Campus safety monitoring system and method based on Internet of Things
A security monitoring system and security monitoring technology, which can be used in closed-circuit television systems, televisions, sensors, etc., and can solve problems such as weak security
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0046] Such as figure 1 As shown, a campus security monitoring system based on the Internet of Things includes multiple cameras installed in the campus (the camera adopts Dahua 8 million DH-SDT-5A1804WA-C8P network high-definition infrared waterproof wide dynamic monitoring camera), and is installed in the security guard The monitoring terminal in the room (using Lenovo all-in-one desktop computer) and the mobile phone terminal of the school personnel (using Huawei P40 mobile phone); also includes the server (the model uses Dell EMC PowerEdgeT30 micro-tower server), the server includes database, input module, processing module and output module; where:
[0047] The database is used to store the pre-stored face images of personnel in the school and the installation location information of each camera on the campus; the pre-stored face images are bound with corresponding mobile phone numbers; in this embodiment, for ease of illustration, three cameras (one No. camera, No. 2 cam...
Embodiment 2
[0063] Compared with Embodiment 1, the only difference is that it also includes an image acquisition module arranged on a slippery road section for real-time acquisition of video images; an input module is also used for acquiring video images; a processing module is also used for using frame The inter-difference method processes the video image into an image sequence. If a moving target appears in each frame of the image sequence, the moving target is positioned and the human body outline frame is extracted; an analysis module is also included to establish a two-dimensional model, and each frame The human body outline frame extracted from the image sequence is input into the two-dimensional model, and the angle parameters between each human body outline frame and the horizontal axis are calculated. If the angle parameter is less than the preset angle threshold, it is judged that a fall behavior has occurred, and a fall prompt message is generated. ; The output module is also us...
Embodiment 3
[0070] Compared with Embodiment 2, the only difference is that the database is also used to store several falling images in advance; it also includes a judging module, which is used to judge whether there is a falling target in each frame image sequence according to the prestored falling images, If the image sequence has a falling target, record the time stamp of the image sequence to generate the first time information; and extract the image sequence in which the human body outline frame of the falling target is standing in the previous frame image, generate a reference image, and record the same The time stamp of the image sequence generates second time information; the processing module is also used to calculate the absolute value of the difference between the first time information and the second time information, if the absolute value is greater than the second preset threshold, it is judged as normal sitting On the contrary, it is determined as a falling state; in other e...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com