CN208172811U - A kind of intelligent vehicle collision prevention device based on monocular vision - Google Patents

Abstract

The utility model discloses an anti-collision device for an intelligent vehicle based on monocular vision. The device includes a camera unit, a processing unit, an alarm unit and a display unit. The camera unit transmits the collected video signal in front of the vehicle to the processing unit for processing The units are respectively connected to the alarm unit and the display unit; the processing unit is realized based on a video acquisition and processing board, and the video acquisition and processing board includes a video input decoding module, a DSP module, an external storage module, a PCI bus driver control module and a power management module. The input decoding module receives the analog signal sent by the camera unit and converts it into a digital signal and then sends it to the DSP module. The DSP module is connected with the display unit through the PCI interface for displaying the vehicle front obstacle distance obtained by processing; the DSP module and The alarm connection is used to control the alarm to send out an alarm when the distance is less than the safety threshold. The utility model has a simple structure, and the cost of identifying the obstacle distance in front of the vehicle through monocular recognition is low.

Description

An anti-collision device for intelligent vehicles based on monocular vision

technical field

The utility model relates to the field of automobile safety, in particular to an intelligent vehicle anti-collision device based on monocular vision.

Background technique

With the development of technology, automobiles have become a necessary means of transportation for people's daily life, and the number of urban automobiles has also increased greatly. The complex and changeable traffic environment has become more and more serious. Therefore, intelligent vehicle anti-collision technology that can reduce traffic accidents is particularly important.

At present, the common anti-collision system uses radar to measure the distance of vehicles with obstacles in front, but because the radar equipment is complex and expensive, the cost of the car is virtually increased, which is not conducive to popularization and use. However, due to the complexity of equipment installation and high requirements for installation accuracy, the binocular vision distance measurement of automobiles requires a large amount of image processing calculations, and it is difficult to guarantee real-time performance.

Utility model content

The purpose of the utility model is to overcome the deficiencies of the prior art and provide an intelligent vehicle anti-collision device based on monocular vision, which has a simple structure and is convenient to implement.

In order to achieve the above object, the technical solution adopted by the utility model is: an intelligent vehicle anti-collision device based on monocular vision, the device includes a camera unit, a processing unit, an alarm unit, and a display unit. The video signal is sent to the processing unit, and the processing unit is respectively connected to the alarm unit and the display unit; the processing unit is realized based on the video acquisition processing board, and the video acquisition processing board includes a video input decoding module, a DSP module, an external storage Module, PCI bus driver control module and power management module, the video input decoding module receives the analog signal sent by the camera unit and converts it into a digital signal and then sends it to the DSP module, and the DSP module is connected with the display unit through the PCI interface, It is used to display the processed obstacle distance in front of the vehicle, and the DSP module is connected to the alarm to control the alarm to send an alarm when the distance is less than the safety threshold.

The video acquisition and processing board is realized by using a video acquisition and processing board whose model is TMS320DM642.

The DSP module is connected with the car audio, and is used to control the car audio to send an alarm message when the distance of the obstacle in front obtained by the DSP module is less than the safety threshold.

The device also includes a braking sensor, which is used to detect the braking data of the vehicle, and is connected to the DSP module; the DSP module is connected to the electronic control braking system of the vehicle, and is used for detecting When it is less than the safety threshold and the brake sensor detects that the vehicle is not braked, the DSP module controls the vehicle's electronic brake system to brake.

The device also includes a speed sensor, the speed sensor is connected to the DSP module, and the safety distance threshold corresponding to the preset speed is preset in the external storage module connected to the DSP module.

The DSP module is respectively connected with an infrared sensor and a vehicle horn, and the infrared sensor is used to identify whether the obstacle in front is an animal or a pedestrian.

The utility model has the advantages of: simple structure, convenient implementation, low cost of identifying obstacles in front of the vehicle through monocular recognition, and easy promotion; timely alarm, preventing collision accidents caused by lack of experience and distraction; when the vehicle does not brake When the vehicle is running, it will automatically brake to avoid the hazards caused by high-speed collisions.

Description of drawings

The following is a brief description of the contents expressed in the accompanying drawings of the utility model specification and the marks in the figures:

Fig. 1 is a structural principle diagram of the utility model;

Fig. 2 is a schematic diagram of an embodiment of the utility model realized by using a TMS320DM642 video acquisition and processing board.

Detailed ways

The specific implementation of the present utility model will be described in further detail below through the description of the best embodiment with reference to the accompanying drawings.

