temporal information for forest-fire segmentation by combining a transformer into a modified lightweight UNet model. First, we extracted a keyframe and two reference frames using three different encoder paths in parallel to obtain shallow features and perform feature fusion. Then, we used a transformer to perform deep temporal-feature extraction, which enhanced the feature learning of the fire pixels and made the feature extraction more robust. Finally, we combined the shallow features of the keyframe for de-convolution in the decoder path via skip-connections to segment the fire. We evaluated empirical outcomes on the UAV-collected video and Corsican Fire datasets. The proposed FFS-UNet demonstrated enhanced performance with fewer parameters by achieving an F1-score of 95.1% and an IoU of 86.8% on the UAV-collected video, and an F1-score of 91.4% and an IoU of 84.8% on the Corsican Fire dataset, which were higher than previous forest fire techniques. Therefore, the suggested FFS-UNet model effectively resolved fire-monitoring issues with UAVs.
... The current fire detection methods consist of applying image processing techniques to onboard visual and infrared sensors data [2,3]. These techniques use characteristic features such as color, motion, and geometry to detect the flame or smoke generated by the fire [4][5][6][7]. Object detection is one of the classical problems in computer vision. It not only classifies the object in image but also localizes that object. ...
Forest fires around the world are the main cause of devastating millions of forest hectares, destroying several infrastructures and unfortunately causing many human casualties among both fire fighting crews and civilians that might be accidentally surrounded by the fire. The early detection of more than 58,950 forest fires and the real-time fire perception are two key factors that allow the firefighting crews to act accordingly in order to prevent the fire from achieving unmanageable proportions [1]. Forest fire detection is such a challenging problem for the current world. Traditional methodologies depend on a set of expensive hardware and sensors that might be not accurate due to some environment parameters and weather fluctuations. This paper proposes an accurate intelligent deep learning-based YOLOv5 model to detect forest fires from a given aerial images.
... In the application of wildfire fighting, human firefighters on the ground need online and dynamic observation of the firefront (i.e., the moving edge of fire) to anticipate a wildfire's unknown characteristics, such as size, scale, and propagation velocity, in order to plan their strategies accordingly. To support human firefighters, teams of UAVs can be deployed as MSNs to estimate the states of fire across thousands of acres and provide human firefighters with such information [24,25,5]. Figure 1a demonstrates an example of separating wildfire areas for coverage and tracking based on fire propagation velocity and direction. The firefront in each area is moving in a different direction and with a varying velocity and, therefore, at least one separate UAV is required to monitor and track the firefront in each area. ...
... Fighting wildfires safely and effectively requires accurate online information on firefront location, size, shape, and propagation velocity [31,32,33,24]. To provide firefighters with this realtime information, researchers have sought to utilize satellite feeds to estimate fire location information [34,35,36]. ...
... Unfortunately, the resolution of these images is too low for more than simple detection of a wildfire's existence [36]. Firefighters need frequent, high-quality images of the wildfire to make strategic plans [24,10,37]. Here, we define high-quality information as local, high-resolution images (or other sensory information) that are captured from a close by distance with respect to the areas prioritized by humans. ...
In recent years, teams of robot and Unmanned Aerial Vehicles (UAVs) have been commissioned by researchers to enable accurate, online wildfire coverage and tracking. While the majority of prior work focuses on the coordination and control of such multi-robot systems, to date, these UAV teams have not been given the ability to reason about a fire’s track (i.e., location and propagation dynamics) to provide performance guarantee over a time horizon. Motivated by the problem of aerial wildfire monitoring, we propose a predictive framework which enables cooperation in multi-UAV teams towards collaborative field coverage and fire tracking with probabilistic performance guarantee. Our approach enables UAVs to infer the latent fire propagation dynamics for time-extended coordination in safety-critical conditions. We derive a set of novel, analytical temporal, and tracking-error bounds to enable the UAV-team to distribute their limited resources and cover the entire fire area according to the case-specific estimated states and provide a probabilistic performance guarantee. Our results are not limited to the aerial wildfire monitoring case-study and are generally applicable to problems, such as search-and-rescue, target tracking and border patrol. We evaluate our approach in simulation and provide demonstrations of the proposed framework on a physical multi-robot testbed to account for real robot dynamics and restrictions. Our quantitative evaluations validate the performance of our method accumulating \(7.5\times\) and \(9.0\times\) smaller tracking-error than state-of-the-art model-based and reinforcement learning benchmarks, respectively.
... In the application of wildfire fighting, human firefighters on the ground need online and dynamic observation of the firefront (i.e., the moving edge of fire) to anticipate a wildfire's unknown characteristics, such as size, scale, and propagation velocity, in order to plan their strategies accordingly. To support human firefighters, teams of UAVs can be deployed as MSNs to estimate the states of fire across thousands of acres and provide human firefighters with such information [24,25,5]. Figure 1a demonstrates an example of separating wildfire areas for coverage and tracking based on fire propagation velocity and direction. The firefront in each area is moving in a different direction and with a varying velocity and, therefore, at least one separate UAV is required to monitor and track the firefront in each area. ...
... Fighting wildfires safely and effectively requires accurate online information on firefront location, size, shape, and propagation velocity [31,32,33,24]. To provide firefighters with this realtime information, researchers have sought to utilize satellite feeds to estimate fire location information [34,35,36]. ...
... Unfortunately, the resolution of these images is too low for more than simple detection of a wildfire's existence [36]. Firefighters need frequent, high-quality images of the wildfire to make strategic plans [24,10,37]. Here, we define high-quality information as local, high-resolution images (or other sensory information) that are captured from a close by distance with respect to the areas prioritized by humans. ...
