WO2022105027A1

WO2022105027A1 - Image recognition method and system, electronic device, and storage medium

Info

Publication number: WO2022105027A1
Application number: PCT/CN2020/141047
Authority: WO
Inventors: 高海超
Original assignee: 安徽鸿程光电有限公司
Priority date: 2020-11-19
Filing date: 2020-12-29
Publication date: 2022-05-27
Also published as: CN112308018A

Abstract

An image recognition method and system, an electronic device, and a storage medium. The method comprises: acquiring a panoramic image and a close-up image, the panoramic image comprising several objects, and the close-up image comprising a preset object; comparing the close-up image and the panoramic image to determine a corresponding area, that corresponds to the close-up image, in the panoramic image; performing image recognition on the close-up image to determine recognition information of the preset object; and on the basis of the recognition information and according to the correspondence between the corresponding area and the close-up image, determining a recognition result of an object in the corresponding area. A panoramic image and a close-up image of a specific object are separately acquired by means of a scenario, and a relationship between the close-up image and the panoramic image is established, to thereby recognize, by using the close-up image, a part that is not clearly recognized in the panoramic image, and thus solving the problem in which a long-distance object image captured by means of a panoramic camera in a large scene is blurry, which is unfavorable for image recognition and leads to a high recognition error rate.

Description

Image recognition method, system, electronic device and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of Chinese Patent Application No. 202011307535.5 filed on November 19, 2020, entitled "An Image Recognition Method, System, Electronic Device and Storage Medium", the entire contents of which are incorporated herein by reference .

technical field

One or more embodiments of the present application relate to the technical field of image recognition, and in particular, to an image recognition method, system, electronic device, and storage medium.

Background technique

With the development of modern camera technology, image recognition technology has gradually become popular and permeated in every corner of life. Its purpose is mainly to more accurately and quickly determine the identity of the objects displayed in the target image or target area in various fields, such as face recognition, prohibited item recognition, and so on.

However, there are still many problems in the field of image recognition in the prior art. Taking face recognition as an example, when recognizing multiple objects in a large scene, due to special reasons such as distance and focus position, certain objects in the panoramic image captured by the panoramic camera will be blurred, which is not conducive to the image. Identification analysis, which will cause the problem of identification failure.

SUMMARY OF THE INVENTION

In view of this, the purpose of one or more embodiments of the present application is to provide an image recognition method, system, electronic device and storage medium to solve the problem of low success rate of specific target recognition in panoramic images captured by panoramic cameras.

Based on the above purpose, one or more embodiments of the present application provide an image recognition method, which includes:

acquiring a panoramic image and a close-up image, the panoramic image includes several objects, the close-up image includes a preset object, and the preset object is an object that satisfies a preset condition among the several objects;

comparing the close-up image and the panoramic image, and determining a corresponding area in the panoramic image corresponding to the close-up image, where the corresponding area includes the preset object;

Perform image recognition on the close-up image to determine the identification information of the preset object;

Based on the identification information, the identification result of the object in the corresponding area is determined according to the corresponding relationship between the corresponding area and the close-up image.

In some embodiments, the comparing the close-up image and the panoramic image to determine a corresponding area in the panoramic image corresponding to the close-up image includes:

determining the comparison area of the close-up image and the comparison area of the panoramic image;

performing similarity comparison between the comparison area of the close-up image and the comparison area of the panoramic image;

If the similarity comparison meets the set condition, the comparison area of the panoramic image is used as the corresponding area.

In some embodiments, the performing image recognition on the close-up image to determine the identification information of the preset object includes:

The feature identification is performed on the close-up image, the identity information of the preset object corresponding to the close-up image is determined, and the identity information is used as the identification information.

In some embodiments, the preset object is specifically:

Among the several objects, the distance to the acquisition position of the panoramic image is greater than a preset threshold.

In some embodiments, the preset object is specifically:

Among the several objects, the distance to the focus area of the panoramic image is greater than a preset threshold.

