CN116205829A - Rearview mirror image fusion method, device, vehicle-mounted equipment and storage medium - Google Patents

Abstract

The application discloses a rearview mirror image fusion method, device, vehicle-mounted equipment, and storage medium. The rearview mirror image fusion method includes: acquiring rearview mirror image data of an automobile electronic rearview mirror, wherein the electronic rearview The mirror includes an electronic interior rearview mirror and left and right electronic exterior mirrors; the image data of the rearview mirror is input into the FPGA chip for deep image fusion to generate a fused image. This application solves the problem that the driver needs to observe three kinds of display devices at the same time during the driving process, and easily causes mistakes when judging the external scene and orientation, realizes the high integration of the system, and improves the safety of driving.

Description

Rearview mirror image fusion method, device, vehicle-mounted equipment and storage medium

technical field

The present application relates to the technical field of image processing, and in particular to a rearview mirror image fusion method, device, vehicle-mounted equipment, and storage medium.

Background technique

Traditional physical exterior rearview mirrors are easily affected by factors such as extreme weather, light intensity, and reflections, which pose certain hidden dangers to driving safety. With the industrialization of the automobile industry and the promotion of the new four modernizations, the safety awareness of automobile manufacturers has improved, and electronic interior and exterior mirrors have gradually appeared in new high-end models. In the existing electronic exterior rearview mirror, cameras are installed on the left and right sides of the vehicle, and two independent display screens are installed in the vehicle to perform low-delay real-time display of images on both sides of the vehicle. The electronic interior rearview mirror (that is, the streaming media rearview mirror) combines the camera function with the traditional interior rearview mirror, installs the rearview camera at the fish fin antenna of the body, and passes the image data collected by the camera through the same The shaft cable is transmitted to the rearview mirror in the car in two directions over a long distance. After processing by the Image Signal Processor chip (ISP for short) and image algorithm enhancement processing, the low-latency image behind the car is projected on the rearview mirror. Live imagery.

The above solution needs to place three different types of display devices in the car. When the driver is changing lanes left or right or reversing, the driver needs to observe the two electronic exterior mirrors in addition to the electronic interior rearview mirror inside the car. , It is easy to cause mistakes in judging the external scene and orientation, and there are potential safety hazards.

Contents of the invention

The main purpose of this application is to provide a rearview mirror image fusion method, device, vehicle-mounted equipment and storage medium, aiming at solving the problem that the driver needs to observe three kinds of display devices at the same time during driving, which is easy to cause problems when judging the external scene and orientation. The problem of mistakes can be realized, and the system can be highly integrated to improve the safety of driving.

In order to achieve the above object, the application provides a rearview mirror image fusion method, the rearview mirror image fusion method comprising:

Acquiring the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic inner rearview mirror and a left and right electronic outer rearview mirror;

The image data of the rearview mirror is input into the FPGA chip for deep image fusion to generate a fused image.

Optionally, after the step of obtaining the rearview mirror image data of the automobile electronic rearview mirror, it also includes:

Carrying out data deserialization processing on the rearview mirror image data, to convert the serial rearview mirror image data into parallel rearview mirror image data;

The described rearview mirror image data is input into the FPGA chip to carry out image depth fusion, and the step of generating the fused picture image comprises: 0. The parallel rearview mirror image data is input into the FPGA chip to carry out image depth fusion ,

A fused frame image is generated.

Optionally, after the step of performing data deserialization processing on the rearview mirror image data to convert the serial rearview mirror image data into parallel rearview mirror image data, it also includes: 5 pairs of the rearview mirror image data Image signal processing is performed on the parallel rearview mirror image data to obtain processed parallel rearview mirror image data.

Optionally, the described rearview mirror image data is input into the FPGA chip to carry out image depth fusion, and the step of generating a fused picture image includes:

0 to obtain the image data of the rearview mirror input into the FPGA chip;

Carrying out image correction to the rearview mirror image data to obtain corrected rearview mirror image data;

Obtain the 3D model of the car and the parameters of the car;

Projecting the corrected rearview mirror image data and the car parameters onto the three-dimensional car model to obtain projected image data;

5. Perform splicing processing on the joints of the images according to the projected image data to obtain spliced image data;

Rendering is performed on the spliced image data to obtain the fused picture image.

