CN115471416A - Object recognition method, storage medium, and apparatus - Google Patents
Object recognition method, storage medium, and apparatus Download PDFInfo
- Publication number
- CN115471416A CN115471416A CN202211047463.4A CN202211047463A CN115471416A CN 115471416 A CN115471416 A CN 115471416A CN 202211047463 A CN202211047463 A CN 202211047463A CN 115471416 A CN115471416 A CN 115471416A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- identification
- marker
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 239000003550 marker Substances 0.000 claims abstract description 113
- 230000003287 optical effect Effects 0.000 claims abstract description 66
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 2
- 239000011521 glass Substances 0.000 description 5
- 239000000047 product Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 210000000245 forearm Anatomy 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 206010004950 Birth mark Diseases 0.000 description 1
- 208000032544 Cicatrix Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 230000037387 scars Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10052—Images from lightfield camera
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The application provides a target identification method, a storage medium and a device, wherein the target identification method comprises the following steps: acquiring a first optical image and a first depth image containing a target to be recognized, wherein the first depth image is an image containing distance information of the target to be recognized; extracting a first marker image containing a first identification marker from the first optical image, and correcting the characteristic parameters of the first identification marker in the first marker image according to the first depth image; extracting a target identification parameter of the first identification marker based on the corrected first marker image; and comparing the target identification parameters with prestored target authentication parameters to generate a target identification result, and combining the optical image with the TOF depth image to realize identification of different target person identities and identification of specific scenes.
Description
Technical Field
The present application relates to a target recognition method, and in particular, to a target recognition method, a storage medium, and a device, which belong to the technical field of image analysis.
Background
At present, along with popularization and development of wearable devices such as AR (Augmented Reality), VR (Virtual Reality), smart watches and the like or related electronic devices, identity recognition methods of users are continuously updated, and face recognition schemes of mobile phones in the prior art are relatively popularized, but wearable devices such as AR glasses and VR glasses can only be worn on the head, and cannot realize comprehensive scanning of face biological information by the devices like mobile phones.
However, as the application demand of users for various wearable electronic devices increases, identification of identities and scenes is very important, but in the existing image identification method, when identification is performed based on one image acquired by the device itself, the information provided by the image is limited, which results in low accuracy and reliability of operations such as identity identification.
Therefore, how to solve the defects that the accuracy and reliability of target identification cannot be improved by combining multiple kinds of image information in the prior art becomes a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present application aims to provide a target recognition method, a storage medium and a device, which are used for solving the problem that the prior art cannot combine various image information to improve the accuracy and reliability of target recognition.
To achieve the above and other related objects, an aspect of the present application provides a target recognition method, including: respectively acquiring a first optical image and a first depth image containing a target to be recognized, wherein the first depth image is an image containing distance information of the target to be recognized; extracting a first marker image containing a first identification marker from the first optical image, and correcting the characteristic parameters of the first identification marker in the first marker image according to the first depth image, wherein the first identification marker comprises a first part of the target to be identified; extracting a target identification parameter of the first identification marker based on the corrected first marker image; and comparing the target identification parameters with prestored target authentication parameters to generate a target identification result.
In an embodiment of the present application, the step of extracting a first marker image including a first identification marker from the first optical image includes: and inputting the first optical image to a pre-trained marker image model, and acquiring an image containing a first part of the target to be recognized as the first marker image.
In an embodiment of the application, the step of correcting the feature parameter of the first identification marker in the first marker image according to the first depth image includes: determining, from the first depth image, a characteristic parameter of the first location in the first marker image as a first distance; acquiring a second depth image of the same first part of the target to be recognized in a feature recognition library, and correcting a first distance in the first marker image into a second distance corresponding to the second image; wherein the first distance is distance information of the first location in the first depth image, and the second distance is distance information of the first location in the second depth image.