In some embodiments, the preset object is specifically:

Among the several objects, an object whose definition is smaller than a preset threshold in the panoramic image.

In some embodiments, the panoramic image and the close-up image are acquired during the same period of time.

Based on the same concept, one or more embodiments of the present application also provide an image recognition system, the system includes: a panoramic camera, a close-up camera, and a processor; wherein,

the panoramic camera, configured to capture a panoramic image, the panoramic image including several objects;

the close-up camera is configured to collect a close-up image, the close-up image includes a preset object, and the preset object is an object that satisfies a preset condition among the several objects;

The processor is configured to perform the image recognition method as described in any of the above.

Based on the same concept, one or more embodiments of the present application also provide an electronic device, the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executes the The image recognition method described in any one of the above is implemented in the program.

Based on the same concept, one or more embodiments of the present application also provide a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to make the computer Perform the image recognition method as described in any of the above.

As can be seen from the above, an image recognition method, system, electronic device, and storage medium provided by one or more embodiments of the present application include: acquiring a panoramic image and a close-up image, where the panoramic image includes several objects, and the close-up image includes A preset object, the preset object is an object that satisfies a preset condition among several objects; the close-up image and the panoramic image are compared to determine the corresponding area in the panoramic image corresponding to the close-up image, and the corresponding area includes the preset object; Image recognition is performed to determine the recognition information of the preset object; based on the recognition information, the recognition result of the object in the corresponding area is determined according to the corresponding relationship between the corresponding area and the close-up image. One or more embodiments of the present application obtain a panoramic image and a close-up image of a specific object from a scene, and establish a connection between the close-up image and the panoramic image, so as to use the close-up image to identify the unclearly recognized part of the panoramic image, thereby solving the problem of solving the problem. This solves the problem of blurring distant objects captured by a panoramic camera in a large scene, which is not conducive to image recognition and has a high recognition error rate.

Description of drawings

In order to more clearly illustrate one or more embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, in the following description The accompanying drawings are only one or more embodiments of the present application, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative efforts.

1 is a schematic flowchart of an image recognition method proposed by one or more embodiments of the present application;

FIG. 2 is a schematic structural diagram of an electronic device according to one or more embodiments of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application will be further described in detail below with reference to specific embodiments and accompanying drawings.

It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application shall have the usual meanings understood by those with ordinary skill in the art to which this disclosure belongs. As used in this disclosure, "first," "second," and similar terms do not denote any order, quantity, or importance, but are merely used to distinguish the various components. "Comprising" or "comprising" and similar words mean that the elements, things, or method steps appearing before the word cover the elements, things, or method steps listed after the word, and their equivalents, but do not exclude other elements, things, or method steps. method steps. Words like "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "Down", "Left", "Right", etc. are only used to represent the relative positional relationship, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

As described in the background art section, in a large scene and a large space, such as a large classroom, a large storage room, etc., the recognition of objects in it is usually a panoramic image that covers the entire space by a panoramic camera, and the panoramic image is further processed. image recognition to achieve. When recognizing the objects in it, due to special reasons such as distance and focus position, a specific person or object (such as a person in the back row or far end) is small or blurred in the panoramic image, which is not conducive to image recognition. It is easy to cause recognition errors or recognition failures, which greatly affects the accuracy of image recognition.

Combined with the above-mentioned actual situation, one or more embodiments of the present application propose an image recognition scheme, by separately obtaining a panoramic image and a close-up image of a specific object for a scene, and establishing a connection between the close-up image and the panoramic image, so as to utilize the close-up image. Image recognition The unclear part of the panoramic image is recognized, and then the blurring of distant objects captured by the panoramic camera in a large scene is not conducive to image recognition, and the recognition error rate is high.

Referring to FIG. 1 , it is a schematic flowchart of an image recognition method according to an embodiment of the present application, which specifically includes step 101 , step 102 , step 103 and step 104 .

Step 101: Obtain a panoramic image and a close-up image, where the panoramic image includes several objects, the close-up image includes a preset object, and the preset object is an object that satisfies a preset condition among the several objects.

