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

A video-based fire smoke and spill detection method and system

A technology for spills and fires, which is applied in the field of fire smoke and spills detection. It can solve problems such as poor real-time performance, difficulty in distinguishing spills, and difficulty in large-scale widespread use, so as to ensure accuracy, reduce computing overhead, and reduce computing frequency. Effect

Active Publication Date: 2021-06-08
上海闪马智能科技有限公司
View PDF14 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Patent Document 8 (CN111523536A) discloses an intelligent detection method for adaptive road spills based on Faster RCNN. This method uses a deep learning-based target detection method to detect spills, but the method has poor real-time performance and does not use timing information. , it is difficult to distinguish between spills and other influencing factors
Patent Document 9 (CN111274982A) discloses a method, device, and storage medium for identifying spilled objects. This method uses vehicle trajectory and lane line information in the video, but does not use the video dimension information of the spilled objects. Therefore, the detection of spilled objects low precision
It can be seen that although some event detection methods based on video recognition already exist in the prior art, there are still many shortcomings, and it is difficult to widely promote and use them on a large scale.

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
  • A video-based fire smoke and spill detection method and system
  • A video-based fire smoke and spill detection method and system
  • A video-based fire smoke and spill detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] see figure 1 , figure 1 It is a schematic flowchart of a method for detecting fire smoke and spills based on video disclosed in the embodiment of the present application. Such as figure 1 As shown, a video-based fire smoke and spill detection method according to the embodiment of the present application, the method includes:

[0038] The continuous background modeling module is used to dynamically model the background area, and then the foreground object is extracted by the foreground object extraction module;

[0039] The human-vehicle target filtering module is used to extract the suspected fire smoke or spilled objects from the foreground objects, and then the recognition module performs fusion recognition on the suspected fire smoke or spilled objects, and outputs the detection and recognition results.

[0040] In the embodiment of the present application, the region of interest of suspected fire smoke or spilled objects is extracted through background modeling o...

Embodiment 2

[0064] see figure 2 , figure 2 It is a structural schematic diagram of a video-based fire smoke and spill detection system disclosed in the embodiment of the present application. Such as figure 2 As shown, a video-based fire smoke and spill detection system according to an embodiment of the present application, the system includes a continuous background modeling module, a foreground target extraction module, a human and vehicle target filtering module, and a recognition module;

[0065] The continuous background modeling module is used to dynamically model the background area;

[0066] The foreground object extraction module is used to extract a foreground object based on the background area;

[0067] The person-vehicle target filtering module is used to extract suspected fire smoke or spilled object targets from the foreground targets;

[0068] The recognition module is configured to perform fusion recognition on the suspected fire smoke or spilled objects, and output...

Embodiment 3

[0076] see image 3 , image 3 It is an electronic device disclosed in the embodiment of this application, characterized in that: the device includes:

[0077] a memory storing executable program code;

[0078] a processor coupled to the memory;

[0079] The processor invokes the executable program code stored in the memory to execute the method described in the first embodiment.

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

This application provides a method and system for detecting fire smoke and spills based on video, which belongs to the field of video detection technology. The method includes: using a continuous background modeling module to dynamically model the background area, and then extracting Foreground target: the human-vehicle target filtering module is used to extract the suspected fire smoke or spill target from the foreground target, and then the recognition module performs fusion recognition on the suspected fire smoke or spill target, and outputs the detection and recognition result. The solution of the present application achieves a balance between detection and recognition efficiency and accuracy.

Description

technical field [0001] The present application relates to the technical field of video detection, in particular, to a method and system for detecting fire smoke and spills based on video. Background technique [0002] In order to protect the safety of people's lives and properties, we have built more than 200 million cameras. How to make full use of these cameras for automatic discovery of abnormal events is an important issue. Among them, a large number of cameras are used to monitor urban roads and highways, and in these scenarios, fire smoke and road spills are undoubtedly important events to be detected. Early detection and early treatment of fire smoke and road spills are important capabilities that a monitoring system should have. [0003] The applicant of the present application found the following relevant patent documents by searching the prior art: Patent Document 1 (CN101339602B) discloses a video fire smoke image recognition method based on the optical flow met...

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): G06K9/00G06K9/32G06K9/62G06N3/04G06N3/08G06T7/194G06T7/246G06T7/269
CPCG06N3/08G06T7/269G06T7/246G06T7/194G06T2207/10016G06T2207/20081G06T2207/20084G06V20/40G06V20/46G06V10/25G06N3/045G06F18/25
Inventor 林亦宁
Owner 上海闪马智能科技有限公司