Method and system for estimating network topological relations of cameras in monitoring scenes

Abstract

The invention relates to the technical field of security and protection, and provides a method and system for establishing network topological relations of cameras in monitoring scenes. The method comprises the steps of resolving the monitoring scenes in video streams shot in a monitoring network into grids, obtaining color histogram information of light streams of all grids in the monitoring scenes, conducting clustering on the grids in the monitoring scenes according to the color histogram information of the light streams of the grids in the monitoring scenes to obtain semantic region segmentation results of the monitoring scenes, and determining the network topological relations among all the cameras according to the semantic region segmentation results in the monitoring scenes. The method and system for establishing the network topological relations among the cameras in the monitoring scenes solves the problem that in the prior art, due to the fact that the topological relations among the cameras are all based on locating and tracking of specific target activities, when obstructions exist in a monitoring environment or the monitoring image resolution ratio is low, algorithm performance decreases sharply.

Description

technical field [0001] The invention belongs to the field of security technology, and in particular relates to a method and system for estimating the topological relationship of a camera network in a monitoring scene. Background technique [0002] The topology estimation of the camera network is a key issue in the deployment of the camera network. Accurate topology estimation can not only grasp the movement patterns of people and crowds in the monitoring area, but also can further optimize the deployment through feedback. [0003] Existing technologies provide some methods for topology estimation of camera networks, including: [0004] 1. Based on the results of people detection and tracking based on image background elimination, the out-of-control correlation of crowd activities among multiple cameras can be obtained to provide a basis for analyzing and establishing the target activity pattern of the entire scene. [0005] 2. Use the personnel pace information captured by ...

AI Technical Summary

Problems solved by technology

[0013] The purpose of the embodiment of the present invention is to provide a method and system for estimating the topological relationship of the camera network in the monitoring scene, so as to solve the problems existing in the prior art. The existing topology inference algorithms are basically based on the positioning and tracking of specific target activities. The video quality requirements are high. When there is occlusion in the monitoring environment or the resolution of the monitoring image is low, the algorithm performance will drop sharply.

Images