The purpose of this step is to obtain a panoramic image and a close-up image of the preset object. Among them, the panoramic image is the image including the whole area of the specific place, which can be obtained by a panoramic camera set in the specific place, or the images are stitched together after shooting the specific place with multiple cameras; The specific scene in which things are identified, such as: classroom, storage room, etc., which can be all or a specific part of the specific scene, take the classroom as an example, it can be the entire classroom, or the area other than the podium in the classroom, etc. Wait. The objects are characters such as students in the classroom or objects such as paintings in the storage room. A close-up image is a clear image of a preset object obtained by means of a close-up camera, etc. It can be obtained by shooting each preset object individually, or it can be obtained uniformly for all preset objects. Taking a classroom as an example, a close-up image can be obtained by A separate image for each student at a distance, an image for all students at a distance, and so on.

In some application scenarios, the preset object targeted by the close-up image may be specifically adjusted according to the specific application scenario. For example, the preset object in one specific application scenario is specifically: an object whose distance to the acquisition position of the panoramic image is greater than a preset threshold among the several objects; the preset object in another specific application scenario The object, specifically: an object whose distance to the focal area of the panoramic image is greater than a preset threshold in the several objects; the preset object in another specific application scenario, specifically: the number of objects in the Objects whose sharpness is less than a preset threshold in the panoramic image, etc. It may be a close-up image of a specific object designated in advance.

In some application scenarios, the obtained panoramic images and close-up images may be collected successively, respectively, or may be collected simultaneously. In order to make the posture of a single target in the close-up image and the posture of the target in the panoramic image as consistent as possible, improve the degree of similarity between the close-up image and some areas in the panoramic image, so as to better perform the similarity comparison in the following steps, improve the Comparison success rate. In some embodiments, the panoramic image and the close-up image are acquired during the same period of time.

Among them, the same time period can be understood as the same time or a very small time interval, and the content of the two images obtained in the same time period will be almost the same, so that image recognition can be carried out very easily.

Step 102 , compare the close-up image and the panoramic image, and determine a corresponding area in the panoramic image that corresponds to the close-up image, where the corresponding area includes the preset object.

The purpose of this step is to compare the panoramic image according to the close-up image, and determine the part corresponding to the close-up image in the panoramic image. According to step 101, the close-up image is an image of a single object in the recognition scene or an image of the area where all the objects meet the conditions, and the panoramic image is an image that reflects the whole picture of the recognized scene, and the close-up image must have corresponding parts in the panoramic image. Therefore, the relationship between the two can be established through image recognition and comparison technology, such as face recognition and feature extraction for close-up images, and image recognition in panoramic images with the extracted features to determine that the similarity is higher than a certain threshold. as the part corresponding to the close-up image.

The corresponding area is the area that can reflect the specific characteristics of the image, such as the face area in face recognition, the specific portrait area in painting recognition, the specific characteristics of contraband in contraband recognition, and so on. In a panoramic image, the corresponding area may be one or more. In some application scenarios, the corresponding area is a concentrated area containing specific features. For example, in face recognition, a frame-shaped area where faces are concentrated in a panoramic image. ; In other application scenarios, the corresponding area is a single area where each specific feature is located. For example, in face recognition, the box-shaped area where each face is located in a panoramic image is a corresponding area. Afterwards, since the close-up image is for the preset objects that meet the conditions, it may include all the preset objects that meet the conditions through one image, or it may be obtained separately for each preset object that meets the conditions. Furthermore, the close-up image must also contain specific features of each preset object, so that by comparing and identifying with the panoramic image, a corresponding relationship between the close-up image and the corresponding area in the panoramic image can be established. Here, it can be that the whole image of the close-up image and the corresponding area in the panoramic image establish a corresponding relationship, or it can be that the comparison area in the close-up image and the corresponding comparison area in the panoramic image establish a corresponding relationship. For example: in the classroom face recognition scene, when the close-up image is an image including all eligible students, the corresponding relationship between the close-up image and the panoramic image can be the establishment of a relationship between the entire image of the close-up image and the corresponding area in the panoramic image, or It can be that the face area of each student in the close-up image establishes a corresponding relationship with the corresponding face area in the panoramic image, etc.; when the close-up image is only an image of a qualified student, the corresponding relationship established with the panoramic image can be It is the establishment of a correspondence between the face area of the student and the corresponding face area in the panoramic image, and so on.

