Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-camera video concentration method and system in geographic scene with optimized virtual viewpoints

A technology of virtual viewpoint and video concentration, applied in image data processing, instrumentation, 3D modeling, etc., can solve the problems of difficult viewing of video, unfavorable users to quickly view video content, discrete distribution, etc., and achieve the effect of enhancing the effect of fusion expression

Pending Publication Date: 2021-07-30
NANJING UNIV OF FINANCE & ECONOMICS
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] For this reason, the present invention provides a method and system for concentrating multi-camera video in a geographical scene with a preferred virtual viewpoint, to solve the problem that in the prior art, when a user watches a video in VGE, the virtual viewpoint is generally selected at a location close to the original geographical location of the camera. Virtual position, this method is very convenient to watch single-camera, short-term and long-term videos, but if the scene contains multiple videos, and the camera's line of sight directions are different, the fields of view do not overlap each other, and are discretely distributed, it is difficult for users to view through a single virtual viewpoint All videos; and if a separate virtual viewpoint is arranged for each video to watch one by one, the viewing time will be greatly increased, which is not conducive to users to quickly view the video content; There is a problem that the cross-camera global movement of moving objects in the scene cannot be expressed when viewing each video image separately

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-camera video concentration method and system in geographic scene with optimized virtual viewpoints
  • Multi-camera video concentration method and system in geographic scene with optimized virtual viewpoints
  • Multi-camera video concentration method and system in geographic scene with optimized virtual viewpoints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] see figure 1 , by introducing video into VGE and supporting video intelligent analysis with geospatial information, it can realize related functions such as video data organization and management, spatial mapping, and video-scene fusion expression in VGE.

[0095] see figure 2 A method for concentrating multi-camera video in a geographical scene with virtual viewpoint optimization is provided, comprising the following steps:

[0096] S1. Obtain video sequence image information, and collect point pairs with the same name in the video image and the three-dimensional geographic scene model, and obtain coordinate data of the point pair with the same name, and the coordinate data includes image coordinates and geographic coordinates;

[0097] S2. Based on the coordinate data of the point pairs with the same name, the mapping relationship between the video image and the geographic space is established, and the camera field of view is positioned;

[0098] S3. By analyzing t...

Embodiment 2

[0158] see Figure 9 , the present invention also provides a multi-camera video concentration system in a geographical scene with a preferred virtual viewpoint, using the method for concentrating a multi-camera video in a geographical scene with a preferred virtual viewpoint in Embodiment 1 or any possible implementation thereof, the concentration system includes:

[0159] Same-name point acquisition module 1: used to obtain video sequence image information, and collect same-name point pairs in video images and three-dimensional geographic scene models, and obtain coordinate data of the same-name point pairs, and the coordinate data includes image coordinates and geographic coordinates;

[0160] Mapping relationship building module 2: used to establish the mapping relationship between video images and geographic space from the coordinate data of the point pairs with the same name, and locate the camera field of view;

[0161] Camera group observable set generation module 3: us...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-camera video concentration method and system in a geographic scene with optimized virtual viewpoints, and the method comprises the steps of obtaining video sequence image information, collecting homonymy point pairs in a video image and a three-dimensional geographic scene model, and obtaining the coordinate data of the homonymy point pairs; establishing a mapping relation between a video image and a geographic space according to coordinate data of the homonymy point pairs, and positioning a camera vision field; constructing a camera observation domain model by analyzing the observable distance and the sight line deflection angle, and generating a camera group observable set; optimizing the observable set by constructing an evaluation model to obtain a virtual viewpoint group; and presetting display parameters of the moving target, and performing multi-camera video concentration according to the display parameters. The invention has the remarkable effects that the mapping relation between the video target and the geographic scene is established, the fusion expression effect of the monitoring video in the geographic scene is enhanced, and great convenience is provided for rapid retrieval and efficient understanding of video geographic scene information integration.

Description

technical field [0001] The invention relates to the technical field of real-time fusion of video streams and three-dimensional models, in particular to a multi-camera video concentration method and system in geographical scenes with optimal virtual viewpoints. Background technique [0002] As the accuracy and real-time requirements of virtual geographic environment (VGE) for scene simulation are improved, multi-source heterogeneous data is introduced to enhance the visual expression and analysis functions of VGE. Among them, video data can not only realize the real scene display of geographical environment, but also describe the temporal and spatial movement of moving objects (pedestrians, vehicles, etc.) in geographical scenes. When a user watches a video in VGE, the virtual viewpoint is generally selected at a virtual position close to the original geographic location of the camera. [0003] However, the traditional virtual viewpoint selection method often has the followi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/70G06T17/05
CPCG06T7/70G06T17/05Y02T10/40
Inventor 解愉嘉毛波王崴
Owner NANJING UNIV OF FINANCE & ECONOMICS