A method of matching scene coordinates in real-time video with geographic information

Abstract

The invention belongs to the field of information technology, and discloses a method for matching scene coordinates in real-time video with geographic information, which mainly comprises the followingfive steps: S1, establishing a scene geographic information storage table, wherein the scene geographic information storage table comprises geographic information of a plurality of scenes, and the geographic information comprises scene geographic coordinates; S2, reading the real-time geographic coordinates and the photographing height of the photographing main body; S3, according to the geographical coordinates of the shooting main body, the shooting height and the geographical coordinates of each scene are selected to take the scene within the shooting range as the target scene; S4: calculating screen coordinates C (x, y) of the target scene in the real-time video according to the real-time geographic coordinates of the shooting subject, the shooting height and the scene geographic coordinates of the target scene; S5, retrieving a scene geographic information storage table, obtaining geographic information of a target scene, and mar that geographic information of the target scene asgeographic information of screen coordinates C (x, y). The invention solves the problem that the prior video positioning technology is highly dependent on the image processing technology.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to a method for matching scene coordinates in real-time video with geographic information. Background technique [0002] Existing methods for locating objects in real-time video mainly rely on image processing techniques. Specifically, it includes three types: object localization based on contrast analysis, object localization based on matching and object localization based on detection. [0003] Target positioning based on contrast analysis mainly uses the contrast difference between the target and the background to achieve target detection and positioning. [0004] Target localization based on matching mainly achieves target localization through feature matching between previous and subsequent frames. Among them, the characteristics are the attributes that distinguish the target object from other things, and must have distinguishability, reliability, independenc...

AI Technical Summary

Problems solved by technology

[0006] The above positioning methods are mainly to process each detection image, and then locate, which have high requirements on image quality, lighting conditions, and image processing hardware configuration. At present, there are a large number of video channels for urban supervision, especially hundreds of channels of video. particularly high investment

Images