Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A detection method, a technology of human body detection, applied in the computer field, to achieve the effect of improving detection efficiency and increasing application scenarios
Active Publication Date: 2020-11-10
ZHEJIANG DAHUA TECH CO LTD
View PDF5 Cites 5 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005]
The embodiment of the present application provides a smoking detection method and device to solve the problem of detecting smoking behavior in indoor and outdoor oblique scenes without collecting clear frontal face images and cigarette images
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment approach 2
[0095] refer to image 3 As shown, a schematic flow diagram of the smoking detection process of Embodiment 2 is provided.
[0096] S301: Collect a plurality of continuous images in the same scene by using an image collector.
[0097] S302: Read an image X.
[0098] S303: Determine at least one complete human detection area from the image X according to a preset human detection model, and assign a corresponding user label to the at least one complete human detection area.
[0099] S304: According to the preset key point model of human body parts, determine key points of hand smoking from at least one complete human body detection area.
[0100] Specifically, using the key point model of human body parts, first determine the hand detection area from the complete human body detection area, and then determine the key smoking points of the hand from the hand detection area.
[0101] S305: Determine whether all the images have been read, if so, execute step 306; otherwise, return...
Embodiment approach 3
[0105] When the user is smoking, there will be a state of hand-face contact. For actions with hand-face contact, such as making a phone call or scratching the face, it is easy to be misidentified as a smoking action. In order to detect smoking-like actions and improve detection accuracy, refer to Figure 4 As shown, a schematic flow chart of smoking detection in Embodiment 3 is provided.
[0106] S401: Collect multiple continuous images in the same scene by using an image collector.
[0107] S402: Read an image X.
[0108] S403: Determine at least one complete human detection area and at least one partial human detection area from the image X according to a preset human detection model, and assign a corresponding user label to at least one complete human detection area.
[0109] S404: Input at least one part of the human body detection area into the preset smoking-like detection model to obtain the corresponding confidence level, and input the complete human body detection ar...
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 relates to the technical field of computers, and provides a smoking detection method and device which are used for detecting smoking behaviors of indoor and outdoor oblique scenes on thepremise that clear front face images and cigarette images are not collected.The method is based on a human body detection model and a human body part key point model. The method includes: determiningcorresponding human body part key points from a plurality of continuous images collected by the image collector in the same scene, and taking the human body part key points belonging to the same userlabel as a human body part key point set of the user; and if the human body part key point set conforms to a preset screening rule, determining the corresponding user as a smoking user. By positioning the human body detection area and the human body part key points, the human body part key point set meeting the preset screening rule is screened out, then the smoking user is determined, smoking detection can be carried out without collecting a clear front face image and a cigarette image, application scenes are increased, and the detection efficiency is improved.
Description
technical field [0001] The present application relates to the field of computer technology, and provides a smoking detection method and device. Background technique [0002] As we all know, smoking is harmful to health, especially in offices, chemical industry parks and other places, and it is easy to cause fires, explosions and other safety accidents. Therefore, it is necessary to detect smoking behavior in specific places and issue alarms in real time. [0003] At present, there are the following two methods for detecting smoking behavior: one is to use smoke alarm devices to detect indoor smoking behavior, which may be affected by the sensitivity of the smoke alarm device itself, and false detection or missed detection may occur; the other method is to use a vehicle-mounted The camera captures the face image, and uses the method of deep learning to detect the face information to determine whether the driver is smoking. The disadvantage of this method is that a clear front...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more