Optionally, before the step 0 of obtaining the rearview mirror image data input into the FPGA chip, it also includes:

Load the global configuration of image processing, initialize OpenGL ES components and camera device drivers.

Optionally, before the step of obtaining the rearview mirror image data of the automotive electronic rearview mirror, it also includes:

The image data of the rearview mirror is collected, including:

The rearview mirror image data of the rear of the car is collected by the rearview camera;

The image data of the rearview mirrors on the left and right sides are collected by the left and right cameras installed at the left and right electronic exterior mirrors.

Optionally, after the described rearview mirror image data is input into the FPGA chip to carry out image depth fusion, after the step of generating the fused picture image, it also includes:

and displaying the fused image on a single display device.

The embodiment of the present application also proposes a rearview mirror image fusion device, and the rearview mirror image fusion device includes:

The image acquisition module is used to acquire the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic inner rearview mirror and a left and right electronic outer rearview mirror;

The image fusion module is used to input the image data of the rearview mirror into the FPGA chip for image depth fusion to generate a fused picture image.

The embodiment of the present application also proposes a vehicle-mounted device, the vehicle-mounted device includes a memory, a processor, and a rearview mirror image fusion program stored in the memory and operable on the processor, the rearview mirror image When the fusion program is executed by the processor, the steps of the above-mentioned rearview mirror image fusion method are realized.

The embodiment of the present application also proposes a computer-readable storage medium, the computer-readable storage medium stores a rearview mirror image fusion program, and when the rearview mirror image fusion program is executed by a processor, the rearview mirror image fusion program as described above is implemented. Steps of the mirror image fusion method.

The rearview mirror image fusion method, device, vehicle-mounted equipment, and storage medium proposed in the embodiments of the present application obtain rearview mirror image data of an electronic rearview mirror of an automobile, wherein the electronic rearview mirror includes an electronic interior rearview mirror and an electronic rearview mirror. The left and right electronic exterior mirrors; the image data of the rearview mirrors are input to the FPGA chip for deep image fusion to generate a fused image. By integrating the image of the electronic interior rearview mirror and the image of the electronic exterior mirror and performing panoramic fusion of the images, the three-way video can be fused into one display image, realizing the image display without dead angles behind the car, and improving driving safety.

Description of drawings

Fig. 1 is the schematic diagram of the functional modules of the vehicle equipment belonging to the rearview mirror image fusion device of the present application;

Fig. 2 is the schematic flow chart of the first exemplary embodiment of the rearview mirror image fusion method of the present application;

Fig. 3 is the schematic flow chart of the second exemplary embodiment of the rearview mirror image fusion method of the present application;

Fig. 4 is a schematic flowchart of a third exemplary embodiment of a rearview mirror image fusion method of the present application.

The realization, functional features and advantages of the present application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

The main solution of the embodiment of the present application is to obtain the rearview mirror image data of the automobile electronic rearview mirror, wherein the electronic rearview mirror includes an electronic interior rearview mirror and a left and right electronic exterior rearview mirror; The mirror image data is input to the FPGA chip for deep image fusion to generate a fused image. By integrating the image of the electronic interior rearview mirror and the image of the electronic exterior mirror and performing panoramic fusion of the images, the three-way video can be fused into one display image, realizing the image display without dead angles behind the car, and improving driving safety.

Specifically, referring to FIG. 1 , FIG. 1 is a schematic diagram of the functional modules of the vehicle-mounted equipment to which the rearview mirror image fusion device of the present application belongs. The rearview mirror image fusion device can be a device independent of the vehicle-mounted equipment, capable of image processing and deep image fusion, and can be carried on the vehicle-mounted equipment in the form of hardware or software.

In this embodiment, the vehicle-mounted device to which the rearview mirror image fusion device belongs includes at least an output module 110 , a processor 120 , a memory 130 and a communication module 140 .

Stored in the memory 130 are an operating system and a rearview mirror image fusion program, and the rearview mirror image fusion device can input the rearview mirror image data into the FPGA chip for the rearview mirror image data of the obtained automotive electronic rearview mirror. The fused picture image generated by deep fusion, the rearview mirror

Information such as the parallel rearview mirror image data obtained after the image data is deserialized, and the processed parallel rearview mirror image data obtained by performing image signal processing on the parallel rearview 5-mirror image data is stored in the memory 130 Middle; the output module 110 may be a display screen or the like. The communication module 140 may include a CAN module, a WIFI module, a mobile communication module, a Bluetooth module, etc., and communicate with external devices or servers through the communication module 140 .

