CN-117115248-B - Event positioning method and device, electronic equipment and storage medium

CN117115248BCN 117115248 BCN117115248 BCN 117115248BCN-117115248-B

Abstract

The embodiment of the application provides an event positioning method, an event positioning device, electronic equipment and a storage medium, which relate to the technical field of visual positioning and comprise the steps of obtaining a side view panoramic visible light image of a scene area to be detected and a DEM side view, wherein the DEM side view comprises position information of points in the scene area to be detected, matching the same scene points in the side view panoramic visible light image and the DEM side view to obtain a scene point matching result, performing dense mapping on the side view panoramic visible light image and the DEM side view to obtain a dense mapping relation according to the scene point matching result, and determining the position information of the points in the side view panoramic visible light image according to the position information of the points in the DEM side view and the dense mapping relation. The embodiment of the application improves the precision of positioning information in a large scene.

Inventors

GONG HUI
ZHU HAO
CHEN XIAO
ZHOU JIAQI
TONG JUNYAN
REN YE

Assignees

杭州海康威视数字技术股份有限公司

Dates

Publication Date: 20260508
Application Date: 20230801

Claims (7)

1. An event localization method, comprising: detecting a preset type event on a first side view visible light image of a scene area to be detected to obtain an event detection result; Acquiring first visual angle information when a camera acquires the first side-looking visible light image and a first area in the first side-looking visible light image, wherein the first area is used for generating a preset type event under the condition that the event detection result indicates that the first side-looking visible light image has the preset type event; Acquiring at least one auxiliary image of the first side-looking visible light image and acquiring second visual angle information of the auxiliary image, wherein an acquisition visual field of the auxiliary image comprises a visual field corresponding to the first area, and the magnification of the auxiliary image is smaller than that of the first side-looking visible light image; Determining a second mapping position of the first region in the auxiliary image according to the first view angle information and the second view angle information; Determining a first mapping position of the first region in a side view panoramic visible light image of the scene region to be detected according to the second view angle information and the second mapping position; According to the predetermined position information of each point in the side view panoramic visible light image, the position information of the first mapping position is used as the positioning of a preset type event; the process of pre-determining the position information of each point in the side view panoramic visible light image comprises the following steps: The method comprises the steps of obtaining a side view panoramic visible light image of a scene area to be detected and a DEM side view, wherein the DEM side view is generated according to elevation information and longitude and latitude information of each point in the DEM image of the scene area to be detected, elevation information and longitude and latitude information of a visible light camera, the DEM image is a bird's eye view and comprises position information of each point in the scene area to be detected, matching the same scene points in the side view panoramic visible light image and the DEM side view to obtain a scene point matching result, densely mapping the side view panoramic visible light image and the DEM side view to obtain a densely mapping relation according to the scene point matching result, and determining the position information of each point in the side view panoramic visible light image according to the position information of each point in the DEM side view and the densely mapping relation.
2. The method of claim 1, wherein the first view information is first PTZ information; the acquiring at least one auxiliary image of the first side-looking visible light image and acquiring second viewing angle information of the auxiliary image includes: Acquiring N auxiliary images of the first side-looking visible light image, and acquiring PTZ information of the auxiliary images, wherein N is an integer greater than 1, the first side-looking visible light image is identical to P, T information of the previous N-1 auxiliary images, the N-1 auxiliary image is identical to the N auxiliary image in magnification, the 1 st auxiliary image is larger in magnification than the first side-looking visible light image, the (i+1) th auxiliary image is larger in magnification than the (i) th auxiliary image, i is E [1, N-1], and i is an integer; the determining, according to the first view information and the second view information, a second mapping position of the first region in the auxiliary image includes: Determining a mapping position of the first region in the 1 st auxiliary image according to the first PTZ information and the PTZ information of the 1 st auxiliary image; and determining the mapping position of the first region in the (i+1) th auxiliary image according to the PTZ information of the (i Zhang Jidi i+1) th auxiliary image, wherein the second mapping position is the mapping position of the first region in the (N) th auxiliary image.
3. The method of claim 1, wherein the acquiring a side view panoramic visible image of the region of the scene to be detected comprises: Acquiring sample side-looking visible light images of a scene area to be detected, which are acquired by a visible light camera under a plurality of different view angles, wherein the view fields of adjacent view angles are overlapped; and carrying out panoramic stitching on each sample side-looking visible light image based on the acquisition view angle of each sample side-looking visible light image to obtain a side-looking panoramic visible light image.
4. The method according to claim 1, wherein the densely mapping the side view panoramic visible light image and the DEM side view according to the scene point matching result to obtain a densely mapping relationship includes: Dividing the side view panoramic visible light image into a plurality of visible light areas according to the scene points, and dividing the DEM side view into a plurality of DEM side view areas; and according to the scene point matching result, calculating a mapping transformation matrix of the visible light region and the DEM side view region with the matching relation to obtain a dense mapping relation.
5. An event positioning device, comprising: The event detection module is used for detecting a preset type event on the first side view visible light image of the scene area to be detected to obtain an event detection result; the first region obtaining is used for obtaining first visual angle information when a camera collects the first side-looking visible light image and a first region in which a preset type event occurs in the first side-looking visible light image under the condition that the event detection result indicates that the preset type event exists in the first side-looking visible light image; The image information acquisition module is used for acquiring at least one auxiliary image of the first side-looking visible light image and acquiring second visual angle information of the auxiliary image, wherein an acquisition visual field of the auxiliary image comprises a visual field corresponding to the first area, and the magnification of the auxiliary image is smaller than that of the first side-looking visible light image; a first mapping location determination module comprising: A second mapping position determining sub-module, configured to determine a second mapping position of the first region in the auxiliary image according to the first view angle information and the second view angle information; the first mapping position determining submodule is used for determining a first mapping position of the first region in the side view panoramic visible light image of the scene region to be detected according to the second visual angle information and the second mapping position; The event positioning module is used for taking the position information of the first mapping position as the positioning of a preset type event according to the position information of each point in the preset side view panoramic visible light image; The image acquisition module is used for acquiring a side view panoramic visible light image of a scene area to be detected and a DEM side view, wherein the DEM side view is generated according to elevation information and longitude and latitude information of each point in the DEM image of the scene area to be detected and elevation information and longitude and latitude information of a visible light camera, the DEM image is a bird's eye view, and the DEM side view comprises position information of each point in the scene area to be detected; The scene point matching module is used for matching the same scene points in the side view panoramic visible light image and the DEM side view to obtain a scene point matching result; The dense mapping module is used for carrying out dense mapping on the side view panoramic visible light image and the DEM side view according to the scene point matching result to obtain a dense mapping relation; And the position information determining module is used for determining the position information of each point in the side view panoramic visible light image according to the position information of each point in the side view of the DEM and the dense mapping relation.
6. An electronic device, comprising: A memory for storing a computer program; a processor for implementing the method of any of claims 1-4 when executing a program stored on a memory.
7. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-4.

