A Two-Stream CNN Model with Adaptive Adjustment of Receptive Field Dedicated to Flame Region Detection

A Vision-Based Detection and Spatial Localization Scheme for Forest Fire Inspection from UAV

Forest fires have the characteristics of strong unpredictability and extreme destruction. Hence, it is difficult to carry out effective prevention and control. Once the fire spreads, devastating damage will be caused to natural resources and the ecological environment. In order to detect early forest fires in real-time and provide firefighting assistance, we propose a vision-based detection and spatial localization scheme and develop a system carried on the unmanned aerial vehicle (UAV) with an OAK-D camera. During the high incidence of forest fires, UAVs equipped with our system are deployed to patrol the forest. Our scheme includes two key aspects. First, the lightweight model, NanoDet, is applied as a detector to identify and locate fires in the vision field. Techniques such as the cosine learning rate strategy and data augmentations are employed to further enhance mean average precision (mAP). After capturing 2D images with fires from the detector, the binocular stereo vision is applied to calculate the depth map, where the HSV-Mask filter and non-zero mean method are proposed to eliminate the interference values when calculating the depth of the fire area. Second, to get the latitude, longitude, and altitude (LLA) coordinates of the fire area, coordinate frame conversion is used along with data from the GPS module and inertial measurement unit (IMU) module. As a result, we experiment with simulated fire in a forest area to test the effectiveness of this system. The results show that 89.34% of the suspicious frames with flame targets are detected and the localization error of latitude and longitude is in the order of 10−5 degrees; this demonstrates that the system meets our precision requirements and is sufficient for forest fire inspection.

Numerical Study on Effects of Pipeline Geometric Parameters on Release Characteristics of Gas Extinguishing Agent

In order to guide the optimization design of the pipeline network of the aircraft-fixed gas fire extinguishing system and improve its fire extinguishing performance, FLUENT software was used to simulate the influence of pipeline parameters such as diameter, length, and roughness on the release characteristics of the fire extinguishing agent. It can be found that the extinguishing agent can be divided into liquid and vapor extinguishing agents in the fire extinguishing pipeline system during the release. The spatial distribution and proportion of the liquid and vapor extinguishing agents are asymmetric. Results show that the peak value of the pressure drop rate (dPmax) has a good quadratic function relationship with the pipeline diameter (D) and the functional relationship is dPmax=−22.224+2.782D+0.089D2, which means that the peak value increased significantly with the increase in the pipeline diameter. Moreover, when the pipeline diameter is 25 mm, the average pressure drop rate of the vessel is about 35.02 MPa/s, which is 5.97 times the value of the average pressure drop rate when the pipeline diameter is 10 mm. With the increase in the pipeline diameter, the release time decreases significantly, the mass flow rate increases obviously, while the gasification ratio decreases rapidly at first and then increases slightly. The pipeline length also has a significant influence on the release characteristics of the extinguishing agent. With the increase in the pipeline length, the release time and the gasification ratio increase linearly, while the mass flow rate decreases linearly. Compared with the pipeline diameter and pipeline length, the influence of the pipeline roughness on the release characteristics of the extinguishing agent is weak. With the increase in the pipeline roughness, the release time and the gasification ratio of the extinguishing agent increases slowly, while the mass flow rate decreases slowly.

A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.