Wherein, when the rearview mirror image fusion program in the memory 130 is executed by the processor, the following steps are realized:

Acquiring the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic inner rearview mirror and a left and right electronic outer rearview mirror;

The image data of the rearview mirror is input into the FPGA chip for deep image fusion to generate a fused image.

5 Further, when the rearview mirror image fusion program in the memory 130 is executed by the processor, the following steps are also realized:

Carrying out data deserialization processing on the rearview mirror image data, to convert the serial rearview mirror image data into parallel rearview mirror image data;

The processed parallel rearview mirror image data is input into the FPGA chip for image depth 0-degree fusion to generate a fused image.

Further, when the rearview mirror image fusion program in the memory 130 is executed by the processor, the following steps are also realized:

Image signal processing is performed on the parallel rearview mirror image data to obtain processed parallel rearview mirror image data.

5 Further, when the rearview mirror image fusion program in the memory 130 is executed by the processor, the following steps are also realized:

Obtain the image data of the rearview mirror input into the FPGA chip;

Carrying out image correction to the rearview mirror image data to obtain corrected rearview mirror image data;

Obtain the 3D model of the car and the parameters of the car;

0 projecting the corrected rearview mirror image data and the car parameters onto the three-dimensional car model to obtain projected image data;

splicing the joints of the images according to the projected image data to obtain the spliced image data;

Rendering is performed on the spliced image data to obtain the fused picture image.

Further, when the rearview mirror image fusion program in the memory 130 is executed by the processor, the following steps are also realized:

Load the global configuration of image processing, initialize OpenGL ES components and camera device drivers.

Further, when the rearview mirror image fusion program in the memory 130 is executed by the processor, the following steps are also realized:

The image data of the rearview mirror is collected, including:

The rearview mirror image data of the rear of the car is collected by the rearview camera;

The image data of the rearview mirrors on the left and right sides are collected by the left and right cameras installed at the left and right electronic exterior mirrors.

Further, when the rearview mirror image fusion program in the memory 130 is executed by the processor, the following steps are also realized:

and displaying the fused image on a single display device.

This embodiment adopts the above scheme, specifically by acquiring the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic interior rearview mirror and a left and right electronic exterior rearview mirror; The image data is input to the FPGA chip for deep image fusion to generate a fused image. By integrating the image of the electronic interior rearview mirror and the image of the electronic exterior mirror and performing panoramic fusion of the images, the three-way video can be fused into one display image, realizing the image display without dead angles behind the car, and improving driving safety.

Based on but not limited to the above-mentioned vehicle-mounted device architecture, the method embodiments of the present application are proposed.

Referring to FIG. 2 , FIG. 2 is a schematic flowchart of a first exemplary embodiment of a rearview mirror image fusion method of the present application. Described rearview mirror image fusion method comprises:

Step S10, acquiring rearview mirror image data of the automobile electronic rearview mirror, wherein the electronic rearview mirror includes an electronic interior rearview mirror and left and right electronic exterior mirrors;

Step S20, inputting the image data of the rearview mirror into the FPGA chip for deep image fusion to generate a fused image.

The execution subject of the method in this embodiment can be a rearview mirror image fusion device, or a rearview mirror image fusion vehicle-mounted device or server. The rearview mirror image fusion device in this embodiment is an example. The rearview mirror image The fusion device can be integrated on the vehicle equipment with data processing function.

In this embodiment, the rearview mirror image data of the electronic rearview mirror of the automobile is obtained, wherein the electronic rearview mirror may include an electronic interior rearview mirror and a left and right electronic exterior rearview mirror; The rear and right rearview mirror image data is input to the FPGA chip for deep image fusion to generate a super wide-angle fused image. This embodiment can reduce the use of SOC by integrating it on an FPGA chip, and through the image fusion algorithm, on the premise that all three video inputs can be displayed, and realize the advantages of better cost, lighter weight, and safer driving. .

It should be noted that, compared with traditional SOC solutions of the same price, FPGA has the advantages of strong image processing performance, less delay from image processing to display, and supports multiple image inputs at the same time. Optionally, the FPGA selected in this embodiment is the ZU3EG chip of Xilinx as the main chip.

