A Self-Adaptive Wildfire Detection Algorithm with Two-Dimensional Otsu Optimization

Abstract

The gradual increase in wildfires has caused frequent trips and outages along electrical transmission lines, which is a serious threat to the operational stability of power grids. A self-adaptive wildfire detection algorithm has been developed and tested in this paper. Most of existing wildfire detection methods employed fixed thresholds to identify potential wildfire pixels while the background pixels were ignored. By calculating two-dimensional histogram of the brightness temperatures of mid-infrared channel, the threshold selection is self-adaptive and potential pixels containing scenes of fire can be distinguished automatically. Based on the two-dimensional Otsu method and contextual test algorithm, an improved wildfire detection algorithm that uses multitemporal Visible and Infrared Radiometer (VIRR) data is described. The wildfire detection results within three kilometers of electrical transmission lines demonstrate the effectiveness of the proposed method, which has accurate low-temperature wildfire detection ability.

Automatic tracking and intelligent observation of tidal bore propagation velocity based on UAV and computer vision

“…In response to the possibility of poor edge detection performance in image edge detection, Zhang et al 31 used a self-adaptive detection algorithm to detect the wildfire by calculating the two-dimensional histogram of mid-infrared channel. For the case of discontinuous image edges, it is necessary to calculate the difference map between high and low threshold images, and find the position of the endpoint within the high threshold image, Search for any points connected to the edge line within the eight neighborhoods of the corresponding points in the difference graph, and save the eligible points in the set of endpoints until the edges are connected.…”

MSIA-Net: A Lightweight Infrared Target Detection Network with Efficient Information Fusion

“…Liu et al [2] proposed the use of the projection coefficient obtained from principal component analysis as a template and the measurement of the degree of matching through nonlinear correlation. Zhang et al [3] improved the fixed threshold recognition method and proposed a detection algorithm based on two-dimensional Otsu and context testing according to the calculation of a brightness temperature histogram in two-dimensional infrared channels. Yin et al [4] proposed an algorithm based on the combination of the classical W4 and frame difference to overcome the false detection caused by background mutations and eliminate the void caused by frame difference.…”

An Improved Forest Fire Monitoring Algorithm With Three-Dimensional Otsu

“…However, one of the major limitations of this method is that the threshold segmentation method based on the one-dimensional image only reflects the gray level information of a single pixel of the image, and fail to consider the neighborhood information between other pixels such as space [24]. To overcome this issue, G. Zhang [25] applied the Otsu method to high-voltage electric fires, and took into account the value of the pixel and the relationship between the pixels in its field, extending the one-dimensional histogram to the two-dimensional histogram. Although the two-dimensional histogram oblique division method improves the area division, but under the influence of highintensity noise, there are more misclassifications, resulting in poor segmentation results.…”