Description

Event positioning method and device, electronic equipment and storage medium Technical Field The present application relates to the field of visual positioning technologies, and in particular, to an event positioning method, an event positioning device, an electronic device, and a storage medium. Background The forests, the valleys and other large scene areas are wide in land and thin in people, positioning is difficult, and when accidents occur, how to monitor and position the places where accidents happen in a long-distance and high-precision manner is a difficult point which needs to be solved all the time. For example, how to locate the position information of the ignition point in the case of unexpected emergency such as fire disaster is always a difficult problem of fire disaster treatment. The positioning modes proposed in the related art mostly have the problems of difficult implementation, low positioning precision and the like, for example, a high-point camera is arranged on a lookout tower, a scheme of monitoring a fire ignition point of a large scene by utilizing video is utilized, and the position of the fire point still cannot be accurately determined due to geographic environment. Disclosure of Invention The embodiment of the application aims to provide an event positioning method, an event positioning device, electronic equipment and a storage medium, so as to improve the accuracy of positioning information in a large scene. The specific technical scheme is as follows: in a first aspect, an embodiment of the present application provides an event positioning method, including: detecting a preset type event on a first side view visible light image of a scene area to be detected to obtain an event detection result; Acquiring first visual angle information when a camera acquires the first side-looking visible light image and a first area in the first side-looking visible light image, wherein the first area is used for generating a preset type event under the condition that the event detection result indicates that the first side-looking visible light image has the preset type event; determining a first mapping position of the first region in a side view panoramic visible light image of the scene region to be detected according to the first view angle information; and according to the predetermined position information of each point in the side view panoramic visible light image, the position information of the first mapping position is used as the positioning of a preset event. In one embodiment of the application, the method further comprises: Acquiring at least one auxiliary image of the first side-looking visible light image and acquiring second visual angle information of the auxiliary image, wherein an acquisition visual field of the auxiliary image comprises a visual field corresponding to the first area, and the magnification of the auxiliary image is smaller than that of the first side-looking visible light image; the determining, according to the first view angle information, a first mapping position of the first region in the side view panoramic visible light image of the to-be-detected scene region includes: Determining a second mapping position of the first region in the auxiliary image according to the first view angle information and the second view angle information; And determining a first mapping position of the first region in the side view panoramic visible light image of the scene region to be detected according to the second view angle information and the second mapping position. In one embodiment of the present application, the first viewing angle information is first PTZ information; the acquiring at least one auxiliary image of the first side-looking visible light image and acquiring second viewing angle information of the auxiliary image includes: Acquiring N auxiliary images of the first side-looking visible light image, and acquiring PTZ information of the auxiliary images, wherein N is an integer greater than 1, the first side-looking visible light image is identical to P, T information of the previous N-1 auxiliary images, the N-1 auxiliary image is identical to the N auxiliary image in magnification, the 1 st auxiliary image is larger in magnification than the first side-looking visible light image, the (i+1) th auxiliary image is larger in magnification than the (i) th auxiliary image, i is E [1, N-1], and i is an integer; the determining, according to the first view information and the second view information, a second mapping position of the first region in the auxiliary image includes: Determining a mapping position of the first region in the 1 st auxiliary image according to the first PTZ information and the PTZ information of the 1 st auxiliary image; and determining the mapping position of the first region in the (i+1) th auxiliary image according to the PTZ information of the (i Zhang Jidi i+1) th auxiliary image, wherein the second mapping position is the m