Further, as an implementation manner, before the above step S101, before obtaining the rearview mirror image data of the electronic rearview mirror of the automobile, it may also include:

The image data of the rearview mirror is collected, including:

The rearview mirror image data of the rear of the car is collected by the rearview camera;

The image data of the rearview mirrors on the left and right sides are collected by the left and right cameras installed at the left and right electronic exterior mirrors.

Specifically, for a single electronic interior rearview mirror, due to the limitation of the installation position of the camera, the field of view that can be highlighted is usually about 80°, but there are still blind spots on the left and right sides of the vehicle, so it is impossible to view the rear of the left and right sides of the vehicle. Full coverage of blind spots in the field of vision. In this embodiment, the rearview mirror image data at the rear of the car is collected by combining the rearview camera, and the rearview mirror image data on the left and right sides are collected by the left and right cameras installed at the left and right electronic exterior mirrors. Collect the left, right and rear panorama of the vehicle to avoid blind spots behind the vehicle.

Further, as an implementation manner, in the above step S102, after inputting the rearview mirror image data into the FPGA chip for image depth fusion and generating the fused picture image, it may also include:

and displaying the fused image on a single display device.

By displaying the fused image integrated with the images of the electronic interior and exterior mirrors on a single display device, the degree of integration of the vehicle can be improved, the weight of the vehicle can be reduced, the manufacturing cost of the vehicle can be reduced, and it can contribute to the lightweight index of the vehicle. contribute.

This embodiment adopts the above scheme, specifically by acquiring the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic interior rearview mirror and a left and right electronic exterior rearview mirror; The image data is input to the FPGA chip for deep image fusion to generate a fused image. Through the integration of the electronic exterior mirror picture and the panoramic fusion of the picture, the picture without dead angle behind the car can be realized, and the safety of driving can be improved; the high integration of the system can be realized by the fusion of the electronic interior and exterior mirror, and the manufacturing cost of the whole vehicle can be reduced. .

Referring to FIG. 3 , FIG. 3 is a schematic flowchart of a second exemplary embodiment of a rearview mirror image fusion method of the present application. Based on the embodiment shown in above-mentioned Fig. 2, in the present embodiment, after obtaining the step of the rearview mirror image data of automobile electronic rearview mirror, described rearview mirror image fusion method also includes:

Step S101, performing data deserialization processing on the rearview mirror image data, so as to convert the serial rearview mirror image data into parallel rearview mirror image data.

Specifically, since the acquired rearview mirror image data of the automobile electronic rearview mirror is serial data, before inputting the FPGA chip, the rearview mirror image data is subjected to data deserialization processing, so that the serial rearview mirror can be The mirror image data is converted into parallel mirror image data.

Then, step S102 is executed to input the parallel rearview mirror image data into the FPGA chip for deep image fusion to generate a fused image.

Further, as an implementation manner, in the above step S101, after performing data deserialization processing on the rearview mirror image data to convert the serial rearview mirror image data into parallel rearview mirror image data, further Can include:

Step S103, performing image signal processing on the parallel rearview mirror image data to obtain processed parallel rearview mirror image data.

Specifically, image signal processing is performed on the parallel rearview mirror image data obtained after data deserialization processing, and the processed parallel rearview mirror image data is obtained, so as to improve the observation effect of subsequent users. Optionally, the image signal processing may include but not limited to: linearity correction, noise removal, dead point repair, color interpolation, white balance correction, exposure correction, etc.

In this embodiment, by performing image signal processing on the image data of the rearview mirror, the image can be enhanced under severe weather conditions, so as to avoid driving safety problems in harsh environments and further improve driving safety.

This embodiment adopts the above scheme, specifically by acquiring the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic interior rearview mirror and a left and right electronic exterior rearview mirror; Carry out data deserialization processing on the image data, to convert the serial rearview mirror image data into parallel rearview mirror image data; carry out image signal processing to the parallel rearview mirror image data, obtain the parallel rearview mirror image data after processing Mirror image data; the rearview mirror image data is input into the FPGA chip for image depth fusion to generate a fused picture image. By integrating the image of the electronic interior rearview mirror and the image of the electronic exterior mirror and performing panoramic fusion of the images, the three-way video can be fused into one display image, realizing the image display without dead angles behind the car, and improving driving safety.

