A Background Filtering Method for Locating Underground Buildings in Mountains Using Dual-temporal Detection

Abstract

The invention discloses a background filtering method for locating underground buildings in mountains by using dual-time phase detection. It includes three steps: preprocessing of infrared image filtering, rough detection of underground buildings based on the low-level pixel gray value of infrared images, and "onion peeling" algorithm to optimize and precise detection. By obtaining dual-temporal infrared images during the day and night, the The infrared image at night is used as the background field. First, the daytime infrared image is subjected to bilateral filtering to remove noise, and then cluster analysis is performed to detect the suspected target area. The suspected target area is processed using the truncation algorithm based on adjacent pixels to roughly detect the underground building area. , using the roughly detected underground building area as the optimization criterion, background filtering is performed on the suspected target area, and the "onion peeling" algorithm is used to uncover the mountain in the area layer by layer until the underground building is detected accurately to the greatest extent. The invention avoids the problem of difficulty in acquiring multi-temporal infrared images, and can accurately detect deep underground buildings.

Description

technical field [0001] The invention belongs to the cross technical field of physical geography, thermophysics and information processing, and more specifically relates to a background filtering method for using dual-temporal detection and positioning of underground buildings in mountains. Background technique [0002] In recent years, due to the needs of various underground resources, mineral resources and groundwater, a large number of underground buildings have been built, and the detection technology of underground buildings has attracted extensive attention. Various underground buildings are distributed and have heat radiation. Different from the background heat source, the underground resource temperature is higher / lower than the mountain background, which is considered as the underground heat source / cold source. Conventional remote sensing detection only realizes conditional objects on the surface or water surface, and is only suitable for the detection process in whi...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the above defects or improvement needs of the prior art, the present invention provides a background filtering method that uses dual-temporal detection to locate underground buildings in mountains, which avoids the difficulty of obtaining multi-temporal infrared images and can accurately detect deep underground buildings. architecture

Images