Since the introduction of MARR visual computing theory, machine vision technology has developed rapidly and is one of the fastest growing technologies in the field of intelligent driving. It is also one of the main research directions in the field of intelligent driving.
This article refers to the address: http://
Machine vision technology in smart driving applications
In the application of machine vision technology in intelligent driving, machine vision technology must have three characteristics of real-time, robustness and practicality [7]. Real-time requirements require that the data processing of the machine vision system must be synchronized with the high-speed driving of the vehicle; robustness requires intelligent vehicles to different road environments such as highways, city roads, ordinary roads, etc., complex road environments such as road width , color, texture, curve, slope, potholes, obstacles and traffic flow, all kinds of weather, sunny, rain, snow, fog, etc. have good adaptability; practicality means that intelligent vehicles can be accepted by ordinary users [ 7].
At present, machine vision is mainly used for path identification and tracking [7]. Compared with other sensors, machine vision has the advantages of rich information detection, contactless measurement and three-dimensional modeling of road environment, but the data processing is extremely large, and there are system real-time and stability problems. Computer hardware, research new algorithms to solve. With the rapid development of computer technology and image processing technology, the three-dimensional reconstruction of the road environment provides powerful information for high-speed intelligent driving of vehicles, and it has practical feasibility in the near future.
The basic principle of road recognition for machine vision is that the CCD image gray value and the image texture and optical flow of the road pavement environment (white road signs, edges, road color, potholes, obstacles, etc.) are different. According to this difference, the required path image information such as azimuth deviation, lateral deviation, position of the vehicle in the road, and the like can be obtained after image processing. Combining this information with the vehicle's dynamic equations can form a mathematical model of the vehicle control system.
3. Structural design of intelligent driving system
(1) Machine vision system
The hardware structure of the machine vision system: mainly composed of two CCD cameras with the same parameters, models and performances, two identical video capture cards and video processing software on the computer. We use the photos taken by the left and right CCD cameras to obtain the relevant depth information by image processing. It is necessary to ensure that the left and right CCD camera signals are synchronized. Otherwise, the ingested pictures do not correspond, and the relevant depth information cannot be correctly extracted. Therefore, our left and right CCD cameras are synchronized cameras, which are to extract the frame synchronization signal from the frame synchronization circuit of the left camera to the frame synchronization circuit of the right CCD camera, so that the left and right images are always synchronized. .
The machine vision processing software system is mainly responsible for obstacle detection and identification, traffic signal detection and recognition, traffic pattern recognition and detection, road edge recognition detection, curve arc recognition detection, forward vehicle distance speed detection and road surface pit slope identification detection. The extraction is based on the three-dimensional reconstruction of the road environment based on the information data. The road vision information processed by the machine vision processing software system is integrated with the multi-sensor information of the auxiliary system, combined with the vehicle dynamics model (many scientists have studied the application of fuzzy control technology and neural network technology in vehicle dynamics models) And the vehicle driving state parameters, the vehicle behavior decision-making scheduling system makes a reasonable decision scheduling, and then the path planning system generates reasonable path planning and vehicle control commands to control the car.
Highway edge detection and detection is related to whether the car can correctly identify the road, especially the low-grade roads lacking traffic patterns. Our machine vision detects the edge information of the road and the width information of the road. The edge detection of the road, the binarization of the image taken by the CCD, the road edge can be extracted; the road width information detection, the road image taken by the left and right CCD is used for stereo matching, and the depth information inside is extracted, according to machine vision The theory calculates the width of the road. According to the data of other sensors, determine the position of the car in the road and the driving state parameters of the car, make a reasonable path planning, optimize the position of the car in the road, and do the path tracking, so as not to deviate from the road surface during driving.
Identification and detection of traffic patterns, road signs, and traffic signals. Traffic patterns include common zebra crossings, lane lines, arrows, and more. These traffic patterns are fixed in color (such as zebra crossings are white) and fixed in shape, so their identification can be quickly identified by using simple image processing and then comparing our pre-established traffic pattern models. Traffic identification is relatively cumbersome. Some traffic signs have text on them. We not only need to use image processing technology to extract these text information, but also need to analyze the traffic information contained in these words. Traffic signals include traffic lights and traffic police semaphores. They all have a fixed operating mode, which can be pre-modeled and then combined with other sensors based on image processing for detection and identification.
