A smoke recognition method and device, and electronic equipment
A recognition method and smoke technology, applied in character and pattern recognition, fire alarms, instruments, etc., can solve the problem of low smoke recognition accuracy, and achieve the effect of improving detection and recognition ability, accuracy, and recognition ability and
Active Publication Date: 2022-03-11
NANJING ENBO TECH
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Technical problem: In view of the problem that the accuracy of smoke recognition in the existing method is not high, the present invention provides a smoke recognition method and device, as well as an electronic device, so that the smoke in the video can be accurately recognized
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0045] The present invention will be further described below in conjunction with the embodiments and the accompanying drawings, wherein the "first", "second" and so on are used for description purposes, not for quantitative limitation or sequence limitation.
[0046] figure 1 It is a flowchart of an embodiment of the smoke recognition method proposed by the present invention, the method includes:
[0047] S100: Obtain a smoke video.
[0048] For example, smoke video can be acquired by an image acquisition device such as a video camera. Moreover, when the method is applied to smoke recognition in different scenes, the smoke video can be obtained with the help of the monitoring system of the corresponding scene. For example, when it is applied to the field of forest fire prevention, the smoke video can be obtained by the forest fire monitoring system.
[0049] S200: Calculate the frame difference of adjacent frame images of the smoke video to obtain a sequence of frame differe...
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
Login to View More Abstract
The invention discloses a smoke recognition method, device and electronic equipment, belonging to the fields of computer vision and smoke detection. The smoke recognition method includes obtaining smoke video; calculating the frame difference of adjacent frame images of the smoke video to obtain a frame difference image sequence; inputting the smoke video into a spatial branch to extract the spatial characteristics of the smoke to obtain the spatial texture information of the smoke; The sequence input time branch extracts the time features of the smoke, and obtains the smoke change information of adjacent frames; the space branch and the time branch perform parallel forward calculations, and during the forward calculation process, the spatial features and time features perform feature cross fusion; The feature information after the final cross fusion is compressed by downsampling, and the prediction result is output through the fully connected layer. The apparatus includes corresponding modules arranged correspondingly to the method. The electronic device is capable of performing the method. The invention can effectively improve the accuracy of smoke recognition.
Description
technical field [0001] The invention belongs to the field of computer vision and smoke detection, and in particular relates to a smoke recognition method and device, and electronic equipment. Background technique [0002] Fire is a serious threat to human life, health and property safety. A large amount of abnormal smoke is usually an early manifestation of fire. Therefore, smoke detection is also an effective method for large-scale fire monitoring. In addition, industrial waste gas emissions will also have adverse effects on human health and the ecological environment. With the development of deep learning technology, computational vision technology has made great progress. Deep learning technology has achieved great success in the fields of object detection, behavior recognition, super-resolution, etc. Fire and smoke detection through computer vision technology has gained a lot of attention in academia and industry. widespread attention in the world. Smoke detection tech...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G08B17/12G06V20/40G06V10/80G06K9/62
CPCG08B17/125G06V20/46G06F18/253
Inventor 曹毅超徐晓昂曾庆峰俞小鹏封晓强
Owner NANJING ENBO TECH