Referring to FIG. 4 , FIG. 4 is a schematic flowchart of a third exemplary embodiment of a rearview mirror image fusion method of the present application. Based on the embodiment shown in above-mentioned Fig. 2 and Fig. 3, in the present embodiment, above-mentioned step S20, described rearview mirror image data is input in the FPGA chip and carries out image depth fusion, and the screen image after generating fusion can comprise:

Step S201, obtaining the image data of the rearview mirror input into the FPGA chip;

Step S202, performing image correction on the rearview mirror image data to obtain corrected rearview mirror image data;

Step S203, obtaining the three-dimensional model of the vehicle and the parameters of the vehicle;

Step S204, projecting the corrected rearview mirror image data and the car parameters onto the three-dimensional car model to obtain projected image data;

Step S205, performing splicing processing on the joints of the images according to the projected image data to obtain spliced image data;

Step S206, performing rendering processing on the spliced image data to obtain the fused picture image.

Specifically, the rearview mirror image data of the electronic interior rearview mirror and the rearview mirror image data of the left and right electronic exterior rearview mirrors input to the FPGA chip are acquired. Then, image correction is performed on the acquired three-way rearview mirror image data to obtain corrected rearview mirror image data. Next, the pre-stored three-dimensional model of the car and car parameters are acquired; optionally, the car parameters may include but not limited to car color. The corrected rearview mirror image data and vehicle parameters are projected onto the three-dimensional model of the vehicle to form projected image data. Then according to the projected image data, splicing processing is performed on the joints in the images, including brightness adjustment of the connected images, etc., to obtain the spliced image data. Finally, image rendering processing is performed on the spliced image data to obtain the fused image.

Further, as an implementation manner, before the above step S201, before obtaining the rearview mirror image data input to the FPGA chip, it may also include:

Load the global configuration of image processing, initialize OpenGL ES components and camera device drivers.

This embodiment adopts the above scheme, specifically by acquiring the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic interior rearview mirror and a left and right electronic exterior rearview mirror; The image data is input to the FPGA chip for deep image fusion to generate a fused image. By integrating the image of the electronic interior rearview mirror and the image of the electronic exterior mirror and performing panoramic fusion of the images, the three-way video can be fused into one display image, realizing the image display without dead angles behind the car, and improving driving safety.

In addition, the embodiment of the present application also proposes a rearview mirror image fusion device, and the rearview mirror image fusion device includes:

The image acquisition module is used to acquire the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic inner rearview mirror and a left and right electronic outer rearview mirror;

The image fusion module is used to input the image data of the rearview mirror into the FPGA chip for image depth fusion to generate a fused picture image.

For the principle and implementation process of realizing the fusion of rearview mirror images in this embodiment, please refer to the above-mentioned embodiments, and details will not be repeated here.

In addition, the embodiment of the present application also proposes a vehicle-mounted device, which includes a memory, a processor, and a rearview mirror image fusion program stored in the memory and operable on the processor. When the mirror image fusion program is executed by the processor, the steps of the above-mentioned rearview mirror image fusion method are realized.

Since this rearview mirror image fusion program is executed by the processor, it adopts all the technical solutions of all the foregoing embodiments, so at least it has all the beneficial effects brought by all the technical solutions of all the foregoing embodiments, and will not repeat them one by one here. repeat.

In addition, the embodiment of the present application also proposes a computer-readable storage medium, on which a rearview mirror image fusion program is stored, and when the rearview mirror image fusion program is executed by a processor, the above-mentioned The steps of the rearview mirror image fusion method.

Since this rearview mirror image fusion program is executed by the processor, it adopts all the technical solutions of all the foregoing embodiments, so at least it has all the beneficial effects brought by all the technical solutions of all the foregoing embodiments, and will not repeat them one by one here. repeat.

Compared with the prior art, the rearview mirror image fusion method, device, vehicle-mounted equipment and storage medium proposed in the embodiments of the present application obtain the rearview mirror image data of the automobile electronic rearview mirror, wherein the electronic rearview mirror includes The electronic interior rearview mirror and the left and right electronic exterior mirrors; the image data of the rearview mirrors are input to the FPGA chip for deep image fusion to generate a fused image. By integrating the image of the electronic interior rearview mirror and the image of the electronic exterior mirror and performing panoramic fusion of the images, the three-way video can be fused into one display image, realizing the image display without dead angles behind the car, and improving driving safety.

It should be noted that, as used herein, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.

The serial numbers of the above embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence or in other words, the part that contributes to the prior art, and the computer software product is stored in one of the above storage media (such as ROM/RAM, magnetic disc, optical disc), several instructions are included to make a device execute the method of each embodiment of the present application.

The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structures or equivalent process transformations made by using the description of the application and the accompanying drawings are directly or indirectly used in other related technical fields. , are all included in the patent protection scope of the present application in the same way.

Claims (10)

1. a rearview mirror image fusion method is characterized in that, the rearview mirror image fusion method comprises: Acquiring the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic inner rearview mirror and a left and right electronic outer rearview mirror; The image data of the rearview mirror is input into the FPGA chip for deep image fusion to generate a fused image. 2. rearview mirror image fusion method as claimed in claim 1, is characterized in that, after the step of the rearview mirror image data of described acquisition electronic rearview mirror of automobile, also comprises: Carrying out data deserialization processing on the rearview mirror image data, to convert the serial rearview mirror image data into parallel rearview mirror image data; The described rearview mirror image data is input in the FPGA chip to carry out image depth fusion, and the step of generating the picture image after fusion comprises: The parallel rearview mirror image data is input into the FPGA chip for deep image fusion to generate a fused image. 3. the rearview mirror image fusion method as claimed in claim 2, is characterized in that, described rearview mirror image data is carried out data deserialization processing, to convert serial rearview mirror image data into parallel After the step of rearview mirror image data, it also includes: Image signal processing is performed on the parallel rearview mirror image data to obtain processed parallel rearview mirror image data. 4. rearview mirror image fusion method as claimed in claim 1, is characterized in that, described rearview mirror image data is input in the FPGA chip and carries out image depth fusion, and the step of generating the picture image after fusion comprises: Obtain the image data of the rearview mirror input into the FPGA chip; Carrying out image correction to the rearview mirror image data to obtain corrected rearview mirror image data; Obtain the 3D model of the car and the parameters of the car; Projecting the corrected rearview mirror image data and the car parameters onto the three-dimensional car model to obtain projected image data; splicing the joints of the images according to the projected image data to obtain the spliced image data; Rendering is performed on the spliced image data to obtain the fused picture image. 5. rearview mirror image fusion method as claimed in claim 4, is characterized in that, before the step of described rearview mirror image data that described acquisition is inputted in the described FPGA chip, also comprises: Load the global configuration of image processing, initialize OpenGL ES components and camera device drivers. 6. rearview mirror image fusion method as claimed in claim 1, is characterized in that, before the step of the rearview mirror image data of described obtaining automobile electronic rearview mirror, also comprises: The image data of the rearview mirror is collected, including: The rearview mirror image data of the rear of the car is collected by the rearview camera; The image data of the rearview mirrors on the left and right sides are collected by the left and right cameras installed at the left and right electronic exterior mirrors. 7. rearview mirror image fusion method as claimed in claim 1, is characterized in that, described rearview mirror image data is input in FPGA chip and carries out image depth fusion, after the step of the picture image after generating fusion, Also includes: and displaying the fused image on a single display device. 8. A rearview mirror image fusion device is characterized in that, said rearview mirror image fusion device comprises: The image acquisition module is used to acquire the rearview mirror image data of the electronic rearview mirror of the automobile, wherein the electronic rearview mirror includes an electronic inner rearview mirror and a left and right electronic outer rearview mirror; The image fusion module is used to input the image data of the rearview mirror into the FPGA chip for image depth fusion to generate a fused picture image. 9. A vehicle-mounted device, characterized in that, said vehicle-mounted device comprises a memory, a processor and a rearview mirror image fusion program stored on said memory and operable on said processor, said rearview mirror image When the fusion program is executed by the processor, the steps of the rearview mirror image fusion method according to any one of claims 1-7 are realized. 10. A computer-readable storage medium, characterized in that, the computer-readable storage medium is stored with a rearview mirror image fusion program, and when the rearview mirror image fusion program is executed by a processor, it is realized as claimed in claim 1- The step of the rearview mirror image fusion method described in any one of 7.

Images