Here, since the close-up image and the panoramic image can be taken at the same time or at a very short interval, the poses and features of the same person or object reflected by the two images are highly similar, and the results of the comparison of the two recognition results correspond to The accuracy rate is very high, far higher than the accuracy rate of identifying the two through images in the pre-stored identification library. Taking the face recognition of students in the classroom as an example, the pre-stored recognition library may store images such as student ID photos, while the close-up images and panoramic images are taken at the same time or at a short interval, and the students reflected in the two images All the features of the face are almost identical, and the accuracy of recognizing the panoramic image directly through the close-up image is much higher than the accuracy of recognizing the two images separately through the pre-stored recognition library.

In some application scenarios, in order to accurately determine the corresponding area in the panoramic image that corresponds to the close-up image, only the specific required area is identified to reduce the amount of computation. The comparing the close-up image and the panoramic image to determine a corresponding area in the panoramic image corresponding to the close-up image includes: determining a comparison area of the close-up image and a ratio of the panoramic image. Compare the area; compare the similarity between the comparison area of the close-up image and the comparison area of the panoramic image; if the similarity comparison meets the set conditions, then use the comparison area of the panoramic image as the corresponding area.

Among them, the comparison area of the close-up image is the area that reflects the specific characteristics of the object in the close-up image, such as the face area of each student in the classroom scene, the specific characteristic area of each item in the storage room scene (such as the main body of the painting) part, etc.) etc. In order to reduce the amount of computation, instead of identifying the entire image or the entire area, only a specific area is identified. In some application scenarios, the characteristic area (each face area) of each object in the close-up image is determined again. , and only identify each feature area in the close-up image and the panoramic image, without identifying the whole image.

After that, the setting conditions may be conditions such as the similarity not less than 90%.

Step 103: Perform image recognition on the close-up image to determine the identification information of the preset object.

The purpose of this step is to identify the close-up image to determine the identification information of the preset object corresponding to the close-up image. Wherein, the identification information may be information identifying the preset object or the identity of the corresponding area, and at the same time, the identification information may only be quantitative statistical information, for example, if 5 preset objects are identified in the close-up image, the identification information can be identified as the number of people 5 people.

The image recognition in this step is similar to the image comparison in step 102, except that the comparison database is replaced. Here, a preset standard image library is used, which stores standard feature images of all objects. Perform image recognition on the close-up image based on the standard image library, and determine the specific identity information of the preset objects contained therein. identification information such as the identity information of the person. Further, in some application scenarios, the performing image recognition on the close-up image to determine the identification information of the preset object includes: performing feature recognition on the close-up image, and determining the preset image corresponding to the close-up image. The identity information of the object is assumed, and the identity information is used as the identification information.

Step 104 , based on the identification information, and according to the corresponding relationship between the corresponding area and the close-up image, determine the recognition result of the object in the corresponding area.

The purpose of this step is to correspond the identification information of the preset object in the close-up image to the corresponding object in the panoramic image according to the corresponding relationship, so as to determine the identification result of the object in the panoramic image. The identification result is similar to the identification information, and both are information that can identify the identity of each object or each corresponding area.

According to the corresponding relationship determined in step 102, the mapping relationship between the preset object in the close-up image and an object in the panoramic image can be directly established, and then according to the identification information of the preset object determined in step 103, it can be directly determined according to the mapping. The recognition result of the object in the panoramic image may be the identity of the object in the panoramic image, such as the student's name, student number, ID number, and the like.

