Seismic gap detection method based on computer vision

Abstract

The invention discloses a seismic gap detection method based on computer vision. The method mainly comprises the steps: (1) acquiring a seismic point distribution binary image; (2) detecting all potential gaps through a distance change algorithm, a segmentation algorithm and iterative comparison to obtain a potential gap distribution image with an optimal detection effect; (3) obtaining the long-axis length and the aperture azimuth angle of each potential seismic gap in the potential gap distribution image with the optimal detection effect through a contour detection algorithm; and (4) judgingthe potential gaps in the potential gap distribution image with the optimal detection effect, distinguishing whether the potential gaps are seismic gaps or non-seismic gaps, keeping the seismic gaps,deleting the non-seismic gaps, and obtaining a seismic gap distribution map and seismic gap characteristic parameters of each seismic gap in the map. The method provided by the invention realizes automatic detection and identification of the seismic gaps, and gives the seismic gap distribution image and the seismic gap characteristic parameters, and providing a powerful tool for seismic prediction and related research by seismic researchers.

Description

technical field [0001] The invention relates to the field of seismology, in particular to a target recognition algorithm and a contour segmentation algorithm. Background technique [0002] Seismic gaps are sections of plate boundary zones and active fault zones that have not experienced major earthquake ruptures for a long time [1] . The second type of gap in the seismic gap refers to the weakening of relatively low-magnitude seismic activity near the epicenter before the occurrence of strong earthquakes, and the strengthening of such seismic activity in the surrounding areas [2] , used to predict the location and magnitude of strong magnitude earthquakes. Different characteristic parameters of seismic gaps correspond to different earthquake levels. For example, the long axis of the gap for earthquakes of magnitude 5-6 is generally 100-300 km, and the aperture azimuth angle of earthquakes that surround the gap is not greater than 120 degrees, etc. [3-7] . [0003] The ex...

AI Technical Summary

Problems solved by technology

[0004] (1) The number of seismic points is large, the screening process is complicated, and the manual efficiency is low

[0005] (2) Manual search for empty areas is likely to cause missed reports of empty areas and affect the accuracy of results

[0006] (3) Manual drawing of the empty area has a large randomness, and the size and shape of the empty area lack consistency

[0007] (4) The process of manually extracting the features of the gob is complicated, and the measurement process is prone to errors, which will affect the magnitude prediction results

Images