Method and system for counting the number of people in straight elevators based on deep learning
A technology of people counting and deep learning, applied in the field of computer vision, can solve the problems of lack of universality and preset value deviation, and achieve the effect of good universality and improved detection.
Active Publication Date: 2021-06-04
ZHEJIANG NEW ZAILING TECH CO LTD
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
For example, the preset radius circle covers the candidate area, the environment is different in different elevator scenarios, or the camera position deviation caused by human factors may cause the deviation of the preset value, so it is not universal
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
[0024] Next, the technical solutions in the embodiments of the present invention will be described in contemplation in the embodiment of the present invention, and it is clear that the described embodiments are intended to be in an embodiment of the invention, not all of the embodiments of the invention. Based on the embodiments of the present invention, there are all other embodiments obtained without making creative labor without making creative labor premises.
[0025] Refer figure 1 The steps of the steps of depth learning-based straightforward statistical methods are shown in the embodiment of the present invention, including the following steps:
[0026] S1, the straightforward monitoring camera judges that someone has an unmanned algorithm through the camera, and the switch gate algorithm determines that the door is closed, and the car starts analysis request when the car is running, triggers an image and calls the direct target detection algorithm;
[0027] S2, after recei...
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 method and system for counting the number of people in a straight elevator based on deep learning, which includes the following steps: the monitoring camera of the straight elevator judges that there is a person through the algorithm of the presence or absence of the camera, and the algorithm of opening and closing the door judges that the door of the straight elevator is closed, and the car is in the running state When the analysis request is started, an image is triggered and the elevator pedestrian detection algorithm is called for target detection; after the analysis request is received, an image is taken from the main stream according to the time node of the triggered image, and the YOLOv3 algorithm is called for analysis to obtain The final detection frame: get the specific number of people in the elevator through the detection frame, write the number into the database, and report it to the ladder platform at the same time.
Description
Technical field [0001] The present invention belongs to the field of computer visual technology, and specifically, a statistical method and system based on deep learning. Background technique [0002] During the use of the ladder, avoid some fault or human factors caused by the phenomenon caused by human factors. The current number of people can be detected by detecting the number of people, and notify the property or cloud ladder platform, and rescuers can save timely. Stamped with gravity sensors, there is a certain load range, which exceeds this range to cause the device to fail, from safety, by detecting the number of linear ride can be reasonably controlled. Load range. The statistical single line is a day flow, for the residential scene, the number of statistical cells is used for big data analysis, and there is a certain warning role in security management; for the school, the hospital is a scene, statistically analyzes flow data, You can improve operational efficiency by ...
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): G06K9/00G06K9/32G06N3/04G06N3/08
Inventor 陈国特王超施行王伟蔡巍伟吴磊磊
Owner ZHEJIANG NEW ZAILING TECH CO LTD