Video image based intelligent construction site regional management and intrusion detection method and system

A video image, intrusion detection technology, applied in image data processing, image enhancement, image analysis and other directions, can solve problems such as insufficient adaptability to field changes, difficulty in meeting requirements, application cost, etc., to save equipment purchase and initial installation. Cost, system deployment is simple and convenient, and the effect of reducing management costs

CN108846335AActive Publication Date: 2018-11-20武汉昊广智联科技有限公司
8 Cites 36 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2018-11-20

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention belongs to the technical field of intelligent construction site management, and discloses a video image based intelligent construction site regional management and intrusion detection method and system. The method includes: automatically recognizing an area divided by placement markers in a monitoring area based on a video monitoring image, adopting a mixed Gaussian model to model avideo image background, and extracting a foreground image containing a moving object; performing median filtering and morphological preprocessing on the foreground image, extracting connected domain features and LBP texture features of the moving object, and adopting the two-level tracking strategy; performing intrusion detection on each extracted moving object and the region detected in the image; sending a sound and light alarm signal according to a regional management specification for a detected illegal intrusion event. The tracking of the moving target adopts the two-level tracking strategy of the connected domain block features and the LBP features, thus ensuring the real-time property and the accuracy of the target tracking.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of smart construction site management, and in particular relates to a video image-based smart construction site area management and intrusion detection method and system. Background technique

[0002] At present, the existing technologies commonly used in the industry are as follows:

[0003] At present, our country is in the stage of large-scale construction of various infrastructures. In 2017, more than 600,000 construction sites are under construction, and the investment is large. At the same time, my country's infrastructure construction is in the transition stage from extensive to intensive. It is urgent to improve management level, reduce costs and increase efficiency. There are many types of construction sites, the site characteristics are also different, and the site conditions are constantly changing, but there is one thing in common: they will be managed in different areas, such as: dangerous area...

Examples

Embodiment Construction

[0090] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0091] In the prior art, image recognition technology is not used to realize partitions in the monitoring area, and target recognition and tracking technology is not used to realize safety management of intrusion and personnel load in each area; in the prior art, equipment installation and maintenance High costs and high management costs. There is no automatic management of new zoning and type definitions.

[0092] The present invention will be further described below in conjunction with specific analysis.

[0093] refer to figure 1 As shown, the video image-based intelligent construction site area management and intrus...