CN215705988U

CN215705988U - Large vehicle blind area monitoring devices based on video image

Info

Publication number: CN215705988U
Application number: CN202121603576.9U
Authority: CN
Inventors: 闫方超; 刘畅; 杜汉宇
Original assignee: Tianjin Bool Technology Co ltd
Current assignee: Tianjin Bool Technology Co ltd
Priority date: 2021-07-14
Filing date: 2021-07-14
Publication date: 2022-02-01
Anticipated expiration: 2031-07-14

Abstract

The utility model provides a large vehicle blind area monitoring device based on video images, which comprises: the system comprises an algorithm controller, an image acquisition unit, a vehicle control unit and an alarm unit, wherein the algorithm controller is used for prefabricating a visual algorithm; the image acquisition unit comprises cameras fixed on two sides of the vehicle body and is electrically connected with the algorithm controller; the whole vehicle controller is electrically connected with the algorithm controller through a control bus; the alarm unit is electrically connected with the algorithm controller. The utility model provides a large vehicle blind area monitoring devices based on video image utilizes the camera to gather the visual image of vehicle rear side to monitor moving object, utilize vehicle control unit to acquire the turn to information of vehicle, thereby judge the danger that exists through the motion information that combines moving object's motion information and the turn to information of vehicle, overcome that current monitoring mode measuring range is limited and be difficult to be applied to moving vehicle not enough.

Description

Large vehicle blind area monitoring devices based on video image

Technical Field

The utility model relates to the technical field of vehicle blind area monitoring, in particular to a large vehicle blind area monitoring device based on video images.

Background

The automobile blind area is an area where a driver is located at a normal driver seat and the sight line of the driver is shielded by an automobile body and cannot be directly observed. For large vehicles, because the vehicles are generally longer and the drivers seat is higher, the blind area is longer than that of a family car, especially the two sides and the rear part of the vehicle; when the vehicle turns or backs, the blind areas can cause great potential safety hazards to the pedestrian and the vehicle.

The existing large-scale vehicle mainly adopts a combination method of an ultrasonic radar and vehicle all-round equipment to monitor the blind area. But the measuring range of the ultrasonic radar is smaller, but the combined mode increases the monitoring cost; the vehicle all-round equipment is mostly used for low-speed states such as vehicle parking, and is difficult to realize timely prediction for running vehicles, and a driver needs to observe road conditions in real time while using the vehicle all-round equipment, so that the use limitation exists.

SUMMERY OF THE UTILITY MODEL

The utility model aims to solve the technical problem of overcoming the defects in the prior art and provides a large vehicle blind area monitoring device based on video images.

The utility model is realized by the following technical scheme: a large vehicle blind area monitoring device based on video images comprises:

the algorithm controller is used for prefabricating a visual algorithm;

the image acquisition unit comprises cameras fixed on two sides of the vehicle body and is electrically connected with the algorithm controller;

the whole vehicle controller is electrically connected with the algorithm controller through a control bus;

and the alarm unit is electrically connected with the algorithm controller.

Furthermore, rear-view mirrors are arranged on two sides of the vehicle, and the cameras are fixed at the bottoms of the rear-view mirrors;

the camera includes wide-angle lens and with wide-angle lens fixed connection's vision sensor, wide-angle lens passes through cardan shaft fixed connection with the rear-view mirror.

Further, the system also comprises a transmission conversion chip for connecting the algorithm controller and the image acquisition unit;

the first storage end of the algorithm controller is electrically connected with a random access memory (SDRAM), the second storage end of the algorithm controller is electrically connected with the flash memory, and the image output end of the algorithm controller is electrically connected with the display.

The utility model has the beneficial effects that: the utility model provides a large vehicle blind area monitoring devices based on video image utilizes the camera to gather the visual image of vehicle rear side to monitor moving object, utilize vehicle control unit to acquire the turn to information of vehicle, thereby judge the danger that exists through the motion information that combines moving object's motion information and the turn to information of vehicle, overcome that current monitoring mode measuring range is limited and be difficult to be applied to moving vehicle not enough.

Drawings

Fig. 1 is a schematic structural diagram of a large vehicle blind area monitoring device based on video images.

Fig. 2 is a schematic connection diagram of a vehicle body and a rearview mirror in a large vehicle blind area monitoring device based on video images.

Fig. 3 is a schematic connection diagram of a rearview mirror and a camera in a large vehicle blind area monitoring device based on video images.

Fig. 4 is a schematic connection diagram of a wide-angle lens in a large vehicle blind area monitoring device based on video images.

In the figure: 1. an algorithm controller; 2. an image acquisition unit; 3. a camera; 4. a vehicle control unit; 5. an alarm unit; 6. a rear view mirror; 7. a wide-angle lens; 8. a cardan shaft; 9. a transmission conversion chip; 10. SDRAM; 11. flashing; 12. a display.

Detailed Description

In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and preferred embodiments.