In recent years, teams of robot and Unmanned Aerial Vehicles (UAVs) have been commissioned by researchers to enable accurate, online wildfire coverage and tracking. While the majority of prior work focuses on the coordination and control of such multi-robot systems, to date, these UAV teams have not been given the ability to reason about a fire's track (i.e., location and propagation dynamics) to provide performance guarantee over a time horizon. Motivated by the problem of aerial wildfire monitoring, we propose a predictive framework which enables cooperation in multi-UAV teams towards collaborative field coverage and fire tracking with probabilistic performance guarantee. Our approach enables UAVs to infer the latent fire propagation dynamics for time-extended coordination in safety-critical conditions. We derive a set of novel, analytical temporal, and tracking-error bounds to enable the UAV-team to distribute their limited resources and cover the entire fire area according to the case-specific estimated states and provide a probabilistic performance guarantee. Our results are not limited to the aerial wildfire monitoring case-study and are generally applicable to problems, such as search-and-rescue, target tracking and border patrol. We evaluate our approach in simulation and provide demonstrations of the proposed framework on a physical multi-robot testbed to account for real robot dynamics and restrictions. Our quantitative evaluations validate the performance of our method accumulating 7.5x and 9.0x smaller tracking-error than state-of-the-art model-based and reinforcement learning benchmarks, respectively.
... Although natural fires play a role in managing the ecosystem, wildfires have a negative impact, destroying millions of ha of forest woodlands, causing the loss of human and animal lives, and immense economic damage. If global numbers are considered, wildfires affect 67 million hectares worldwide per year, approximately 1.7% of the land area [4]. The annual average global economic burden of fires considering firefighting, economic damage to infrastructures, financial losses of tourist and industrial sector, health issues, etc., are globally over €2,000B/year [5]. ...
Forest fires are among the most dangerous accidents, as they lead to the repercussions of climate change by reducing oxygen levels and increasing carbon dioxide levels. These risks led to the attention of many institutions worldwide, most notably the European Union and the European Parliament, which led to the emergence of many directives and regulations aimed at controlling the phenomenon of forest fires in Europe, such as the (E.U.) 2019/570. Among the proposed solutions, the usage of unmanned aerial vehicles (UAVs) is considered to operate alongside existing aircraft and helicopters through extinguishing forest fires. Scientific researches in this regard have shown the high effectiveness use of UAVs. Still, some defects and shortcomings appeared during practical experiments represented in the limited operating time and low payload. As UAVs are used for firefighting forest fires, they must be characterized by the heavy payload for the extinguishing fluids, long time for flight endurance during the mission, the ability to high maneuver, and work as a decision-making system.
In this paper, a new UAV platform for forest firefighting is represented named WILD HOPPER.
WILD HOPPER is a 600-liter platform designed for forest firefighting. This payload capacity overcomes typical limitations of electrically powered drones that cannot be used for anything more than fire monitoring, as they do not have sufficient lifting power. The enhanced capabilities of the WILD HOPPER allow it to complement existing aerial means and overcome their main limitations, especially the need to cover night operations. This allows reducing the duration of the wildfires heavily by allowing continuous aerial support to the extinguishing activities once the conventional aerial means (hydroplanes and helicopters) are set back to the base at night. On the other hand, WILD HOPPER has significant powerful advantages due to the accuracy of the release, derived from multirotor platform dynamic capabilities.
... 1. Anti-spoofing capabilities 2. Anti-jamming capabilities 3. Defining all the standards with which the system is compliant. 4. A detailed diagram that shows the system architecture of the C2 link, including informational or data flows and the performance of the subsystem, and values for the data rates and latencies. ...
Systemic integrated Unmanned Aerial System (UAS), is the process of gathering the subsystems into one fulfilled system. This integration is done in order to improve the system performance, reducing operational costs, and improving the time response of the system. Normally, such systems are integrated using different techniques such as communication processes, and computer networking. In this paper, a new integrated system is implemented by linking functionally computing systems and software applications together in one powerful system.
... From an economic perspective, these vehicles have a lower operating cost compared to the use of manned aircraft to perform the same type of mission (Christensen, 2015). The current UAV fire detection systems rely mostly on image processing techniques to perform automatic fire segmentation of onboard footage captured by visible spectrum or forwardlooking infrared (FLIR) cameras (Sousa and Gamboa, 2020;Chamoso et al., 2018;Ma et al., 2018;Yuan et al., 2017;Vipin, 2012). Despite the high detection effectiveness achieved by these systems, each onboard sensor has a limited field-of-view (FOV), meaning that a fire will only be detected when the UAV is flying directly above it. ...
Purpose
The purpose of this paper is to generate optimised trajectories for an unmanned aerial vehicle (UAV) during a forest fire detection mission. It is assumed that the UAV flies 3D curvature-constrained Dubins manoeuvres and has a limited amount of battery energy that prevents it from covering the entire search area in a single trip.
Design/methodology/approach
In this paper, the search area is discretised into a grid of multiple targets, and each target assigned with a score that is proportional to the time elapsed since the last UAV visit. This problem, known as Dubins Airplane Orienteering Problem, consists of finding the number and order of targets to visit and the UAV heading at each target that maximises the total trip score without exceeding the UAV battery energy. The solution is found using the Randomised Variable Neighbourhood Search metaheuristic. All target scores are updated after each trajectory generation according to the elapsed time since the last UAV visit.
Findings
The proposed approach produced feasible results when generating optimised trajectories for a fire detection mission context where energy battery constraints are important.
Practical implications
The authors carry out the planning of UAV missions with limited amounts of onboard energy such as a real fire detection mission using a single electric propulsion and fixed-wing UAV.
Originality/value
This paper introduces an energy-based approach to the Dubins Airplane Orienteering Problem, which takes into account the UAV performance and energy budget when generating optimised trajectories.
