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

Abstract

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.

Table Tennis Track Detection Based on Temporal Feature Multiplexing Network

“…The model proposed in this paper performed cross-sectional performance comparison experiments with lightweight detection networks that were currently widely used in multiple fields. The selected comparison networks included the lightweight one-stage detection model YOLOX [ 91 ], the two-stage lightweight detection network ThunderNet [ 92 ], the ultra-lightweight Anchor Free detection network NanoDet [ 93 ], and detection networks using the lightweight backbone networks, such as ShuffleNetV2 [ 94 ] and MobileNetV3 [ 95 ], combined with the detectors proposed in this paper. The comparison experiments were subdivided into the detection of targets when shooting horizontally versus vertically, and the results of the comparison tests were shown in Figure 17 , Figure 18 , and Figure 19 , respectively.…”

Research on Forest Fire Detection Algorithm Based on Improved YOLOv5

“…Spatial pyramid pooling is a multi-scale feature fusion pooling method that can preserve object features well [30,31], maintain feature map shape, and output fixed-size features with any feature image size as input. The pooling operation, as one of the most basic algorithms for image processing in the field of deep learning, can reduce the size of the feature map of the model by retaining some features while reducing the computational cost, preventing overfitting, and improving the model's generalization ability.…”

Fire image detection based on clustering data mining techniques

“…) 𝑌 𝑋 (4) By maximizing the mutual information, the feature separability also maximised. MIFS selects highly informative features with mutual information as a way of measuring the relationship between two random variables.…”

“…However, establishing a precise and reliable fire detection method is challenging it terms of localization, coverage range and life span of sensor network [3]. Thus, vision-based techniques address the challenge and perform the detection task through aerial images or video and assist in notifying the firefighter's team about the exact fire location [4].…”