As shown in fig. 1, 2, 3 and 4, the present invention provides a video image-based monitoring device for blind areas of a large vehicle, comprising:

the algorithm controller 1, the algorithm controller 1 prefabricates a vision algorithm; the visual algorithm comprises five steps of image acquisition, image processing, candidate area determination, target image determination and target image tracking. The method specifically comprises the steps of carrying out white balance, noise reduction, sharpening, region selection, gray level conversion, deformity correction and other processing on a picture to obtain a target image and determine a candidate region; and further combining the trained model algorithm to determine a final target image. And then, tracking the moving target by using a moving frame algorithm, thereby measuring and calculating the distance, the speed and the position of the moving target.

The system comprises an image acquisition unit 2, wherein the image acquisition unit 2 comprises cameras 3 fixed on two sides of a vehicle body, and the image acquisition unit 2 is electrically connected with an algorithm controller 1; the cameras 3 are used for respectively collecting image information behind two sides of the vehicle.

The whole vehicle controller 4 is electrically connected with the algorithm controller 1 through a control bus; the vehicle control unit 4 can acquire state information of the vehicle during driving, such as steering information, speed information, and the like.

And the alarm unit 5 is electrically connected with the algorithm controller 1. When the vehicle runs, the algorithm controller 1 acquires the steering and lane changing information of the vehicle through the vehicle control unit 4, and obtains the relative distance, the relative speed and the relative position information of the moving target through calculation by combining the image information acquired by the image acquisition unit 2. It should be added that the algorithm controller 1 stores a safety threshold of distance and speed in advance, and if the relative distance and the relative speed exceed the safety threshold, the algorithm controller 1 performs an early warning through the warning unit 5. The alarm unit 5 includes, but is not limited to, an audible and visual alarm.

The utility model provides a large vehicle blind area monitoring devices based on video image utilizes the camera to gather the visual image of vehicle rear side to monitor moving object, utilize vehicle control unit to acquire the turn to information of vehicle, thereby judge the danger that exists through the motion information that combines moving object's motion information and the turn to information of vehicle, overcome that current monitoring mode measuring range is limited and be difficult to be applied to moving vehicle not enough.

Furthermore, rear-view mirrors 6 are arranged on two sides of the vehicle, and the camera 3 is fixed at the bottom of the rear-view mirrors 6; it should be noted here that the camera 3 may be fixed at any position on both sides of the vehicle where no occlusion occurs.

Camera 3 includes wide-angle lens 7 and with wide-angle lens 7 fixed connection's vision sensor, wide-angle lens 7 passes through cardan shaft 8 fixed connection with rear-view mirror 6. The visual sensor is preferably a starlight level sensor, which is used to ensure that the visual data is acquired under extremely low illumination. Meanwhile, in order to ensure the image acquisition quality, a supplementary light source, such as an infrared LED, is arranged near the camera 3 on the vehicle body, and the supplementary light source is provided with a photosensitive element and can be turned on and/or turned off according to the working environment. Meanwhile, the structural design of the universal shaft 8 can effectively increase the acquisition range of the camera 3.

Further, the system also comprises a transmission conversion chip 9 for connecting the algorithm controller 1 and the image acquisition unit 2; the transmission conversion chip 9 is used for converting the analog quantity collected by the camera 3 into digital quantity information.

The image output end of the algorithm controller 1 is electrically connected with the display 12. The display 12 is preferably a touch screen display 12 for controlling the alarm unit 5. Specifically, when the alarm unit 5 rings, the driver can cancel the alarm by touching.

The first storage terminal of the algorithm controller 1 is electrically connected to the SDRAM10, and the second storage terminal of the algorithm controller 1 is electrically connected to the flash memory 11. Wherein the SDRAM10 and the flash memory 11 are used for storing temporary data and execution codes stored by the algorithm controller 1. And the algorithm controller is connected with the power supply unit through a power supply interface.

The application provides a large-scale vehicle blind area monitoring devices based on video image, algorithm controller utilizes the camera of rear-view mirror department to gather the visual image of vehicle rear side and monitor the moving object, utilizes vehicle control unit to obtain the turn to information of vehicle simultaneously, thereby judges the danger that exists through the motion information that combines the moving object and the turn to information of vehicle to utilize the display control alarm unit, thereby overcome that current monitoring mode measuring range is limited and be difficult to be applied to the not enough of moving vehicle.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A large vehicle blind area monitoring device based on video images is characterized by comprising:

an algorithm controller that pre-manufactures a vision algorithm;

the image acquisition unit comprises cameras fixed on two sides of the vehicle body, and is electrically connected with the algorithm controller;

the vehicle control unit is electrically connected with the algorithm controller through a control bus;

and the alarm unit is electrically connected with the algorithm controller.

2. The video image-based large vehicle blind area monitoring device according to claim 1, wherein rear view mirrors are arranged on two sides of the vehicle, and the cameras are fixed to the bottoms of the rear view mirrors;

the camera include wide-angle lens and with wide-angle lens fixed connection's vision sensor, wide-angle lens with the rear-view mirror passes through cardan shaft fixed connection.

3. The video image-based large vehicle blind area monitoring device according to claim 1, further comprising a transmission conversion chip for connecting the algorithm controller and the image acquisition unit;

the first storage end of the algorithm controller is electrically connected with the SDRAM, the second storage end of the algorithm controller is electrically connected with the flash memory, and the image output end of the algorithm controller is electrically connected with the display.