The anti-collision device for an intelligent vehicle based on monocular vision of the utility model includes: a camera unit, a processing unit, an alarm unit, and a display unit. camera unit. The camera unit adopts a single CCD camera fixed on the roof, and the CCD camera transmits the collected analog video signal to the processing unit. The processing unit adopts a video acquisition and processing board based on TMS320DM642. The main hardware function modules of the board include video input decoding module, core DM642 DSP module, external storage module, PCI bus driver control module and power management module, etc. The video input decoding module receives the analog signal sent by the camera unit and converts it into a digital signal and then sends it to the DSP module. The DSP module is connected to the display unit through the PCI interface to display the processed obstacle distance in front of the vehicle. The DSP module communicates with the alarm It is used to control the alarm to send out an alarm when the distance is less than the safety threshold. The basic working principle is that the video decoder converts the received analog video signal into a digital video signal, and sends it to DM642 for image processing operations, including background difference method and monocular ranging algorithm, and DM642 then transmits the processed video data to the display through the PCI interface , constitute a digital monitoring system, and at the same time, DM642 transmits the processing results to the alarm with digital signals, and can effectively give the driver early warning information, avoiding the risk of vehicle collision and improving the traffic environment. The recognition algorithm run by the DSP can be realized by using the algorithm in the prior art, and the applicant does not make further explanation here.

In a preferred technical solution, the DSP module is connected with the car audio, and is used to control the car audio to send out an alarm message when the DSP module processes and obtains that the distance of the obstacle ahead is less than the safety threshold. The car audio alarm can effectively remind the driver while reducing the cost of peripherals.

In another preferred embodiment, the braking data of the vehicle is detected by the braking sensor, which is connected with the DSP module; When the brake sensor detects that the vehicle is not braked, the DSP module controls the vehicle's electronic brake system to brake. When the detected distance is less than the safety distance, when the brake needs to be controlled, and the driver does not brake, the DSP module sends a control signal to the vehicle's brake controller to control the vehicle to automatically brake, reducing the risk of vehicle collision. Immediate collision after deceleration will not cause major casualties, ensuring the safety of personnel.

The safety distance is also different according to the vehicle speed. The safety distance thresholds corresponding to different vehicle speeds are pre-stored in the external storage module SDRAM. When the corresponding safety distance threshold is obtained according to the vehicle speed, then it is judged whether it is less than the safety threshold. Alarm and other operations are required.

In order to further reduce the possibility of collision, the infrared sensor is used to detect whether the obstacle in front is an animal or a person, and if so, the car horn emits a sound to remind pedestrians or animals to avoid the vehicle. When an obstacle is detected in front, at this time, the temperature of the person or animal is detected by infrared to determine whether it is a person or an animal. If so, the DSP module controls the car horn to make a sound to remind pedestrians or drive animals away, further avoiding the possibility of collision and improving driving safety.

Apparently, the specific implementation of the utility model is not limited by the above methods, as long as various insubstantial improvements are made by adopting the method concept and technical solutions of the present invention, they all fall within the protection scope of the present invention.

Claims (6)

1. A kind of intelligent vehicle anti-collision device based on monocular vision, it is characterized in that: described device comprises camera unit, processing unit, alarm unit, display unit, and camera unit transmits the video signal of the front of the vehicle that collects to processing unit, The processing unit is connected to the alarm unit and the display unit respectively; the processing unit is realized based on a video acquisition processing board, and the video acquisition processing board includes a video input decoding module, a DSP module, an external storage module, a PCI bus driver control module and The power management module, the video input decoding module receives the analog signal sent by the camera unit and converts it into a digital signal and then sends it to the DSP module. The DSP module is connected to the display unit through the PCI interface for displaying the processed front of the vehicle. Obstacle distance, the DSP module is connected with the alarm, and is used to control the alarm to send an alarm when the distance is less than the safety threshold. 2 . The anti-collision device for an intelligent vehicle based on monocular vision as claimed in claim 1 , wherein the video acquisition and processing board is implemented by a video acquisition and processing board whose model is TMS320DM642. 3. A kind of intelligent vehicle anti-collision device based on monocular vision as claimed in claim 1, is characterized in that: described DSP module is connected with vehicle audio system, is used for when DSP module processing obtains the front obstacle distance less than safety threshold Control the car audio to send an alarm message. 4. A kind of intelligent vehicle anti-collision device based on monocular vision as claimed in claim 1, is characterized in that: described device also comprises braking sensor, and described braking sensor is used for detecting the braking data of vehicle, and its Connected with the DSP module; the DSP module is connected with the electronic control braking system of the vehicle, and is used to control the electronic control braking of the vehicle by the DSP module when the distance of the obstacle in front is less than the safety threshold and the brake sensor detects that the vehicle is not braking The system brakes. 5. a kind of intelligent vehicle anti-collision device based on monocular vision as claimed in claim 1, is characterized in that: described device also comprises speed sensor, and described speed sensor is connected with DSP module, and the connected with described DSP module The safety distance threshold corresponding to the preset speed in the external storage module. 6. A kind of intelligent vehicle anti-collision device based on monocular vision as claimed in claim 1, is characterized in that: described DSP module is connected infrared sensor, vehicle-mounted horn respectively, and described infrared sensor is used for identifying whether obstacle ahead is animals or pedestrians.