At this point, the identity information of specific objects or unclear objects in the panoramic image can be determined. After that, for the objects that can be clearly distinguished in the panoramic image, the clear objects in the panoramic image can be directly identified according to image recognition and other similar methods. recognition, and finally the recognition result of the entire panoramic image can be determined. The recognition result may be information reflecting the identity or quantity of objects in the recognition scene, such as the identity information of each student in the classroom or the number of students in the classroom, the relevant identity information or quantity information of paintings in the storage room, and so on.

Finally, the recognition result can also be output to store, display or reprocess the recognition result. According to different application scenarios and implementation needs, the specific output mode of the recognition result can be flexibly selected.

For example, for an application scenario in which the method of this embodiment is executed on a single device, the recognition result can be directly output on the display component (display, projector, etc.) of the current device in the form of display, so that the operator of the current device can The content of the recognition result can be seen directly on the display part.

For another example, for an application scenario in which the method of this embodiment is executed on a system composed of multiple devices, the identification result may be sent to the system through any data communication method (wired connection, NFC, Bluetooth, wifi, cellular mobile network, etc.). other preset devices as receivers in the device, so that the preset device that has received the identification result can perform subsequent processing on it. Optionally, the preset device may be a preset server, and the server is generally set in the cloud, as a data processing and storage center, which can store and distribute the identification results; wherein, the recipient of the distribution is a terminal device, the The holder or operator of these terminal devices may be the current user, the relevant monitoring personnel who recognize the scene, the unit or individual related to the object in the recognized scene, and so on.

For another example, for an application scenario where the method of this embodiment is executed on a system composed of multiple devices, the identification result may be directly sent to a preset terminal device through any data communication method, and the terminal device may be one of the ones listed in the preceding paragraphs. one or more of.

In a specific application scenario, taking the classroom as an example of recognition, a panoramic image is taken through a panoramic lens, and a close-up image is taken through a close-up lens. Assuming that there are 30 students, the panoramic lens can scan 30 people, and the close-up lens can scan 9 people.

Performing face detection on the close-up picture will get the Rect1 (rectangular area) set of detected faces. If 9 are detected, record them as Rect11, Rect12, ..., Rect19.

Extract eigenvalues from Rect11 to Rect19, and register the extracted eigenvalues in the face recognition model together with the numbers No1 to No9. Perform face recognition on panoramic images, because they are images at the same time or at a similar time, the similarity between the face in the panoramic image and the face in the close-up image will be very high, and the matching face with a similarity of more than 90% is extracted as the panoramic person. The face set Rect2 includes: Rect21, Rect22, ..., Rect29, each face corresponds to a number, No1 to No9. The numbers in Rect2 are in one-to-one correspondence with the numbers in Rect1.

Reload the preset 30 student face database sample eigenvalues to the face recognition model, and this eigenvalue corresponds to the person's name. Perform face recognition on the close-up face, and identify the face set RECT3 (Rect31, Rect32, ..., Rect39) set and the corresponding personnel names (name1, name2, ..., name9). Then it can correspond to the Rect1 set, and the number No1 of Rect11 corresponds to the number No1 of Rect21, so that Rect11 can be found corresponding to Rect21 through the number, and then it can correspond to the Rect2 set.

Rect2 is a collection of Rects (rectangular areas) in the panoramic image, so that the face name name9 identified in the close-up shot corresponds to the panoramic shot.

Then, the faces in other areas of the panoramic image are recognized and integrated into the recognition results of the students in the entire classroom.

By applying an image recognition method provided by one or more embodiments of the present application, the method includes: acquiring a panoramic image and a close-up image, the panoramic image includes several objects, the close-up image includes a preset object, and the preset object is one of the objects that satisfies the preset Conditional object; compare the close-up image and the panoramic image to determine the corresponding area in the panoramic image corresponding to the close-up image, and the corresponding area includes the preset object; perform image recognition on the close-up image to determine the identification information of the preset object; based on the recognition According to the corresponding relationship between the corresponding area and the close-up image, the recognition result of the object in the corresponding area is determined. One or more embodiments of the present application obtain a panoramic image and a close-up image of a specific object from a scene, and establish a connection between the close-up image and the panoramic image, so as to use the close-up image to identify the unclearly recognized part of the panoramic image, thereby solving the problem of solving the problem. This solves the problem of blurring distant objects captured by a panoramic camera in a large scene, which is not conducive to image recognition and has a high recognition error rate.