In an embodiment of the application, the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result includes: responding to the target identification parameter is consistent with a prestored target authentication parameter, and the target identification result is that target identification is successful; responding to the fact that the target identification parameters do not accord with prestored target authentication parameters, and enabling the target identification result to be target identification failure; wherein the target recognition result comprises an identity recognition result.
In an embodiment of the present application, the target identification parameter includes a biometric parameter of the target to be identified; the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result includes: responding to the biological characteristic parameters to accord with the pre-stored biological characteristic parameters, and judging that the target identification result is successful; and responding to the fact that the biological characteristic parameters do not accord with the pre-stored biological characteristic parameters, and determining that the target identification result is target identification failure.
In an embodiment of the present application, the target recognition parameters further include a posture characteristic parameter of the target to be recognized; the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result includes: responding to the biological characteristic parameters and the posture characteristic parameters, wherein the biological characteristic parameters and the posture characteristic parameters are consistent, and the target recognition result is successful; and responding to the fact that the biological characteristic parameters do not accord with the pre-stored biological characteristic parameters or the gesture characteristic parameters do not accord with the pre-stored gesture characteristic parameters, and determining that the target recognition result is target recognition failure.
In an embodiment of the present application, the method further includes: extracting a second marker image containing a second identification marker from the first optical image, and correcting the characteristic parameters of the second identification marker in the second marker image according to the first depth image, wherein the second identification marker comprises a first article associated with the target to be identified or a second article associated with the scene; extracting a target identification parameter of the second identification marker based on the corrected second marker image; and comparing the target identification parameters of the first identification marker and the second identification marker with prestored target authentication parameters to generate a target identification result.
In an embodiment of the application, the target identification parameters of the second identification marker are a material object characteristic parameter and a posture characteristic parameter.
In an embodiment of the present application, before the step of extracting the first identification marker from the first optical image, the method further comprises: pre-processing the first optical image and the first depth image, the pre-processing comprising at least: and carrying out image fusion and denoising treatment on the first optical image and the first depth image.
To achieve the above and other related objects, another aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the object recognition method.
To achieve the above and other related objects, a further aspect of the present application provides an electronic device including: a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored by the memory so as to enable the electronic equipment to execute the target identification method.
To achieve the above and other related objects, a last aspect of the present application provides an intelligent wearable device, which includes: the optical camera is used for collecting an optical image containing a test target; the depth camera is used for acquiring a depth image containing a test target; one or more processors in communication with the optical camera, the depth camera; and a memory configured to store instructions that, when executed by the one or more processors, cause the one or more processors to perform steps comprising: respectively acquiring a first optical image and a first depth image containing a target to be recognized, wherein the first depth image is an image containing distance information of the target to be recognized; extracting a first marker image containing a first identification marker from the first optical image, and correcting the characteristic parameters of the first identification marker in the first marker image according to the first depth image, wherein the first identification marker comprises a first part of the target to be identified; extracting a target identification parameter of the first identification marker based on the corrected first marker image; and comparing the target identification parameters with prestored target authentication parameters to generate a target identification result.
As described above, the object recognition method, the storage medium, and the device according to the present application have the following advantages:
the method is based on the fact that a TOF camera (Time of Flight, depth camera) is combined with an optical camera to collect static images or multi-frame dynamic images, data processing and recognition are conducted, and recognition of the identity of a device wearer or a user is achieved. Can be applied to wearable equipment such as AR, VR, all have application prospect in many fields such as intelligent house, intelligent transportation, auxiliary driving.
The TOF camera can provide distance data in the application, and can be used as powerful supplement of image data of a traditional optical camera. TOF camera combines the optical camera of high resolution, both can realize the measurement of target object size through the TOF camera, also can acquire more target object details through the optical camera, and this application combines together both, provides a method to the nimble identification and the scene recognition of equipment such as wearable.
The application can realize non-contact identification; the biological characteristics are combined with gesture characteristics such as gestures, so that the accuracy and robustness of recognition are improved; each identification characteristic can be flexibly set, and the playability is high.