Detection and identification of the distance and speed of cars and obstacles ahead. It is very important to safely and accurately identify and detect the front car and obstacles for intelligent driving of the car. It is necessary to recognize not only the cars and obstacles in front, but also the speed of movement, the direction of movement and the distance from the vehicle. It is necessary to predict the distance from each other and the speed and direction of movement based on several consecutive measurements. Their possible trajectories provide reliable data for overtaking, decelerating, avoiding obstacles and reducing risk of danger. Using machine vision technology, a three-dimensional motion detection method based on the corresponding point estimation of the imaging model and a three-dimensional motion detection method based on the estimation of the optical flow can be used. Model method and optical flow method have many mature algorithms to choose from, which is beneficial to the realization of system programs.
Camera calibration in machine vision systems: The purpose of camera calibration is to determine the internal and external attribute parameters of the camera and to establish a spatial imaging model to determine the corresponding relationship between the object point in the spatial coordinate system and its image point on the image. The calibration of the camera is divided into camera internal parameter calibration and external parameter calibration. The internal parameters determine the geometric and optical characteristics of the camera, which do not change with the movement of the camera. The external parameters determine the three-dimensional position and orientation of the camera image plane relative to the objective world coordinate system. After the camera moves, it needs to be recalibrated. In this paper, the camera moves with the car, but the parameters we need are internal parameters, just need to pre-calibrate the internal parameters of the camera.
(2) Main control system
The core of the entire intelligent driving system is the main control system, which is responsible for information collection, identification, and processing of various sensors. Finally, based on the processed information, vehicle behavior decision scheduling, planning paths and generating vehicle control commands. The design idea of ​​the whole intelligent driving system is also based on simulated artificial driving. The main control system is the brain of the car, and the machine vision system is like the eyes of the human. In the event of a system crash or an unstable operation of the control software in the main control system, a major traffic accident resulting in a car crash will result. The main control system computer has a bad working environment, the car vibrates at high speed, and the temperature near the car engine is high. In order to ensure the safe and stable operation of the main control system, the main control system computer should use high performance and high stability. Industrial computer.
(3) Auxiliary ranging positioning system
It mainly includes car GPS positioning system, ranging radar, electronic map and so on. With the development of traffic information, GIS-based electronic maps have begun to be used in daily car driving. GIS-based electronic maps include a wide range of geographic location information that can be used to set macroscopic paths for car driving in large directions. Then, through the car GPS global positioning system to determine the geographical location information of the car's current location point, compare it with the geographical location information of the point on the electronic map, you can know where the car is now in the macro path we set, can Prevent the car from taking the wrong intersection when driving automatically, taking the wrong direction and deviating from the preset macro path. The integrated use of GIS-based electronic maps and on-board GPS global positioning systems ensures that cars can be driven autonomously in a macroscopic manner according to our pre-defined macro path without deviating from our pre-defined path.
A siren is a loud noise-making device. Civil defense sirens are mounted in fixed locations and used to warn of natural disasters or attacks. Sirens are used on emergency service vehicles such as ambulances, police cars, and fire trucks. There are two general types: pneumatic and electronic.
Many fire sirens (used for calling the volunteer fire fighters) serve double duty as tornado or civil defense sirens, alerting an entire community of impending danger. Most fire
sirens are either mounted on the roof of a fire station or on a pole
next to the fire station. Fire sirens can also be mounted on or near
government buildings, on tall structures such as water towers,
as well as in systems where several sirens are distributed around a
town for better sound coverage. Most fire sirens are single tone and
mechanically driven by electric motors with a rotor attached to the
shaft. Some newer sirens are electronically driven speakers.
Fire sirens are often called "fire whistles", "fire alarms", or
"fire horns". Although there is no standard signaling of fire sirens,
some utilize codes to inform firefighters of the location of the fire.
Civil defense sirens also used as fire sirens often can produce an
alternating "hi-lo" signal (similar to emergency vehicles in many
European countries) as the fire signal, or a slow wail (typically 3x) as
to not confuse the public with the standard civil defense signals of
alert (steady tone) and attack (fast wavering tone). Fire sirens are
often tested once a day at noon and are also called "noon sirens" or
"noon whistles".
The first emergency vehicles relied on a bell. Then in the 70s,
they switched to a duotone airhorn. Then in the 80s, that was overtaken
by an electronic wail.
Piezo Alarm,Siren And Alarm,Piezo Buzzer Siren,Piezo Buzzer Alarm Siren
Jiangsu Huawha Electronices Co.,Ltd , https://www.hnbuzzer.com