It should be noted that, the methods of one or more embodiments of the present application may be executed by a single device, such as a computer or a server. The method in this embodiment can also be applied in a distributed scenario, and is completed by the cooperation of multiple devices. In the case of such a distributed scenario, one device among the multiple devices may only execute one or more steps in the method of one or more embodiments of the present application, and the multiple devices may perform operations on each other. interact to complete the described method.

The foregoing describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Based on the same inventive concept, one or more embodiments of the present application further provide an image recognition system, a panoramic camera, a close-up camera, and a processor; wherein,

The processor is configured to execute an image recognition method as described in any one of the above embodiments.

The systems in the foregoing embodiments are used to implement the corresponding methods in the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

Based on the same inventive concept, one or more embodiments of the present application further provide an electronic device. The electronic device includes a memory, a processor, and a computer program stored on the memory and running on the processor, and the processor implements the image recognition method described in any one of the above embodiments when the processor executes the program.

FIG. 2 shows a schematic diagram of a more specific hardware structure of an electronic device provided in this embodiment. The device may include: a processor 210 , a memory 220 , an input/output interface 230 , a communication interface 240 and a bus 250 . The processor 210 , the memory 220 , the input/output interface 230 and the communication interface 240 realize the communication connection among each other within the device through the bus 250 .

The processor 210 can be implemented by a general-purpose CPU (Central Processing Unit, central processing unit), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. program to realize the technical solutions provided by the embodiments of the present application.

The memory 220 can be implemented in the form of a ROM (Read Only Memory, read-only memory), a RAM (Random Access Memory, random access memory), a static storage device, a dynamic storage device, and the like. The memory 220 may store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of the present application through software or firmware, relevant program codes are stored in the memory 220 and invoked by the processor 210 for execution.

The input/output interface 230 is used for connecting input/output modules to realize information input and output. The input/output module can be configured in the device as a component (not shown in the figure), or can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, and the like.

The communication interface 240 is used to connect a communication module (not shown in the figure), so as to realize the communication interaction between the device and other devices. The communication module may implement communication through wired means (eg, USB, network cable, etc.), or may implement communication through wireless means (eg, mobile network, WIFI, Bluetooth, etc.).

The bus 250 includes a path to transfer information between the various components of the device (eg, the processor 210, the memory 220, the input/output interface 230, and the communication interface 240). By way of example and not limitation, the bus 250 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), Hyper Transport (HT) interconnect, Industry Standard Architecture (ISA) bus, Infiniband interconnect, Low Pin Count (LPC) bus, Memory bus, Micro Channel Architecture (MCA) bus, Peripheral components Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or two or more of these The combination. Bus 250 may include one or more buses, where appropriate. Although embodiments of this application describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

It should be noted that, although the above-mentioned device only shows the processor 210, the memory 220, the input/output interface 230, the communication interface 240 and the bus 250, in the specific implementation process, the device may also include necessary components for normal operation. other components. In addition, those skilled in the art can understand that, the above-mentioned device may only include components necessary to implement the solutions of the embodiments of the present application, rather than all the components shown in the figures.

The devices in the foregoing embodiments are used to implement the corresponding methods in the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

Based on the same inventive concept, one or more embodiments of the present application further provide a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the The computer executes an image recognition method described in any one of the embodiments above.

The computer readable medium of this embodiment includes both permanent and non-permanent, removable and non-removable media and can be implemented by any method or technology for information storage. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), suitable firmware, a plug-in, a function card, and the like. When implemented in software, elements of the present application are programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted over a transmission medium or communication link by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, etc. Wait. The code segments may be downloaded via a computer network such as the Internet, an intranet, or the like.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps may be performed in the order mentioned in the embodiment, or may be different from the order in the embodiment, or several steps may be performed simultaneously.

Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that execution of the instructions via the processor of the computer or other programmable data processing apparatus enables the Implementation of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams. Such processors may be, but are not limited to, general purpose processors, special purpose processors, application specific processors, or field programmable logic circuits. It will also be understood that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can also be implemented by special purpose hardware for performing the specified functions or actions, or by special purpose hardware and/or A combination of computer instructions is implemented.

It should be understood by those of ordinary skill in the art that the discussion of any of the above embodiments is only exemplary, and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the spirit of the present disclosure, the above embodiments or Technical features in different embodiments can also be combined, steps can be implemented in any order, and there are many other variations of the different aspects of one or more embodiments of the application as described above, which are not in detail for the sake of brevity supply.

Additionally, in order to simplify illustration and discussion, and in order not to obscure one or more embodiments of the present application, the figures provided may or may not be shown in connection with integrated circuit (IC) chips and other components. Well known power/ground connection. Furthermore, devices may be shown in block diagram form in order to avoid obscuring one or more embodiments of the present application, and this also takes into account the fact that details regarding the implementation of such block diagram devices are highly dependent on the implementation of the present application (ie, these details should be well within the purview of those skilled in the art) to which one or more embodiments are claimed. Where specific details (eg, circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that these specific details may be made without or with changes One or more embodiments of the present application are implemented below. Accordingly, these descriptions are to be regarded as illustrative rather than restrictive.

Although the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations to these embodiments will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures (eg, dynamic RAM (DRAM)) may use the discussed embodiments.

The one or more embodiments of the present application are intended to cover all such alternatives, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present application should be included within the protection scope of the present disclosure.

Claims

An image recognition method, comprising:

acquiring a panoramic image and a close-up image, the panoramic image includes several objects, and the close-up image includes a preset object; the preset object is an object that satisfies a preset condition among the several objects;

comparing the close-up image and the panoramic image, and determining a corresponding area in the panoramic image corresponding to the close-up image, where the corresponding area includes the preset object;

Perform image recognition on the close-up image to determine the identification information of the preset object;

Based on the identification information, the identification result of the object in the corresponding area is determined according to the corresponding relationship between the corresponding area and the close-up image.
The method according to claim 1, wherein the comparing the close-up image and the panoramic image to determine a corresponding area in the panoramic image corresponding to the close-up image comprises:

determining the comparison area of the close-up image and the comparison area of the panoramic image;

performing similarity comparison between the comparison area of the close-up image and the comparison area of the panoramic image;

If the similarity comparison meets the set condition, the comparison area of the panoramic image is used as the corresponding area.
The method according to claim 1, wherein the performing image recognition on the close-up image to determine the identification information of the preset object comprises:

The feature identification is performed on the close-up image, the identity information of the preset object corresponding to the close-up image is determined, and the identity information is used as the identification information.
The method according to claim 1, wherein the preset object is specifically:

Among the several objects, the distance to the acquisition position of the panoramic image is greater than a preset threshold.
The method according to claim 1, wherein the preset object is specifically:

Among the several objects, the distance to the focus area of the panoramic image is greater than a preset threshold.
The method according to claim 1, wherein the preset object is specifically:

Among the several objects, an object whose definition is smaller than a preset threshold in the panoramic image.
The method according to any one of claims 1-6, wherein the panoramic image and the close-up image are acquired within the same period of time.
An image recognition system, comprising: a panoramic camera, a close-up camera and a processor; wherein,

the panoramic camera, configured to capture a panoramic image, the panoramic image including several objects;

the close-up camera is configured to collect a close-up image, the close-up image includes a preset object, and the preset object is an object that satisfies a preset condition among the several objects;

The processor, configured to perform the method of any one of claims 1 to 7.
An electronic device includes a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method according to any one of claims 1 to 7 when the processor executes the program.
A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 7.