Drawings
Fig. 1 is a schematic flow chart illustrating a target identification method according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating a calibration procedure of the target identification method according to an embodiment of the present disclosure.
Fig. 3 is a calibration diagram of the target identification method according to an embodiment of the present disclosure.
Fig. 4 is a comparison identification flowchart of the target identification method according to an embodiment of the present disclosure.
Fig. 5 is a flowchart illustrating a target recognition method according to an embodiment of the present disclosure.
Fig. 6 is a schematic structural connection diagram of an electronic device according to an embodiment of the present disclosure.
Description of the element reference
6. Electronic device
61. Processor with a memory having a plurality of memory cells
62. Memory device
S11 to S14
S121 to S123
S141 to S142
S51 to S55
Detailed Description
The following embodiments of the present application are described by specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure of the present application. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It should be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present application, and the drawings only show the components related to the present application and are not drawn according to the number, shape and size of the components in actual implementation, the type, quantity and proportion of each component in actual implementation may be changed freely, and the layout of the components may be more complicated.
The target identification method, the storage medium and the device can combine the optical image and the TOF depth image to realize identification of different target person identities and identification of specific scenes. Further, this application can realize the identification of the person of wearing according to intelligent wearing equipment person's biological feature or gesture feature on the one hand, and on the other hand can realize the discernment of any electronic equipment to specific scene.
The target identification method provided by the embodiment of the application can be applied to electronic devices, and the electronic devices include, but are not limited to, a mobile phone, an intelligent wearable device, a vehicle-mounted device, an Augmented Reality (AR)/Virtual Reality (VR) device, a notebook computer, a super-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), a smart speaker, a Set Top Box (STB), a television, or the like. The embodiment of the application does not set any limit to the specific type of the electronic device.
The principle and implementation of a target identification method, a storage medium and an apparatus of the present embodiment will be described in detail below with reference to fig. 1 to 6, so that those skilled in the art can understand the target identification method, the storage medium and the apparatus of the present embodiment without creative efforts.
Please refer to fig. 1, which is a schematic flow chart illustrating a target identification method according to an embodiment of the present application. As shown in fig. 1, the target identification method specifically includes the following steps:
s11, respectively obtaining a first optical image and a first depth image containing the target to be recognized, wherein the first depth image is an image depth image containing the distance information of the target to be recognized.
In particular, the optical image may be a still image or a moving image of a plurality of frames. The depth image may be a still image or a moving image of a plurality of frames. The identification is carried out by utilizing the dynamic images of multiple frames, and the accuracy is higher.
S12, extracting a first marker image containing a first identification marker from the first optical image, and correcting the characteristic parameters of the first identification marker in the first marker image according to the first depth image, wherein the first identification marker comprises a first part optical image depth image of the target to be identified.
In one embodiment, the identification marker includes a body part of the target person or an object associated with the identity or scene. In particular, the identification marker may be a part of the body of the user of the device, such as a body part of a hand, arm or leg, or a specific object, such as a pen container in an office, a pen in a hand, etc. The characteristics represented by the body part of the target person can be used for identifying the identity of a person, the characteristics represented by the object associated with the identity can be used for identifying the identity of the person, and the characteristics represented by the object associated with the scene can be used for identifying a specific scene.
Please refer to fig. 2, which illustrates a calibration flowchart of the target recognition method of the present application in an embodiment. As shown in fig. 2, S12 specifically includes the following steps:
and S121, inputting the first optical image to a pre-trained marker image model, and acquiring an image of a first part containing the target to be recognized as the first marker image. Specifically, the optical image is input to a pre-trained marker image model, and the identification marker is determined to be at least one of a target body part, an identity-related item, or a scene-related item, in one embodiment, the target body part image is a palm image.
And S122, determining the characteristic parameter of the first position in the first marker image as a first distance depth image according to the first depth image.
S123, acquiring a second depth image of the same first part of the target to be recognized in a feature recognition library, and correcting the first distance in the first marker image into a second distance corresponding to the second image; wherein the first distance is distance information of the first location in the first depth image, and the second distance is distance information of the first location in the second depth image. Specifically, according to the same palm image, correcting the first distance into a second distance corresponding to the palm image in a feature recognition library; the first distance and the second distance are distances between a shooting point of the intelligent wearable device for acquiring the palm image and the palm of the wearer of the intelligent wearable device.
Please refer to fig. 3, which is a schematic calibration diagram of the target identification method according to an embodiment of the present application. As shown in fig. 3, an example of simple optical image data conversion is presented, the hand gesture stored in the device feature recognition library is a palm image obtained by a device user at a distance of 50cm, and the palm image is vertical, while the hand gesture obtained in the recognition process is a palm image at a distance of 70cm, and meanwhile, a certain inclination exists in the palm image, and the palm image at a distance of 70cm is corrected to be a 50cm image by geometric principles such as cosine theorem.
In another embodiment, step S12 may also be performed by first correcting the feature parameters of the identification marker according to the depth image, and then extracting the identification marker from the optical image.
And S13, extracting a target identification parameter of the first identification marker based on the corrected first marker image.
S14, comparing the target identification parameters with prestored target authentication parameters to generate target identification results; wherein the target recognition result comprises an identity recognition result.
Please refer to fig. 4, which is a flowchart illustrating a comparison and recognition process of the target recognition method according to an embodiment of the present application. As shown in fig. 4, S14 specifically includes the following steps:
and S141, responding to the target identification parameter being consistent with the pre-stored target authentication parameter, wherein the target identification result is successful target identification.
S142, responding to the fact that the target identification parameters are not consistent with pre-stored target authentication parameters, and determining that the target identification result is target identification failure; the target recognition result comprises an identity recognition result and/or a scene recognition result.
Specifically, for example, the length errors of the five fingers are set to be within 2mm, and when the length errors of the five fingers in the target identification parameters are within 2mm, the target identification of the five fingers is successful; when one or more fingers have length errors exceeding 2mm, the target recognition of five fingers fails. The threshold range within 2mm is generally set according to the resolution of TOF hardware, and the threshold range is smaller as hardware equipment is better.
In one embodiment, the target identification parameters include biometric parameters of the target to be identified; the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result includes:
responding to the biological characteristic parameters to accord with the pre-stored biological characteristic parameters, and judging that the target identification result is successful; and responding to the fact that the biological characteristic parameters do not accord with the pre-stored biological characteristic parameters, and the target identification result is target identification failure.
Specifically, the biometric parameters of the target person may be physical parameters of the user's body, such as the length of five fingers, the length of index finger knuckles, the width of fingers, arms, the location of specific moles or scars on the arms, the length of the arm forearm, characteristics of palm prints, and birthmarks of specific sizes, etc.; the biometric parameters of a specific object are also physical characteristic parameters, such as the size, shape, etc. of the object.
In another embodiment, the target recognition parameters further include a posture characteristic parameter of the target to be recognized; the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result comprises the following steps:
responding to the biological characteristic parameters and the posture characteristic parameters, wherein the biological characteristic parameters and the posture characteristic parameters are consistent, and the target recognition result is successful; and responding to the fact that the biological characteristic parameters do not accord with the prestored biological characteristic parameters or the gesture characteristic parameters do not accord with the prestored gesture characteristic parameters, wherein the target identification result is target identification failure.
Specifically, the posture characteristic parameter of the target person may be a specific posture presented by the body of the user in the recognition process, such as an included angle between the palm and the forearm after being supported, an OK gesture performed by left hand, a cross arm chest holding of two arms, and the like; the posture characteristic parameters of the specific object can be the placing position, the distance from a background wall and the like.
In one embodiment, the method further comprises: extracting a second marker image containing a second identification marker from the first optical image, and correcting the characteristic parameters of the second identification marker in the second marker image according to the first depth image, wherein the second identification marker comprises a first article associated with the target to be identified or a second article associated with the scene; extracting a target identification parameter of the second identification marker based on the corrected second marker image; and comparing the target identification parameters of the first identification marker and the second identification marker with pre-stored target authentication parameters to generate a target identification result.
In an embodiment, the target identification parameters of the second identification marker are a real object characteristic parameter and a posture characteristic parameter.
In another embodiment, the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result includes:
and responding to the condition that at least two target identification parameters are consistent with the prestored target authentication parameters, wherein the target identification result is successful target identification.
Specifically, in order to further improve the accuracy of identification, for identity identification or scene identification, more than two biological characteristic parameters may be used for identification, more than two posture characteristic parameters may be used for identification, or one or more biological characteristic parameters and one or more posture characteristic parameters may be combined for identification. Therefore, the identification accuracy is improved by increasing the identification complexity. Such as identifying the hand characteristics of the user of the device plus a pen specific to that user in the study, etc.
For scene recognition, for example: 1. a specific picture is hung in a conference room scene or a cabinet is placed in the conference room scene, and after the electronic device used by the user executes the target identification method, for example, after scanning, the current scene is identified as the conference room scene, and the conference under the scene is automatically accessed. 2. In an exhibition scene, after the electronic device used by the user executes the target identification method, for example, after a specific product is scanned, the related product information corresponding to the exhibition scene is identified, and further, the exchange between the personal information and the manufacturer information of the exhibition product is completed through the presented interface. 3. In an off-vehicle scene of a certain user, after the electronic device used by the user executes the target identification method, for example, a specific pendant in the vehicle is scanned from the outside of the vehicle, the vehicle is identified as the user vehicle, and thus the vehicle or other specific functions are remotely activated or closed. 4. In an in-car scene of a certain user, after the electronic device used by the user executes the target identification method, for example, a specific hanging piece in the car is scanned from the outside of the car, the call function of the AR glasses is closed, and the call function is switched to the in-car device.
Furthermore, through an external human-computer interaction interface set or presented by a software program, different mark identifiers and characteristic parameters can be flexibly set so as to limit a user and a use scene. For example, a dialog box presented through a human-machine interface. In practical application, for the biometric parameters, a plurality of biometric parameters form a biometric parameter list, and a plurality of posture characteristic parameters form a posture characteristic parameter list. The biometric parameters and the gesture parameters may be automatically configured through active guidance, for example, a list of biometric parameters is presented for selection by the user, or may be set by the user, for example, the user may create a new gesture.
In an embodiment, after step S11 and before step S12, the method for identifying an object further includes:
pre-processing the first optical image and the first depth image, the pre-processing comprising at least: and carrying out image fusion and denoising treatment on the first optical image and the first depth image. Optical image depth image optical image depth image wherein image fusion refers to associating distance data of the depth image on the optical image to increase the optical image portion data dimension.
Please refer to fig. 5, which is a flowchart illustrating a target recognition method according to an embodiment of the present application. As shown in fig. 5, the whole process of object recognition includes: and S51, inputting data of the optical camera and the TOF camera, and performing preprocessing such as image fusion. S52, image data (optical image and TOF image data) of the identification marker is extracted. And S53, identifying the optical image of the marker for correction according to the TOF camera data. And S54, extracting the biological characteristic parameters and the posture characteristic parameters of the characteristic markers from the corrected identification marker images. S55, comparing the biological characteristic parameters and the posture characteristic parameters with identity authentication information stored in the equipment, and if the biological characteristic parameters and the posture characteristic parameters are in accordance with the identity authentication information stored in the equipment, judging that the identity identification is successful; and if the biological characteristic parameters and the posture characteristic parameters do not accord with the identity authentication information stored in the equipment, judging that the identity recognition fails.
The protection scope of the object recognition method described in this application is not limited to the execution sequence of the steps listed in this embodiment, and all the solutions implemented by adding, subtracting, and replacing steps in the prior art according to the principles of this application are included in the protection scope of this application.
