PR058 » Intelligent traffic light control system based on image recognition and sensor.
The system mainly USES the camera to collect the image of the intersection, and then detects the traffic and pedestrian situation of the road junction with ultrasonic, infrared and other sensors. The above data is processed by FPGA, and the current traffic light scheme is determined. To achieve the efficiency of vehicles through intersections. It can slow the contradiction between the rapid growth of vehicles and the slow expansion of urban roads, and ensure the safety while reducing the congestion and waiting time for car owners. At the same time, it can achieve the goal of energy conservation and emission reduction, and indirectly contribute to environmental protection.
Because the system is always data processing and control, and not the sequential system, it can give full play to the advantages of FPGA high-speed processing and extremely low delay. Meanwhile, the stability of FPGA also provides an important guarantee for the safe operation of the system.
It is proposed to build an experimental model to test the various functions of the system, and to promote it systematically. Apply for a practical patent.
Car number in the current world constantly under the background of the era of rapid growth, how to improve the efficiency of vehicle traffic in the city road became the various countries in major cities have headaches, widening the existing roads and build the new road is the most effective solution, but the time is very long these solutions and the need to invest a lot of manpower material resources and financial resources, and such a huge project will produce certain effect to the current traffic. Under such a problem, what we are thinking about is how to use current road resources more fully and efficiently. Of course, it's a guarantee of road safety. Intelligent control of traffic lights is a good direction. According to the observation, the traffic light at the intersection of the city is the fixed control plan. The traffic efficiency is very low when there is no one at the intersection. So we plan to design a by image recognition and other sensor integrated intelligent traffic light controller, to choose appropriate for the current intersection traffic light control scheme, to the highest utilization rate of the road.
This design can be applied to any intersections in order to reach the purpose of improve the overall traffic rate, reduce the financial burden on city road, is all the traffic administrative department of the application of the design, low cost and easy application, a camera can also play the role of real-time monitoring road conditions, and so on...
The information of the intersection is collected by the camera, ultrasonic and infrared sensor and transmitted to the FPGA for processing. The data of the camera will be stored in the SDRAM to be called in the first place. After comprehensive processing and judgment of the above road information, the system will be implemented according to the pre-given traffic light scheme.
Always take the current picture of the road and send its data to SDRAM by the way of SPI.
By sending an ultrasonic signal and receiving a signal from the reflected signal to obtain the presence of an object on the current path.
The sending port and the receiving port are separated by the two sides of the road, and the infrared signal is checked to determine whether there is an object in the current road.
The image data captured by the temporary camera so that the FPGA can be called at any time during processing.
Display current road conditions and traffic light schemes through displays and other devices.
(1) Camera: collect image information.
(2) Ultrasonic wave: to collect sound waves at intersections.
(3) Infrared sensor: collect the infrared information of the intersection.
(1) Traffic light model: show current traffic lights.
(2) VGA display: display road images.
Model system:Using design as a set of intersection traffic light intelligent control model, by using the model to simulate the different road conditions degree of intelligent detection system and constantly optimized, finally get high efficiency traffic light control scheme.
Advantages of FPGA:Because the system is always data processing and control, and not the sequential system, it can give full play to the advantages of FPGA high-speed processing and extremely low delay. Meanwhile, the stability of FPGA also provides an important guarantee for the safe operation of the system.
We intend to design an intelligent traffic light controller that recognizes and analyzes other sensor signals through FPGA and analyzes the signals. It is able to select the appropriate traffic light control scheme according to the current intersection conditions and guarantee the safety of intersections while vehicles driving fast, which aims at achieving the highest efficiency of the road and reduce the burden on city roads.
Making a set of traffic light models which is capable of real-time demonstration of traffic lights at road intersections and adding a series of signal collection devices such as cameras, infrared sensors, ultrasonic sensors to the model. At the same time, the FPGA control board will process the collected signals and control the traffic intelligently.
The project is planned to be expanded as follows:
1. A set of simulated real-time traffic model, including such as trees and other real things
2. A highly simulated traffic light model
3. Design PCB circuit boards for cameras and other signal collection devices to ensure high read system integration
4. A DE10-nano FPGA development board for image recognition, signal processing, and controlment
5. A smart car which can be self-tracking and can automatically determine whether to proceed according to the intersection of traffic lights
Hardware part:
Controller and adapter: use the 80 extension pins of the DE10-nano to connect and communicate with the four traffic lights, as well as the cameras and the ultrasonic modules on the traffic lights, as shown in the following diagram and to power the traffic lights.
The FPC interface is used in the transfer board to reduce the volume and ensure the integrity of the high-speed signal. At the same time, the installed LED lights and buzzer can act as a signal indicating device. The CD4511 integrated chip is used as the decoder of digital tube, which reduces the occupation and control difficulty of pin resources.
Traffic lights: the red and green light is made directly by PCB, which uses high luminance light emitting diode as the light source of the red and green light. It also reduces the complexity of the design in the case of easy identification. The design of the camera socket and the ultrasonic module socket can provide the connection line between the camera and the ultrasonic to the adapter board, thus reducing the complexity of the connection. The FPC interface is directly connected with the switch board.
Trolley controller: Using the integrated MCU STM32 as the main controller of the car, the running frequency of the STM32F1 series is up to 72MHz, and all solutions can be completed within the 0.02s of the intelligent vehicle control cycle to ensure the stable operation and accurate identification of the vehicle. The special control board is designed with multiple signal collection module and dual motor drive, which is in line with the design requirements.
OV2640 camera：The OV2640 is a 1/4-inch CMOS UXGA (1632*1232) image sensor manufactured by OV (OmniVision) company. The sensor's small size and low operating voltage provide all the features of a single UXGA camera and image processor. Through the SCCB bus control, various 8/10-bit image data of various resolutions such as full frame, sub-sampling, scaling, and window taking can be output. The product's UXGA image can be up to 15 frames per second (SVGA up to 30 frames and CIF up to 60 frames). Users can fully control image quality, data format, and transmission methods. All image processing functions including gamma curve, white balance, contrast, color, etc. can be programmed via the SCCB interface. OmmiVision’s image sensor apply unique sensor technology by reducing and eliminating optical or electronic defects such as fixed pattern noise, smearing, floating, etc., to improve image quality, get a clear and stable color image. The internal structure of the resulting image is shown in the following figure:
HC-SR04 Ultrasonic Module：Ultrasonic module using standard IIC communication protocol. Ultrasonic pulse echo transit time method is used to realize the detection of roadway objects. The current approaching distance of pedestrians and vehicles can be judged by it.
The schematic diagram is as follows:
Comprehensive scenario: Using the scene diagram built by various model devices:
Software part:
The software part is divided into two parts. The first part is the intelligent traffic light control part written in Verilog language. The second part is the intelligent car control code written in C .
1. The control part of the traffic light：
As shown above, each sub module of the design system is written in Verilog language. Finally, the principle diagram of the hardware electrical connection is created to connect the sub modules to the overall traffic light control system. The sub modules include clock frequency divider, decoder, image recognition module, ultrasonic distance measuring module, timing red and green light control module and intelligent control module.
Intelligent vehicle control part: Using the infrared photoelectric tube and color sensor to collect the information of the road and the traffic light, then the current state and situation are analyzed with the corresponding algorithm, and the speed of the wheel and the steering direction are controlled by the incremental PID control.