Fire fighting access occupation detection method and system based on depth information

A technology of fire exit and detection method, applied in data processing applications, instruments, character and pattern recognition, etc., can solve the problems of large error in abnormal target size, low accuracy, false alarm, etc., to avoid false alarm problems and reduce leakage. The effect of detecting problems and reducing the false negative rate

Pending Publication Date: 2022-04-19
海纳云物联科技有限公司 +1
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For example, the invention patent with the application number CN202011013470.3 discloses an adaptive detection method for fire exit occupancy based on surveillance video. Although to a certain extent, this solution has the following disadvantages: (1). The frame difference method judges the area ratio of different areas of the image to judge the size of the abnormal target. The error is too large, which may easily lead to false positives; (2) Judging whether the fire exit is occupied by communicating with the key area through the external rectangular frame of the abnormal object, because the two-dimensional image has perspective Phenomenon, this kind of judgment method is easy to judge objects that are not on the channel as being on the channel, resulting in false alarms; (3), outdoor light changes frequently, Gaussian modeling is performed through pixel values, and the accuracy rate is low

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
  • Fire fighting access occupation detection method and system based on depth information
  • Fire fighting access occupation detection method and system based on depth information
  • Fire fighting access occupation detection method and system based on depth information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] Such as figure 1 As shown, this embodiment discloses a method for detecting the occupancy of fire exits based on depth information, including the following steps:

[0074] S1: Collect real-time depth images and real-time color images of fire exits;

[0075] S2: Acquiring potential targets based on the collected real-time depth image, and cutting out the potential targets from the real-time color image;

[0076] S3: Perform multi-label classification on the intercepted potential targets, and determine whether to warn and the level of warning according to the classification results.

[0077] The fire exit occupancy detection method based on depth information provided by this embodiment obtains potential targets by fusing depth information, effectively avoids false alarms caused by two-dimensional perspective transformation, and effectively solves the problem that traditional detection methods cannot detect all Objects occupying indoor fire exits are detected, and the ac...

Embodiment 2

[0151] This embodiment provides a fire exit occupancy detection system based on depth information. The system includes an image acquisition unit, a processor, and a memory, wherein the processor implements the above embodiments when executing the computer program stored in the memory. A fire exit occupancy detection method.

[0152] In the above solution, the image acquisition unit includes a camera or a camera capable of acquiring real-time depth images and real-time color images of fire exits in real time.

[0153] Preferably, the image acquisition unit includes: an RGBD camera installed in the fire escape, used to collect real-time depth images and real-time color images of the fire escape, so as to monitor whether the fire escape is occupied.

[0154] In this embodiment, the RGBD camera is used as the image acquisition unit. Compared with using two cameras to acquire the color image and the depth image respectively, the acquisition of the depth image and the color image ca...

Embodiment 3

[0157] This embodiment also provides a computer-readable storage medium, where instructions are stored on the computer-readable storage medium, and when the instructions are executed by the processor, the method for detecting the occupancy of fire exits based on depth information in the first embodiment above is implemented step.

[0158] For example, when the processor executes the computer program, the following steps are implemented:

[0159] S1: Collect real-time depth images and real-time color images of fire exits;

[0160] S2: Acquiring potential targets based on the collected real-time depth image, and cutting out the potential targets from the real-time color image;

[0161] S3: Perform multi-label classification on the intercepted potential targets, and determine whether to warn and the level of warning according to the classification results.

[0162] In addition, the above logic instructions in the memory can be implemented in the form of software functional unit...

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 fire fighting access occupation detection method and system based on depth information. The method comprises the following steps: acquiring a real-time depth image and a real-time color image of a fire fighting access; obtaining a potential target based on the collected real-time depth image, and cutting out the potential target from the real-time color image; and carrying out multi-label classification on the intercepted potential targets, and determining whether to carry out early warning or not and the early warning level according to a classification result. According to the fire fighting access occupation detection method provided by the invention, the potential targets are obtained by fusing the depth information, the problem of false alarm caused by two-dimensional perspective transformation is effectively avoided, the potential targets are classified based on multi-label classification, early warning is performed according to the classification result, the probability of false alarm and missing alarm can be greatly reduced, and the accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of household appliances, and in particular relates to a method and system for detecting the occupancy of a fire exit based on depth information. Background technique [0002] The fire exit is the life passage. It is an important passage for quickly extinguishing fires, saving the lives and property of the people, and reducing losses. It cannot be occupied casually and must be kept open at all times. If the fire exit is occupied, it will bring great hidden dangers to the life and property of the owners of the community. [0003] At present, incidents of loss of human resources and property caused by the occupation of indoor fire escapes occur frequently. In view of the occupation of indoor fire escapes, some old communities adopt manual on-site inspections or call for indoor corridor monitoring. This method is time-consuming and laborious, and cannot be found in time. question. Some new communities install ...

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): G06V20/52G06V10/22G06V10/25G06V10/764G06K9/62G06Q10/06G06Q50/26
CPCG06Q10/0635G06Q50/265G06F18/2431
Inventor 陈斌金岩冯谨强郑慧芬孙少峰安广飞高照远
Owner 海纳云物联科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap