WO2018120470A1 - Image processing method for use when reversing vehicles and relevant equipment therefor - Google Patents

Abstract

Disclosed in the embodiments of the present invention are an image processing method for use when reversing vehicles and relevant equipment therefor, for use in highlighting different types of barrier images in a vehicle reversing image by using different marks to alert a driver of the location and the type of a barrier in the vehicle reversing image. The method in the embodiments of the present invention comprises: receiving a vehicle reversing image sent from a vehicle reversing camera, the vehicle reversing image being an image which is collected by the vehicle reversing camera within a target range at a back side of a vehicle during reversing; carrying out image recognition on the vehicle reversing image so as to identify a barrier image within the target range which is contained in the vehicle reversing image; highlighting the barrier image in the vehicle reversing image. The embodiments of the present invention may use different marks to highlight different types of barrier images in the vehicle reversing image, alerting the driver of the location and the type of a barrier in the vehicle reversing image.

Description

Method for reversing image processing and related equipment

The present application claims priority to Chinese Patent Application No. 201611265855.2, entitled "A Method and Apparatus for Reversing Security Reminder" on December 30, 2016, the entire contents of which are incorporated herein by reference. In the application.

Technical field

The present application relates to the field of communications technologies, and in particular, to a method for reversing image processing and related devices.

Background technique

At present, the reversing system of the vehicle has low-end and high-end, and the reversing system of the low-end vehicle has no auxiliary device. The driver can complete the reversing behavior by watching the left and right rear view mirrors and controlling the gear position and the brakes and the braking system. Mid- to high-end cars generally have some reversing aids. Others basically provide a reversing video display combined with a reversing radar to assist the reversing. The driver can observe the display on the multimedia car display installed in the center of the front end of the cab. Reversing the image to assist in completing the reversing control.

The reversing video display mainly uses the video picture captured by the reversing camera installed at the rear of the vehicle, and then transmits the video picture back to the display screen of the vehicle terminal (car machine) installed in the center of the center console. The driver can directly improve the safety of the reverse by directly observing the road condition picture directly behind the vehicle collected by the rear camera displayed on the display of the vehicle.

Due to the limited objective effect of these auxiliary devices, the reversing behavior mainly depends on the driver's own cognitive experience to control the processing. Since the subjective judgment ability of the person may be biased and is also easily affected by the emotion, the reversing assistance is made. The device’s real risk warning is low.

Summary of the invention

The embodiment of the present application provides a method for reversing image processing and related equipment, which is used to remind a driver whether there is an obstacle in a reversing road condition, and provides information on the position and type of the obstacle, thereby improving the risk warning capability and reducing the reversing safety accident. .

In view of this, the first aspect of the present application provides a method for reversing image processing, which specifically includes: a terminal on a vehicle receives a reversing image transmitted from a reversing camera, wherein the reversing image collected by the reversing camera is behind the reversing vehicle The image within the range captured by the reversing camera. In the embodiment of the present application, the terminal can highlight the obstacle image in the reverse image, and can clearly remind the driver of the position of the obstacle in the reverse image.

In a possible design, in a first implementation manner of the first aspect of the embodiments of the present application, the reversing image includes a multi-frame image, and performing image recognition on the reversing image to determine the reversing image After the obstacle image in the target range included in the method, the method includes: the terminal performing image recognition on the reverse image, and then identifying the type of the obstacle of the obstacle image in the reverse image according to the result of the image recognition, Wherein, the type of the obstacle includes a dynamic obstacle and a static obstacle, and then the terminal highlights the obstacle image in the reverse image in the display screen according to the type of the obstacle. In the embodiment of the present application, the type of the obstacle is specifically described, and the embodiment of the present application is enriched.

In a possible design, in a second implementation manner of the first aspect of the embodiments of the present application, the highlighting the obstacle image in the reverse image according to the type of the obstacle includes: If the terminal determines that the vehicle is backing up If the obstacle in the image is a static obstacle, then the obstacle is marked with the first mark so that the obstacle is highlighted in the reverse image of the display screen due to the marking of the first mark; if the terminal determines the obstacle in the reverse image If the object is a dynamic obstacle, then the obstacle is marked with a second mark such that the obstacle is highlighted in the reverse image of the display screen due to the marking of the second mark. In the embodiment of the present application, since the terminal marks the static obstacle with the first mark, the dynamic mark is marked with the second mark, so that the user can clearly distinguish the static obstacle and the dynamic obstacle in the reverse image by the reverse image.

In a possible design, in a third implementation manner of the first aspect of the embodiments of the present application, the method further includes: if the terminal determines that only a static obstacle exists in the reverse image, then the control speaker sends a first prompt Sound, if the terminal judges that there is only a dynamic obstacle in the reverse image, then the control speaker emits a second prompt sound. If the terminal determines that there are static obstacles and dynamic obstacles in the reverse image, then the control speaker emits a third prompt sound. In the embodiment of the present application, the terminal may control the speaker to emit different prompt sounds according to the type of the obstacle existing in the reverse image, so that the user can determine the type of the obstacle existing in the reverse image through the prompt sound emitted by the speaker.

In a possible design, in a fourth implementation manner of the first aspect of the embodiments, the method further includes: when the user transmits an obstacle cancellation instruction to the terminal, the terminal may cancel the instruction according to the obstacle The obstacle feature data corresponding to the obstacle cancel instruction is saved in the local non-obstacle feature database, and the local database is refreshed. In the embodiment of the present application, the user may also send an obstacle cancellation instruction to the terminal, so that the terminal can learn autonomously according to the instruction, thereby improving the accuracy of the obstacle recognition.

In a possible design, in a fifth implementation manner of the first aspect of the embodiments, the method further includes: the user sends a download request instruction to the terminal, and then the terminal sends an instruction according to the download request from the Internet. Download the latest image recognition engine program data and update the image recognition engine program data to the database. In the embodiment of the present application, the terminal may download the image recognition engine program data through the download request instruction of the user, and improve the image recognition capability of the image.

A second aspect of the present application provides a terminal, including: the terminal includes: an input device, an output device, an optical sensor, a processor, and a memory; and the optical sensor is configured to perform the following steps: acquiring a reverse image, the reverse The image is an image captured by the optical sensor within a target range of the vehicle that is being reversed; the processor is configured to perform an operation of: performing image recognition on the reverse image by calling an operation instruction stored in the memory An obstacle image within the target range included in the reverse image is determined; the control display unit highlights the obstacle image. In the embodiment of the present application, the terminal can highlight the obstacle image in the reverse image, and can clearly remind the driver of the position of the obstacle in the reverse image.

In a possible design, in a first implementation manner of the second aspect of the embodiment of the present application, the processor is further configured to perform the following steps, including: acquiring an obstacle type of the obstacle image, where The type of obstacle includes a dynamic obstacle and a static obstacle; the highlighting the image of the obstacle in the reverse image includes: highlighting the said in the reverse image according to a type of the obstacle Obstacle image. In the embodiment of the present application, the type of the obstacle is specifically described, and the embodiment of the present application is enriched.

In a possible design, in a second implementation manner of the second aspect of the embodiments of the present application, the processor is further configured to perform the following steps, including: if the obstacle is a static obstacle, a mark annotating the obstacle image such that the obstacle image is highlighted; if the obstacle is a dynamic obstacle, marking the The obstacle image causes the obstacle image to be highlighted. In the embodiment of the present application, since the terminal marks the static obstacle with the first mark, the dynamic mark is marked with the second mark, so that the user can clearly distinguish the static obstacle and the dynamic obstacle in the reverse image by the reverse image.

In a possible implementation, in a third implementation manner of the second aspect of the embodiment of the present application, the processor is further configured to perform the following steps, including: if there is only a static obstacle in the inverted image, then controlling The horn emits a first prompt sound; if only a dynamic obstacle exists in the inverted image, controlling the horn to emit a second prompt sound, if there is a static obstacle and a dynamic obstacle simultaneously in the inverted image, then controlling The horn emits a third prompt tone. In the embodiment of the present application, the terminal may control the speaker to emit different prompt sounds according to the type of the obstacle existing in the reverse image, so that the user can determine the type of the obstacle existing in the reverse image through the prompt sound emitted by the speaker.

In a possible design, in a fourth implementation manner of the second aspect of the embodiments of the present application, the processor is further configured to: perform: receiving an obstacle cancellation instruction from a user; The object cancel instruction updates the local database, and deletes the obstacle feature image corresponding to the obstacle cancel instruction in the local database. In the embodiment of the present application, the user may also send an obstacle cancellation instruction to the terminal, so that the terminal can learn independently according to the instruction, and improve the accuracy of the user.

In a possible design, in a fifth implementation manner of the second aspect of the embodiments of the present application, the processor is further configured to perform the following steps, including: receiving a download request instruction from a user, the download request instruction Instructs to download and update image recognition engine program data from the Internet. In the embodiment of the present application, the terminal may download the image recognition engine program data through the download request instruction of the user, and improve the image recognition capability of the image.

The third aspect of the present application provides a terminal, including:

a first receiving unit, configured to receive a reverse image transmitted by the reversing camera, where the reversing image is an image of the rear target range of the vehicle being reversed collected by the reversing camera;

An image recognition unit, configured to perform image recognition on the reversing image to determine an obstacle image in the target range included in the reversing image;

a display unit for highlighting the obstacle image in the reverse image.

In the embodiment of the present application, the display unit can highlight the obstacle image in the reverse image, and can clearly remind the driver of the position of the obstacle in the reverse image.

In a possible design, in a first implementation manner of the third aspect of the embodiments of the present application, the reversing image includes a multi-frame image, and the image recognition unit includes:

Obtaining a subunit for acquiring a type of an obstacle of the obstacle image, the type of the obstacle comprising: a dynamic obstacle and a static obstacle;

The display unit includes:

a display subunit for highlighting the obstacle image in the reverse image according to the type of the obstacle.

In the embodiment of the present application, how to perform image recognition on the reverse image and the result of the identification are described, so that the embodiment of the present application is more specific and more operable.

In a possible design, in a second implementation manner of the third aspect of the embodiments of the present application, the display subunit includes:

a first labeling module, configured to: when the obstacle is a static obstacle, mark the obstacle image with a first mark, so that the obstacle image is highlighted;

The second labeling module is configured to mark the obstacle image with a second mark when the obstacle is a dynamic obstacle, so that the obstacle image is highlighted.

In the embodiment of the present application, since the terminal marks the static obstacle with the first mark, the dynamic mark is marked with the second mark, so that the user can clearly distinguish the static obstacle and the dynamic obstacle in the reverse image by the reverse image.

In a possible design, in a third implementation manner of the third aspect of the embodiments, the terminal further includes:

a first control unit, configured to control the speaker to emit a first prompt sound when only a static obstacle exists in the inverted image;

The second control unit is configured to control the speaker to emit a second prompt sound when only a dynamic obstacle exists in the inverted image.

The third control unit is configured to control the speaker to emit a third prompt sound when the static obstacle and the dynamic obstacle are simultaneously present in the inverted image.

In the embodiment of the present application, the terminal may control the speaker to emit different prompt sounds according to the type of the obstacle existing in the reverse image, so that the user can determine the type of the obstacle existing in the reverse image through the prompt sound emitted by the speaker.

In a possible implementation, in a fourth implementation manner of the third aspect of the embodiments, the terminal further includes:

a second receiving unit, configured to receive an obstacle cancellation instruction from the user;

And an updating unit, configured to update the local database according to the obstacle cancellation instruction, and delete an obstacle feature image corresponding to the obstacle cancellation instruction in the local database.

In the embodiment of the present application, the user may also send an obstacle cancellation instruction to the terminal, so that the terminal can learn independently according to the instruction, and improve the accuracy of the user.

In a possible implementation, in a fifth implementation manner of the third aspect of the embodiments, the terminal includes:

And a third receiving unit, configured to receive a download request instruction from the user, the download request instruction instructing downloading and updating the image recognition engine program data from the Internet.

In the embodiment of the present application, the terminal may download the image recognition engine program data through the download request instruction of the user, and improve the image recognition capability of the image.

Yet another aspect of the present application provides a computer readable storage medium having instructions stored therein that, when executed on a computer, cause the computer to perform the methods described in the above aspects.

Yet another aspect of the present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the methods described in the various aspects above.

In the technical solution provided by the embodiment of the present application, the terminal receives a reverse image transmitted by the reversing camera, where the reversing image is an image of the rear target range of the reversing vehicle collected by the reversing camera; and performing an image on the reversing image Identifying to determine an obstacle image within the target range included in the reverse image; highlighting the obstacle image in the reverse image. The embodiment of the present application can remind the driver whether there is an obstacle in the reversing road condition, and provide the location and type information of the obstacle, thereby improving the risk warning capability and reducing the reversing safety accident.

DRAWINGS

FIG. 1 is a schematic diagram of an application scenario in an embodiment of the present application;

2 is a schematic diagram of an embodiment of a method for reversing image processing in an embodiment of the present application;

3 is a schematic block diagram of a method for reversing image processing in an embodiment of the present application;

FIG. 4 is a schematic diagram of an application scenario in the embodiment of the present application;

FIG. 5 is a schematic diagram of an application scenario in the embodiment of the present application;

FIG. 6 is a schematic diagram of an application scenario in the embodiment of the present application;

7 is a schematic block diagram of a method for reversing image processing in an embodiment of the present application;

FIG. 8 is a schematic diagram of an application scenario in the embodiment of the present application;

FIG. 9 is a schematic diagram of an embodiment of a terminal in an embodiment of the present application.

detailed description

The embodiment of the present application provides a method for reversing image processing and related equipment for highlighting different types of obstacle images in a reversing image by using different markers, and reminding the driver of the position and type of obstacles in the reversing image, and reducing The accident rate.

The terms "first", "second", "third", "fourth", etc. (if present) in the specification and claims of the present application and the above figures are used to distinguish similar objects without having to use To describe a specific order or order. It is to be understood that the data so used may be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than what is illustrated or described herein. In addition, the terms "comprises" and "comprises" and "the" and "the" are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to Those steps or units may include other steps or units not explicitly listed or inherent to such processes, methods, products or devices.

In-vehicle terminal: In this paper, the car machine, that is, the car navigation entertainment multimedia machine installed in the center of the cab, has multimedia entertainment audio and video service functions, such as U disk playback/radio/navigation and other entertainment functions, and has a high-definition display. Entertainment interface.

Telematics Box (TBOX): A box-shaped ECU unit that is installed inside the vehicle body to collect electronic status information of other electronic control units (ECUs) in the vehicle body network, and can provide 3GPP/ to the vehicle. LTE Telecom/Mobile/Unicom Data Access Service Data Channel.

Image Recognition: Also known as Pattern Recognition, image recognition is a computer program processing algorithm that filters out a combination of continuous data with certain characteristics in a continuous piece of data information. Image recognition filters out obstacle content information that is different from the background content of the road surface, and obtains position information and type information (moving or stationary) of the suspected obstacle in the image.

The embodiment of the present application can be used in the application scenario shown in FIG. 1 . In this application scenario, the vehicle has a liquid crystal display (LCD), which can display the acquired reversing video, and the user can obtain the road condition within a certain range of the tail of the vehicle when the vehicle is reversing through the reversing video. In the prior art, the user generally judges the position and type of the obstacle objectively through the reversing screen displayed on the LCD. However, the driver's own cognitive experience is limited, and the subjective judgment ability of the person may be biased and also susceptible to emotions. The impact of the reduction, so that these reversing aids really play a lower risk warning role.

In view of this, in the embodiment of the present application, after receiving the reversing image transmitted by the reversing camera, the terminal performs image recognition on the reversing image, identifies an obstacle in the reversing image, and highlights different types of obstacles with different markings. .

It should be noted that the embodiment of the present application is mainly applied to a terminal, and the terminal may be any terminal device including a mobile phone, a tablet PDA (Personal Digital Assistant), a POS (Point of Sales), an in-vehicle terminal, and the like. , specifically here is not limited.

For the sake of understanding, the specific process in the embodiment of the present application is described below. The terminal device uses a vehicle as an example. Referring to FIG. 2, an embodiment of the method for reversing image processing in the embodiment of the present application includes:

201. The vehicle receives the reverse image transmitted by the reversing camera.

When the user drives the reverse gear and starts the reverse operation, the reverse camera is triggered to shoot. The image captured by the reverse camera is an image within a certain range behind the vehicle, and the reverse camera transmits the acquired image to the vehicle. machine.

As shown in the schematic block diagram of the embodiment of the present application, the reversing camera transmits the acquired reversing image to the vehicle. There are two methods. The first is that the reversing camera 301 outputs the collected original video signal to the image processing unit. 302, wherein the output video format is an analog format: CVBS/YUV/ARGB, and after the image processing unit 302 receives the original video signal, the input reverse video analog signal is converted into a digital format, and then output to the video processing. Unit 303, the transmitted video format is a digital video format: DRBG/BT565. The second type is that the reversing camera 301 directly converts the collected original video signal into a digital video signal and then outputs it to the video processing unit 303. The transmitted video format is a digital video format: DRBG/BT565.

202. The vehicle performs image recognition on the reverse image to determine the type of the obstacle and the position of the obstacle in the reverse image.

After the vehicle receives the reversing image acquired by the reversing camera, image recognition is performed on the reversing image to determine the type of obstacle and the position of the obstacle in the reversing image. It should be noted that the reversing image includes a multi-frame image, and the image recognition of the reversing image by the vehicle may be performed by using the pre-stored obstacle feature information data to perform image recognition on the multi-frame image to determine an obstacle in the multi-frame image. The area of the object image is then tracked and recognized by the image recognition logic for the state of the obstacle region of each frame image or each several frames of image, when a relative image of the image of the same obstacle region is found to be a certain image relative to the surrounding background image After a certain change has been made within the number of frames, the obstacle area becomes a moving obstacle, otherwise it is still regarded as a static obstacle. Once an obstacle area is identified as a moving obstacle, unless the feature information of the obstacle area image disappears in the reversing video picture, the obstacle area image is always regarded as a moving obstacle, and the area is correspondingly The labeling and control speakers emit corresponding beeps.

As shown in the schematic block diagram of the embodiment of the present application, the method for image recognition of the reverse image by the vehicle is that after the video processing unit 303 in the vehicle receives the reverse video data in the digital video format, the video processing unit 303 The digital video data input to the video processing unit 303 by the reversing video data is adjusted by the internal scaler 3031 to adjust the video resolution and position to suit the screen size. The scale-adjusted image data is transmitted to the display storage module 3034 inside the video processing unit 303. The control logic module 3033 within the video processing unit 303 will then read the content in the display storage module 3034 and perform image recognition on the display memory content to identify the obstacle information in the display storage module 3034.

203. The car machine highlights the obstacle image in the reverse image according to the type of the obstacle.

If the vehicle acquires the obstacle type in the reverse image and the position of the obstacle in the reverse image according to the result of the image recognition, it will be highlighted in the reverse image displayed on the display on the vehicle according to the type of the obstacle. An obstacle image, if the obstacle in the reverse image displayed in the display is a static obstacle, then the obstacle image is marked with a first mark so that the obstacle image is highlighted; if the reverse image is displayed in the display The obstacle is a dynamic obstacle, then the obstacle image is marked with a second mark so that the obstacle image is highlighted.

As shown in FIG. 4, when the obstacle displayed in the display 401 on the vehicle is a static obstacle, the obstacle is marked with a first mark, and the first mark may be a frame mark, and the frame is high. The yellow mark of the brightness allows the driver to clearly see the position of the obstacle in the reverse image through the display of the vehicle; when the obstacle displayed in the display 401 is a dynamic obstacle, the obstacle is marked with the second mark The second mark may also be a frame mark, and the frame has a high-brightness red mark, so that the driver can clearly see the position of the obstacle in the reverse image through the display of the vehicle, and the like In the case, the type of the obstacle can be judged by the different colors displayed by the frame. The stone 4011 on the display screen on the vehicle in FIG. 4 represents a static obstacle, and the bicycle 4012 represents a dynamic obstacle. If the user desires to distinguish the obstacles on the reversing video in the display 401 on the vehicle by the first mark and the second mark on the obstacle as static obstacles and dynamic obstacles, the display form of the mark may be a frame using different colors, the frame The obstacle can also be other display forms, such as rendering the area of the obstacle in the reverse image with different colors; the first mark and the second mark can also be distinguished by different shapes, for example, the static obstacle uses a rectangular frame. The dynamic obstacles use a triangular frame, and the specific display forms of the first mark and the second mark are various, and are not limited herein.

It should be noted that, by setting the vehicle, the first mark and the second mark displayed on the reverse video are the same mark, and the mark types of the first mark and the second mark are not specifically limited herein.

It should be noted that when the vehicle determines that the obstacle displayed on the display screen 401 is a dynamic obstacle, the vehicle can also highlight the dynamic obstacle on the display screen 401 according to the speed of the dynamic obstacle. When the speed of the dynamic obstacle displayed on the display screen 401 exceeds the preset speed, it is determined that the obstacle is an excessive obstacle, and when the speed of the dynamic obstacle displayed on the display screen 401 does not exceed the preset speed, it is determined. The obstacle is a non-over obstacle, and the vehicle can highlight the over obstacle and the non-over obstacle on the display screen 401 with different obstacle marks. For example, when the dynamic obstacle is an overspeed obstacle, it can be marked with a high-brightness red frame mark. When the obstacle is a non-speeding obstacle, the high-brightness orange frame mark can be used to mark the obstacle of the overspeed obstacle. There are various forms of the marker mark and the obstacle mark of the non-elevation obstacle, and are not limited herein.

It should be noted that the vehicle can also highlight the dynamic obstacle on the display screen 401 according to the size of the obstacle. When the size of the dynamic obstacle displayed on the display screen 401 exceeds the preset volume, it is determined that the obstacle is a large obstacle, and when the size of the dynamic obstacle displayed on the display screen 401 does not exceed the preset volume, it is determined. The obstacle is a small obstacle, and the vehicle can highlight large obstacles and small obstacles on the display screen 401 with different obstacle markers. For example, when the dynamic obstacle is a large obstacle, it can be marked with a triangular frame mark, and when the obstacle is a small obstacle, it can be marked with a rectangular frame mark, an obstacle mark of a large obstacle and a small obstacle. There are various forms of obstacle markings, which are not limited herein.

It should be noted that the vehicle can also highlight the dynamic obstacle on the display screen 401 according to the type of the obstacle. When the vehicle determines that the dynamic obstacle displayed on the display screen 401 is a car, it is determined that the obstacle is an automobile obstacle, and when the vehicle determines that the dynamic obstacle displayed on the display screen 401 is a truck, the obstacle is determined to be For truck-like obstacles, the vehicle can use different obstacle markers on the display screen 401 to highlight automobile obstacles and truck-like obstacles. For example, when the dynamic obstacle is a vehicle lightning obstacle, it can be marked with a static type frame mark. When the obstacle is a truck type obstacle, the mark can be marked with a flashing frame mark, and the obstacle mark of the automobile type obstacle is marked. There are various forms of obstacle markings for truck-like obstacles, which are not limited herein.

As shown in FIG. 3 of the embodiment of the present application, the display in the vehicle machine highlights the obstacle image in the reverse image. The control logic module 3033 in the video processing unit 303 in the vehicle reads the display storage module 3034. After the content, the content in the display storage module 3034 is image-recognized, and the obstacle information in the display storage module 3034 is identified. The obstacle information includes the position of the obstacle in the reverse image and the type of the obstacle, and the control logic After the module 3033 identifies the obstacle information in the display storage module 3034, it controls the drawing module 3032 to perform the drawing work of the prompting mark (such as the prompt box) of the related graphic according to the recognition result. After the prompting mark is drawn, the drawing module 3032 will draw the drawing. A vector user interface (UI) graphic overlay is mixed into the display storage module 3034 such that the video image content in the display storage module 3034 contains the reverse image to be displayed and associated prompt tags, and then the drive display in the video processing unit 303 The module outputs the content in the display storage module 3034 to the display screen, so that The display on the vehicle's display image with the obstacle reverse flag of tips, the transmitted video signal is a digital video signal format: DRGB / LVDS.

204. The vehicle controls the horn to emit a prompt tone according to the type of the obstacle.

When the vehicle has recognized the type of obstacle in the reverse image, the horn will be controlled to sound according to the type of obstacle. When the vehicle recognizes that there is only a static obstacle in the reverse image, the opportunity control horn emits a first prompt sound, such as a "beep" - "beep" - "beep" prompt sound, it should be noted that the reverse image is found There are many types of beeps sounded by a horn when there are static obstacles. In addition to the "beep" - "beep" - "beep" beep, there are other types of beep, for example, "哔" - "哔" - “哔”, the sound effect of the specific sound is not limited here; when the vehicle recognizes that there is only a dynamic obstacle in the reverse image, the opportunity control speaker emits a second prompt, such as “beep toot”-“dot The beep of "beep" - "beep beep", it should be noted that when there are dynamic obstacles in the reversing image, there are many types of beeps that can be emitted by the speaker, except for "dudu toot" - "dudu toot" There are other types of prompts for the "-" toot beep, for example, "哔哔哔"-"哔哔哔"-"哔哔哔", the sound effect of the specific sound is not limited here. When there are dynamic obstacles and static obstacles on the reverse image, the vehicle control horn emits a third prompt sound, such as a "beep-beep-beep-beep-beep" sound. It should be noted that the reverse is found. There are many types of beeps that can be emitted by the speaker when there are both dynamic obstacles and static obstacles in the image. In addition to the beep-beep-beep-beep beep, there are other types of beep, such as , "哔-哔哔哔-哔-哔哔哔", the sound effect of the specific tone is not limited here. The prompt tone should distinguish between the static obstacle or the dynamic obstacle or the two obstacles in the reverse image, so that the driver can also know whether there are obstacles and obstacles on the reverse image through the prompt sound. Types of.

It should be noted that, by setting the vehicle, the first prompt tone, the second prompt tone, and the third prompt tone may be the same type of prompt tone, or the third prompt tone may be set to be the same as the first prompt tone. The type, or the third prompt tone is the same as the second prompt tone. The specific setting type is not limited here.

It should be noted that the car machine can also adjust the volume of the sound by its own volume adjustment function.

As shown in FIG. 5, FIG. 5 is a schematic diagram of an embodiment in the case where a dynamic obstacle exists in the reverse image.

As shown in the schematic block diagram of the embodiment of the present application, the method for the car machine control speaker to emit the prompt tone is that after the control logic module 3033 in the video processing unit 303 in the vehicle reads the content in the display storage module 3034, The content in the storage module 3034 is displayed for image recognition, and the obstacle information in the display storage module 3034 is identified. The obstacle information includes the position of the obstacle in the reverse image and the type of the obstacle. The control logic module 3033 controls the audio according to the recognition result. The processing unit 304 is configured to generate an audio coded signal of the prompt tone that matches the current obstacle type, and the audio processing unit 304 outputs the prompt audio and audio coded signal to the horn after internal processing, so that the horn emits an obstacle in the reverse image. The sound corresponding to the object type.

205. The vehicle receives an obstacle cancellation instruction from the user, and updates the local database according to the obstacle cancellation instruction.

As shown in FIG. 6 , in the embodiment of the present application, the user can open the learning mode on the setting interface of the vehicle, and the user reverses the gear and starts the reverse driving. At this time, the font of the “learning mode” is displayed on the display of the vehicle. There is an obstacle in the reversing image. The display of the car will display the reversing image with the obstacle mark. When the user judges the content of the reversing image in the display and determines that the obstacle in a certain area indicates an error, Actually it is not an obstacle. At this time, the user will click on the area on the display, and then the area will pop up a confirmation window with “Are you sure it is not an obstacle?”, at this time, the user clicks on the confirmation, indicating that there is no obstacle in the area. , cancel the obstacle characteristics.

After the user clicks the confirmation, the vehicle cancels the obstacle mark in the area in the reverse image according to the obstacle cancellation instruction of the user, and controls the speaker to cancel the prompt sound associated with the obstacle, and simultaneously feeds the relevant feature information of the area fed back by the user. The feature is included in the local non-obstacle feature database, and the local database is refreshed. At this time, the obstacle mark of the area that the user clicked in before disappears.

If the user ends the reversing, but re-attaches the reverse gear at this position, enters the reverse mode. At this time, the road display screen of the current car tail is displayed on the display of the car. At this time, the car machine will think that the area that the user originally clicked on the screen is not There is an obstacle, there is no obstacle mark in this area, and the horn will not emit a corresponding tone according to the area.

It should be noted that the user can start the learning mode of the vehicle before starting the reversing, or after determining that there is a wrong obstacle in the reversing image, and then click the learning mode of the driving machine, what can be the learning mode of the vehicle Open, specifically here is not limited.

It should be noted that, in the vehicle of the embodiment of the present application, the user may not need to perform the step of opening the learning mode on the setting interface, that is, the learning mode in the vehicle and the interface of the reverse image in which the obstacle exists are the same. In the mode, the user can reverse the vehicle by the obstacle prompt in the reverse image, or directly click the obstacle area through the display screen, that is, an obstacle cancellation command is issued to the vehicle.

It should be noted that the display screen in the embodiment of the present application has a touch screen function.

It should be noted that the user can update the local feature database through the learning mode, but does not update the public feature database and the image recognition engine itself.

As shown in the schematic block diagram of the embodiment of the present application, the vehicle machine receives the obstacle cancellation instruction from the user, and updates the local database according to the obstacle cancellation instruction. In the learning mode of the vehicle, the user clicks on the vehicle. The relevant obstacle cue area in the reversing image displayed on the display screen 705 of the touch screen function, the display screen 705 passes the touch information to the touch processing unit 706. The touch processing unit 706 calculates coordinate information of the touch according to the touch event described above, and transmits the information to the control logic module 7033 in the video processing unit 703. Control logic module 7033 According to the feedback click information, the current obstacle prompt box ID is matched, and the drawing module is controlled to cancel or close the drawing of the prompt box.

The control logic module 7033 matches the data content in the current area display storage module 7034 according to the feedback click information, and finds the related feature information data of the image calculation of the area and then updates into the algorithm database 7035, so that the next control logic module When 7033 recognizes the feature information again, the regional calculation result will be generated with the non-obstacle conclusion.

The control logic module 7033 cancels the frame control prompt of the area according to the information clicked by the user, and then refreshes the audio control policy notification to the audio processing unit 704 according to the overall obstacle calculation result state of the rear view video interface: if the user feedback obstacle is canceled After the area prompts, there are other obstacles, according to the prompt rules: when there is only a dynamic obstacle, the moving obstacle alarm sound is output; when there is only a static obstacle, the static obstacle alarm sound is output; there are both dynamic obstacles and existence In the case of static obstacles, the alarm sounds of both obstacles are output at the same time; when there are no dynamic obstacles or static obstacles, no obstacle alarm sound is output.

After the drawing module 7032 cancels or closes the prompt box display of a certain area, the new graphic user interface (GUI) is output and outputted to the display storage module 7034, so that the display content of the vehicle display screen 705 is no longer displayed. A prompt box with the area is displayed.

206. The vehicle receives the download request instruction from the user, and downloads and updates the image recognition engine program data according to the download instruction.

In the embodiment of the present application, as shown in FIG. 8 , firstly, the vehicle of the user is installed with an in-vehicle communication box, which may be a Huawei TBOX product, or another in-vehicle device with Ethernet wireless data transceiving function. The type of vehicle communication box is not limited here. The car on the user's car works normally. The interface shows that the network is connected and the signal status is good. The user turns on the image recognition setting and finds that the current image recognition engine version in the car is not the latest version on the display. The user clicks the latest version download button, passes the download request command to the car, and starts downloading the latest version of the image recognition engine. When downloading, the screen displays the download entry identifier.

After the download is completed, the car display screen image recognition engine installation interface. After the installation is completed, the user has completed the installation. The user re-enters the image recognition setting interface and sees that the current image recognition engine version is the latest version.

The user initiates reversing. At this time, the video processing unit in the vehicle uses the latest image recognition algorithm and feature database to enter the pattern recognition of the reversing video image, and the recognition accuracy will be improved.

It should be noted that the user can update the image recognition engine itself and the public feature database by remote downloading, but does not update the local feature database.

As shown in FIG. 8, the specific process of the car machine receiving the download request instruction from the user and downloading and updating the image recognition engine program data according to the download instruction is that the vehicle passes the universal serial bus (Universal Serial Bus, USB). ) or other interface to establish a data connection with the TBOX device, obtain the image engine version in the remote city service is 1.0.1, which is newer than the current version of the car. At this time, the car machine can click the download button in the setting interface, and the user clicks the download button. After that, the car informs the TBOX of the event.

After receiving the download request event of the vehicle, the TBOX generates a data request frame to be sent to the communication base station according to a wireless data transmission protocol format, for example, a protocol format such as 3GPP/4GPP/LTE. The specific wireless data transmission protocol format type is not limited herein. After receiving the data request from the TBOX, the communication base station packages the data into a conventional wired Ethernet transmission protocol, for example The protocol such as TCP/IP is sent to the remote server. The type of the specific wired Ethernet transmission protocol is not limited here. After receiving the data request, the server encapsulates the local latest image recognition engine code program data in a certain protocol format. The TCP/IP data frame is reported to the communication base station, and the communication base station converts the data into a 3GPP/4GPP/LTE protocol frame for transmission. The modem on the TBOX receives the 3GPP/4GPP/LTE protocol frame data containing the image recognition engine code program data uploaded by the communication base station, and after unpacking, transmits the image recognition engine code program data to the vehicle in a certain protocol format. After receiving the data of the new version of the image recognition engine, the car machine first stores it in the storage space of the car itself. After the download is completely completed, the update installation is automatically started, and the latest version of the image recognition engine data in the local storage space is overwritten. The image identifies the engine data and completes the update upgrade. After the upgrade is completed, the user performing the reverse will use the new image recognition engine program to perform image recognition to calculate the obstacle result, so that the image recognition ability of the vehicle is improved.

It should be noted that the application can automatically upload the local feature database of each vehicle terminal to the cloud server by using the characteristics of the TBOX Internet access, and the SERVE program running on the server automatically learns according to the new feature database data. The public database and the correction engine algorithm are updated to realize the intelligent improvement technology of the background automatic learning similar to the "neural network" mode. The more feedback each terminal has, the faster the learning, the greater the degree of improvement, and the automatic maintenance of the person can be removed. growing up.

It should be noted that the embodiment of the present application can also save the key data result of the image recognition generated when the vehicle reverses over a period of time, and save the reverse obstacle LOG file. When the vehicle reverses an accident, the insurance company or related responsible party The personnel can help to restore the accident mechanism and correctly locate the responsibility relationship according to the real-time information of the obstacles expressed by the reverse obstacle LOG file recorded inside the vehicle.

In the technical solution provided by the embodiment of the present application, the terminal receives the reversing image transmitted by the reversing camera, and the reversing image is an image of the rear target range of the reversing vehicle collected by the reversing camera; and performing image recognition on the reversing image to determine an obstacle The type and the position of the obstacle in the reversing image; then, according to the type of the obstacle, the obstacle image in the reversing image is highlighted in the display screen, and according to the type of the obstacle, the control horn emits a beep. The embodiment of the present application can use different markers to highlight different types of obstacle images in the reverse image, and can also control the speaker to emit different sounds according to the obstacle type in the reverse image, so that the driver can accurately judge the sound combined with the reverse image and the speaker. The type and location of obstacles in the reversing video reduces the risk of reversing safety.

The above-mentioned FIG. 3 to FIG. 8 describe the method of the reverse image processing in the embodiment of the present application in detail. The terminal in the embodiment of the present application is described in detail below from the perspective of hardware processing.

As shown in FIG. 9 , the embodiment of the present application further provides a terminal, where the terminal includes a processor 980 and a touch screen. In practical applications, the touch screen may further include a touch panel 931 and a display panel 941 . For the convenience of description, only the parts related to the embodiments of the present application are shown in FIG. 9, and the specific technical details are not disclosed. Please refer to the method part of the embodiment of the present application. The terminal can be any terminal device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), an in-vehicle computer, and the like.

Referring to FIG. 9, the terminal includes: a radio frequency (RF) circuit 910, a memory 920, an input unit 930, a display unit 940, a sensor 950, an audio circuit 960, a wireless fidelity (WiFi) module 970, and a processor 980. And the power supply 990 and the like, wherein the WiFi module 970 can be a module in the TBOX, and the specific location is not limited herein. It will be understood by those skilled in the art that the terminal structure shown in FIG. 9 does not constitute a limitation to the terminal, and may include more or less components than those illustrated, or combine some components or different components. Arrangement.

The following describes the components of the terminal in detail with reference to FIG. 9:

The RF circuit 910 can be used for receiving and transmitting signals during the transmission or reception of information or during a call. Specifically, after receiving the downlink information of the base station, it is processed by the processor 1380. In addition, the uplink data is designed to be sent to the base station. Generally, RF circuit 910 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuitry 910 can also communicate with the network and other devices via wireless communication. The above wireless communication may use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division). Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), E-mail, Short Messaging Service (SMS), and the like.

The memory 920 can be used to store software programs and modules, and the processor 980 executes the method of reverse image processing in the embodiments of the present application by running software programs and modules stored in the memory 920. The memory 920 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to Data created by the use of the terminal (such as audio data, phone book, etc.). Moreover, memory 920 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 930 can be configured to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the terminal. Specifically, the input unit 930 may include a touch panel 931 and other input devices 932 (eg, a mouse, a keyboard, etc.). The touch operation of the user on or near the user may be collected (for example, the user uses a finger, a stylus, or the like, any suitable object or accessory on the touch panel 931 or in the vicinity of the touch panel 931), and according to a preset program Drive the corresponding connecting device. Optionally, the touch panel 931 can include two parts: a touch detection device and a touch controller. Wherein, the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information. The processor 980 is provided and can receive commands from the processor 980 and execute them. In addition, the touch panel 931 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 931, the input unit 930 may also include other input devices 932. Specifically, other input devices 932 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.

The display unit 940 can be used to display information input by the user or information provided to the user as well as various menus of the terminal. The display unit 940 can include a display panel 941. Alternatively, the display panel 941 can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Further, the touch panel 931 can cover the display panel 941. When the touch panel 931 detects a touch operation on or near the touch panel 931, the touch panel 931 transmits to the processor 980 to determine the type of the touch event, and then the processor 980 according to the touch event. The type provides a corresponding visual output on display panel 941. Although in FIG. 9, the touch panel 931 and the display panel 941 function as two independent components to implement the input and input functions of the terminal, in some embodiments, the touch can be performed. The panel 931 is integrated with the display panel 941 to implement input and output functions of the terminal.

The terminal may also include at least one type of sensor 950, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 941 according to the brightness of the ambient light, and the proximity sensor may close the display panel 941 and/or when the terminal moves to the ear. Or backlight. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity. It can be used to identify the attitude of the terminal (such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for the terminal can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, no longer Narration.

An audio circuit 960, a speaker 961, and a microphone 962 can provide an audio interface between the user and the terminal. The audio circuit 960 can transmit the converted electrical data of the received audio data to the speaker 961, and convert it into a sound signal output by the speaker 961. On the other hand, the microphone 962 converts the collected sound signal into an electrical signal, and the audio circuit 960 After receiving, it is converted into audio data, and then processed by the audio data output processor 980, transmitted to the terminal, for example, via the RF circuit 99, or outputted to the memory 920 for further processing.

WiFi is a short-range wireless transmission technology, and the terminal can help users to send and receive emails, browse web pages, and access streaming media through the WiFi module 970, which provides users with wireless broadband Internet access. Although FIG. 9 shows the WiFi module 970, it can be understood that it does not belong to the necessary configuration of the terminal, and may be omitted as needed within the scope of not changing the essence of the invention.

Processor 980 is the control center of the terminal, interconnecting various portions of the entire terminal using various interfaces and lines, executing or executing software programs and/or modules stored in memory 920, and invoking data stored in memory 920, The method of reverse image processing in the embodiment of the present application. Optionally, the processor 980 may include one or more processing units; preferably, the processor 980 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application, and the like. The modem processor primarily handles wireless communications. It will be appreciated that the above described modem processor may also not be integrated into the processor 980.

The terminal also includes a power source 990 (such as a battery) that supplies power to the various components. Preferably, the power source can be logically coupled to the processor 980 through a power management system to manage functions such as charging, discharging, and power management through the power management system.

Although not shown, the terminal may further include a camera, a Bluetooth module, and the like, and details are not described herein again.

In the embodiment of the present application, the sensor 950 included in the terminal has the following functions:

Obtaining a reversing image, which is an image of the rear target range of the vehicle being reversed collected by the optical sensor 950, wherein the sensor 950 is an optical sensor;

In the embodiment of the present application, the processor 980 included in the terminal further has the following functions:

Performing image recognition on the reversing image to determine an obstacle image within a target range included in the reversing image;

The control display unit 940 highlights an obstacle image.

The processor 980 included in the terminal also has the following functions:

Obtaining a type of obstacle of the obstacle image, the type of the obstacle including a dynamic obstacle and a static obstacle;

The obstacle image in the reverse image is highlighted based on the type of obstacle.

The processor 980 included in the terminal also has the following functions:

If the position of the same obstacle image is different in each frame of the image, it is determined that the obstacle is a dynamic obstacle;

If the same obstacle image has the same position in each frame of image, it is determined that the obstacle is a static obstacle.

The processor 980 included in the terminal also has the following functions:

If the obstacle is a static obstacle, the control display unit 940 displays the obstacle having the first mark;

If the obstacle is a dynamic obstacle, the control display unit 940 displays the obstacle having the second mark.

The processor 980 included in the terminal also has the following functions:

If the obstacle is a static obstacle, the control horn emits a first prompt tone;

If the obstacle is a dynamic obstacle, the control horn emits a second tone.

The processor 980 included in the terminal also has the following functions:

Receiving an obstacle cancellation instruction from the user;

The local database is updated according to the obstacle cancel instruction, and the obstacle feature image corresponding to the obstacle cancel instruction in the local database is deleted.

The processor 980 included in the terminal also has the following functions:

A download request instruction from the user is received, the download request instruction instructing downloading and updating the image recognition engine program data from the Internet.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, it may be implemented in whole or in part in the form of a computer program product.

A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with embodiments of the present application are generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, computer instructions can be wired from a website site, computer, server or data center (eg, Coax, fiber, digital subscriber line (DSL) or wireless (eg, infrared, wireless, microwave, etc.) is transmitted to another website, computer, server, or data center. The computer readable storage medium can be any available media that can be stored by the computer or a data storage device such as a server, data center, or the like that includes one or more available media. Useful media can be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (D)).

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the system, the device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the several embodiments provided by the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner, for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

The above embodiments are only used to explain the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still The technical solutions described in the embodiments are modified, or the equivalents of the technical features are replaced by the equivalents. The modifications and substitutions of the embodiments do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (14)

1. A method for reversing image processing, comprising:

   Receiving a reversing image transmitted by the reversing camera, wherein the reversing image is an image of the rear target range of the reversing vehicle collected by the reversing camera;

   Performing image recognition on the reversing image to determine an obstacle image within the target range included in the reversing image;

   The obstacle image in the reverse image is highlighted.
2. The method according to claim 1, wherein after the image recognition of the reversing image to determine an obstacle image within the target range included in the reversing image, the method further comprises :

   Obtaining a type of obstacle of the obstacle image, the type of the obstacle including a dynamic obstacle and a static obstacle;

   The highlighting the obstacle image in the reverse image includes:

   The obstacle image in the reverse image is highlighted based on the type of the obstacle.
3. The method according to claim 2, wherein the highlighting the obstacle image in the reversing image according to the type of the obstacle comprises:

   If the obstacle is a static obstacle, mark the obstacle image with a first mark so that the obstacle image is highlighted;

   If the obstacle is a dynamic obstacle, the obstacle image is marked with a second mark such that the obstacle image is highlighted.
4. The method according to claim 2 or 3, wherein the method further comprises:

   If there is only a static obstacle in the inverted image, controlling the speaker to emit a first prompt tone;

   If there is only a dynamic obstacle in the inverted image, controlling the speaker to emit a second prompt tone;

   If there are static obstacles and dynamic obstacles in the inverted image, the speaker is controlled to emit a third prompt sound.
5. The method according to any one of claims 1 to 3, further comprising:

   Receiving an obstacle cancellation instruction from the user;

   The obstacle feature data corresponding to the obstacle cancel instruction is saved to the local non-obstacle feature database according to the obstacle cancel instruction.
6. The method according to any one of claims 1 to 3, further comprising:

   A download request instruction is received from a user, the download request instruction instructing downloading and updating image recognition engine program data from the Internet.
7. A terminal, wherein the terminal comprises:

   Input device, output device, optical sensor, processor and memory;

   The optical sensor is configured to perform the following steps:

   Acquiring a reversing image, wherein the reversing image is an image of the rear target range of the vehicle being reversed collected by the optical sensor;

   The processor is configured to perform the following steps by calling an operation instruction stored in the memory:

   Performing image recognition on the reversing image to determine a barrier within the target range included in the reversing image Obstacle image

   The control display unit highlights the obstacle image.
8. The terminal according to claim 7, wherein the processor is further configured to perform the following steps, including:

   Obtaining a type of the obstacle of the obstacle image, the type of the obstacle comprising: a dynamic obstacle and a static obstacle;

   The highlighting the obstacle image in the reverse image includes:

   The obstacle image in the reverse image is highlighted based on the type of the obstacle.
9. The terminal according to claim 8, wherein the processor is further configured to perform the following steps, including:

   If the obstacle is a static obstacle, the control display unit displays the obstacle having the first mark;

   If the obstacle is a dynamic obstacle, the control display unit displays the obstacle having the second mark.
10. The terminal according to claim 8 or 9, wherein the processor is further configured to perform the following steps, including:

    If there is only a static obstacle in the inverted image, controlling the speaker to emit a first prompt tone;

    If there is only a dynamic obstacle in the inverted image, controlling the speaker to emit a second prompt tone;

    If there are static obstacles and dynamic obstacles in the inverted image, the speaker is controlled to emit a third prompt sound.
11. The terminal according to any one of claims 7 to 9, wherein the processor is further configured to perform the following steps, including:

    Receiving an obstacle cancellation instruction from the user;

    The obstacle feature data corresponding to the obstacle cancel instruction is saved to the local non-obstacle feature database according to the obstacle cancel instruction.
12. The terminal according to any one of claims 7 to 9, wherein the processor is further configured to perform the following steps, including:

    A download request instruction is received from a user, the download request instruction instructing downloading and updating image recognition engine program data from the Internet.
13. A computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-3.
14. A computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-3.

Images