Street lamp intelligent detection and night state judgment method

A state judgment and intelligent detection technology, which is applied in the interpretation of photos, image data processing, instruments, etc., can solve the problems of consuming a lot of manpower and material resources, and a large number of street lights

Pending Publication Date: 2019-08-16
NANTONG UNIVERSITY
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The number of street lights in the city is extremely large, and it take

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
  • Street lamp intelligent detection and night state judgment method
  • Street lamp intelligent detection and night state judgment method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0030] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0031] The present invention provides a method for street lamp intelligent detection and night state judgment, including the following steps:

[0032] Step 1. Collect street lamp pictures in the daytime environment, and manually mark the position coordinates of the street lamps in the picture;

[0033] Step 2. Use deep convolutional neural network to train street lamp detection model, the specific steps are:

[0034] 2-1. Construct the basic network layer, which is composed of 6 layers of convolutional layer, pooling layer and ReLU activation function, send the image to the basic network, and get the output o1;

[0035] 2-2. Construct a region generation network to distinguish between foreground and background. Apply a sliding window on the out...

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 provides a street lamp intelligent detection and night state judgment method which comprises the following steps: step 1, collecting street lamp pictures in a daytime environment, and manually marking position coordinates of street lamps in the pictures; step 2, training a street lamp detection model by adopting a deep convolutional neural network; step 3, initializing the system inthe daytime environment, and initializing the position and angle relationship of the street lamp in the camera by using the street lamp detection model obtained in the step 2; step 4, judging the state of the street lamp at night, and obtaining a street lamp position interval according to the camera and the street lamp position model obtained in the step 3; step 5, judging the light and shade state of the street lamp according to the street lamp position obtained in the step 4; and step 6, if the street lamp is continuously found to be in a non-bright state, sending alarm information to streetlamp managers. According to the invention, the light and shade state of the street lamp in the night environment can be obtained without transforming the existing street lamp and the road surface environment and transmitting the image of the camera installed in the road administration department to the background for analysis.

Description

technical field [0001] The invention relates to the technical field of intelligent detection and judgment, in particular to a method for intelligent detection and judgment of street lights at night. Background technique [0002] The road administration department needs to know the situation of the street lamps existing in the urban roads, and it is necessary to be able to know in time which street lamps are out of order. The number of urban street lights is extremely large, and relying on manual inspections requires a lot of manpower and material resources. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a method for intelligent detection of street lamps and judgment of night state, which does not need to modify the existing street lamps, and does not require any modification to the road surface environment, and transmits the image of the camera installed by the road administration department to the background fo...

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): G06K9/00G06T7/70G01C11/04
CPCG06T7/70G01C11/04G06T2207/30232G06V20/52
Inventor 胡彬唐庆阳程实
Owner NANTONG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products