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

Adaptive detection method of fire exit occupancy based on surveillance video

An adaptive detection and fire exit technology, applied in the field of computer vision, can solve the problems of unsatisfactory accuracy, robustness, and real-time performance, and achieve the effects of avoiding false alarms, improving accuracy, and reducing false alarms

Active Publication Date: 2021-06-29
NANJING ANYUAN TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Artificial monitoring of fire exits consumes a lot of manpower and cannot meet the requirements of accuracy, robustness and real-time

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
  • Adaptive detection method of fire exit occupancy based on surveillance video
  • Adaptive detection method of fire exit occupancy based on surveillance video
  • Adaptive detection method of fire exit occupancy based on surveillance video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0044] The present invention has designed the self-adaptive detection method of fire-fighting channel occupancy based on monitoring video, such as figure 1 As shown, the steps are as follows:

[0045] Step 1: Obtain the video stream corresponding to the camera in the scene to be detected, intercept a video frame image, draw one or more polygons on the video frame image as the key detection area, and set the key detection area for the video stream All subsequent video frames are valid;

[0046] Step 2: Take the pixel value at a certain position of all frames in a video segment, calculate its average as a standard value for comparison, and use the frame whose pixel value at this position in the video segment is closest to the standard value as the key frame of the video segment ;

[0047] Step 3: Mix Gaussian background modeling, and judge...

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 an adaptive detection method for fire-fighting passage occupancy based on monitoring video, using the target detection technology in the field of computer vision, which is different from other fire-fighting passage occupancy detection methods, does not need to manually construct features, and effectively reduces false alarms in manual feature extraction methods , Occurrence of missed alarms; through the method of mixed Gaussian background modeling, it is easy to detect slow-moving objects; using the target detection algorithm to eliminate people or fire vehicles suspected of occupying objects, effectively avoiding the occurrence of false alarms; using continuous multi- The frame judgment method improves the accuracy of system detection and reduces the occurrence of false positives.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a method for self-adaptive detection of fire exit occupancy. Background technique [0002] "Fire exits" are "life passages", and residents can rest assured only if the "road of life" is kept unimpeded at all times. Fire rescue is a race against time, and blockage of fire exits frequently becomes the biggest obstacle to fire rescue. Once fire exits are blocked or occupied, it will pose a major hidden danger to the safety of residents' lives and property. Realizing efficient detection and real-time early warning of fire exit occupancy is a problem that needs to be solved urgently in the current society. Artificial monitoring of fire exits consumes a lot of manpower and cannot meet the requirements of accuracy, robustness and real-time performance. Contents of the invention [0003] In order to solve the technical problems mentioned in the above-mentioned bac...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/32G06T7/194
CPCG06T7/194G06T2207/10016G06T2207/30232G06V20/52G06V10/25G06V2201/07
Inventor 王三明王聪明云尧王杰胡小敏刘宝
Owner NANJING ANYUAN TECH CO LTD