Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Cigarette automatic detection method based on deep learning in monitoring scene

A deep learning and automatic detection technology, applied in the field of deep learning and computer vision, to achieve the effects of easy detection, improved contrast and details, and improved dynamic range

Active Publication Date: 2019-10-29
FUZHOU UNIVERSITY
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Not only does it require additional expenses for the installation of related equipment, but it also cannot give certain warnings after the smoking event occurs

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
  • Cigarette automatic detection method based on deep learning in monitoring scene
  • Cigarette automatic detection method based on deep learning in monitoring scene
  • Cigarette automatic detection method based on deep learning in monitoring scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0057] It should be pointed out that the following detailed description is exemplary and intended to provide further explanation to the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0058] It should be noted that the terminology used here is only for describing specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and / or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and / or combinatio...

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 relates to a cigarette automatic detection method based on deep learning in a monitoring scene, and the method comprises the steps: firstly carrying out the overturning, zooming and smoothing of a cigarette data set photographed and downloaded from a network, obtaining a bigger data set, training the data set based on a YOLOv3 deep learning network, and forming a template library; performing corresponding image enhancement processing on the to-be-detected image or video frame by using an image enhancement method; carrying out image segmentation on the large-size image, cigarettesor people with cigarettes in the image are separated out, and the time needed by detection is shortened; then pre-generating prediction boxes on the image to be detected, and comparing each prediction box with a pre-trained template library; and finally, selecting a prediction box higher than a preset threshold value from the detection confidence coefficients of all the prediction boxes, and determining the prediction box as a target object. After the whole image of the current frame is scanned, all detected targets are marked and displayed on the image, and cigarette detection is completed.The method can effectively improve the detection accuracy and shorten the detection time.

Description

technical field [0001] The invention relates to the fields of deep learning and computer vision, in particular to an automatic cigarette detection method based on deep learning in a monitoring scene. Background technique [0002] With the continuous improvement of modern people's living standards, concepts continue to improve. People pay more and more attention to the dangers of smoking. Recently, accidents caused by smoking have been well-known, such as: smoking on the high-speed rail caused the suspension of the high-speed rail, causing hundreds of passengers to be stranded; smoking at the gas station caused the gas station to catch fire, resulting in casualties and property losses; more What's more, forest fires were caused by smoking, and the great rivers and mountains of the motherland were destroyed. Therefore, smoking is strictly prohibited on high-speed railways and EMUs. In recent years, the punishment has been increased to the legal level; in public areas such as...

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): G06T7/00G06T7/10G06T7/136G06T5/00
CPCG06T7/0004G06T7/10G06T7/136G06T2207/20081G06T2207/10016G06T5/70
Inventor 柯逍黄旭
Owner FUZHOU UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products