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

Intelligent traffic light system based on deep learning and method for controlling traffic light

A deep learning, traffic light technology, applied in the field of traffic lights, can solve the problems of affecting the traffic efficiency, the traffic light time is too long, the traffic light time is short, etc., to achieve the effect of solving traffic congestion

Inactive Publication Date: 2017-09-05
SHANGHAI INTEGRATED CIRCUIT RES & DEV CENT +1
View PDF8 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The passing time of green lights in this fixed cycle and fixed direction will face a problem: it is impossible to change the time of traffic lights according to the traffic flow. It often occurs in the peak congestion stage. Some roads have little traffic but the traffic lights take too long. Or the traffic light time is too short when there is too much traffic
In the prior art, the regulation of traffic lights through PLC fixed programs will affect the actual traffic efficiency, and the actual traffic conditions on the road surface cannot be well regulated.

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
  • Intelligent traffic light system based on deep learning and method for controlling traffic light
  • Intelligent traffic light system based on deep learning and method for controlling traffic light
  • Intelligent traffic light system based on deep learning and method for controlling traffic light

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] figure 2 It is a structural frame diagram of the intelligent traffic light system based on deep learning in Embodiment 1. image 3 It is a schematic diagram of an intersection where an intelligent traffic light system is installed in Embodiment 1.

[0048] Such as figure 2 As shown, an intelligent traffic light system based on deep learning includes a data acquisition and processing module, a deep learning module and a traffic light center control module. Among them, the data acquisition and processing module includes a data acquisition module, an intelligent identification module and a data monitoring module, and one end of the intelligent identification module is connected to the data acquisition module, and the other end is connected to the data monitoring module, and the red light corresponds to the image collected by the data acquisition module on the lane It is transmitted to the corresponding intelligent identification module to identify the vehicle type. The...

Embodiment 2

[0069] Figure 4 It is a structural frame diagram of the intelligent traffic light system based on deep learning in Embodiment 2. Figure 5 It is a schematic diagram of an intersection where an intelligent traffic light system is installed in Embodiment 2.

[0070] Such as Figure 4As shown, an intelligent traffic light system based on deep learning includes a data collection and processing module, a deep learning module and a traffic light center control module, and the deep learning module is connected to the data collection and processing module at one end and the traffic light center control module at the other end. Among them, the data acquisition and processing module includes a data acquisition module, an intelligent identification module and a data monitoring module. The data acquisition module is connected to the intelligent identification module and the data monitoring module at the same time. The identification module identifies the vehicle type. At the same time,...

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 discloses an intelligent traffic light system based on deep learning and a method for controlling a traffic light. The intelligent traffic light system comprises a data collecting and processing module, a deep learning module and a traffic light central controlling module, wherein the data collecting and processing module is used for collecting images of an intersection corresponding to the traffic light in real time, and identifying vehicle model information, a traffic volume, the vehicle queue length and the corresponding passing time of vehicles; the deep learning module comprises a neural network which can simulate a human brain for analysis and learning, and a control model, and the control model inputs the vehicle model information, the traffic volume, the vehicle queue length and the corresponding passing time of the vehicles into the neural network for autonomous deep learning and forming the control model; the traffic light central controlling module is used for controlling the traffic light. According to the intelligent traffic light system based on deep learning, the control model which is formed through autonomous deep learning can calculate and control the duration of a green light after the next change of the traffic light according to the vehicle queue length at the intersection and the vehicle model information, and efficiently solve the problem of heavy traffic.

Description

technical field [0001] The invention relates to the field of traffic lights, in particular to an intelligent traffic light system based on deep learning and a method for controlling traffic lights. Background technique [0002] Current traffic lights adopt PLC control program to control the time of traffic lights, that is, the PLC control program of traffic lights is set in advance according to the situation of the crossing. For example, in the period of a crossroads, according to the north-south direction, the red light is on for 25 seconds, turn to the green light for 25 seconds, and then flash 3 times according to the rule of once every second, then turn the yellow light on for 2 seconds, and the east-west direction green light is on for 20 seconds seconds, then flash 3 times, turn to yellow light for 2 seconds, then red light for 30 seconds, complete a cycle, and so on. [0003] The passing time of green lights in this fixed cycle and fixed direction will face a problem...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/08G08G1/01
CPCG08G1/08G08G1/0145
Inventor 李赟晟王勇
Owner SHANGHAI INTEGRATED CIRCUIT RES & DEV CENT
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