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the object recognition method.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned computer-readable storage medium comprises: various computer storage media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Please refer to fig. 6, which is a schematic structural connection diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the present embodiment provides an electronic device 6, which specifically includes: a processor 61 and a memory 62; the memory 62 is configured to store a computer program, and the processor 61 is configured to execute the computer program stored in the memory 62, so as to enable the electronic device 6 to execute the steps of the object recognition method. The target identification method comprises the following steps: respectively acquiring an optical image and a depth image containing a test target, wherein the depth image is an image containing distance information of the test target; extracting an identification marker from an optical image, and correcting the characteristic parameter of the identification marker according to the depth image; extracting target identification parameters of the identification marker based on the corrected identification marker; and comparing the target identification parameters with prestored target authentication parameters to generate a target identification result.
The Processor 61 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware component.
The Memory 62 may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
In practical applications, the electronic device may be a computer including all or a portion of the components of memory, a memory controller, one or more processing units (CPUs), peripheral interfaces, RF circuits, audio circuits, speakers, microphones, input/output (I/O) subsystems, a display screen, other output or control devices, and external ports; the computer includes, but is not limited to, a Personal computer such as a desktop computer, a notebook computer, a tablet computer, a smart phone, a smart television, a Personal Digital Assistant (PDA), and the like, and the electronic device may also be a vehicle end. In other embodiments, the electronic device may also be a server, where the server may be arranged on one or more entity servers according to various factors such as functions and loads, or may be a cloud server formed by a distributed or centralized server cluster, which is not limited in this embodiment.
This application intelligent wearing equipment include:
the optical camera is used for collecting an optical image containing a test target;
the depth camera is used for acquiring a depth image containing a test target;
one or more processors in communication with the optical camera, the depth camera; and a memory configured to store instructions that, when executed by the one or more processors, cause the one or more processors to perform steps comprising:
respectively acquiring a first optical image and a first depth image containing a target to be recognized, wherein the first depth image is an image containing distance information of the target to be recognized;
extracting a first marker image containing a first identification marker from the first optical image, and correcting the characteristic parameters of the first identification marker in the first marker image according to the first depth image, wherein the first identification marker comprises a first part of the target to be identified;
extracting a target identification parameter of the first identification marker based on the corrected first marker image;
and comparing the target identification parameters with prestored target authentication parameters to generate a target identification result. Depth image optical image depth image
This application is preferred, can be applied to and carry out identification and scene recognition on AR/VR class intelligent glasses product, intelligent wrist-watch and other intelligence wearing equipment, and AR class product can all match AR class equipment and use at intelligent house, wisdom traffic, supplementary driving, and the object for appreciation nature is high. For example, in the aspect of intelligent home, the AR is used for recognizing objects in a family, and after the family arrives, the specific gesture can be recognized through the AR to start the furniture equipment; in the aspect of intelligent traffic, the AR is utilized to browse traffic information; and the driver wears AR glasses to carry out navigation and the like in the aspect of driving assistance. Thus, compared with the identification of fingerprints, through the optical camera and the TOF camera, the device is touched each time when identification is not needed.
In summary, the target identification method, the storage medium and the device of the present application collect a static image or a multi-frame dynamic image based on a TOF camera in combination with an optical camera, perform data processing and identification, and realize identification of a device wearer or a user identity. Can be applied to wearable equipment such as AR, VR, all have application prospect in many fields such as intelligent house, intelligent transportation, auxiliary driving. The TOF camera can provide distance data in the application, and can be used as powerful supplement of image data of a traditional optical camera. TOF camera combines the optical camera of high resolution, both can realize the measurement of target object size through the TOF camera, also can acquire more target object details through the optical camera, and this application combines together both, provides a method to the nimble identification and the scene recognition of equipment such as wearable. The application can realize non-contact identification; the biological characteristics are combined with gesture characteristics such as gestures, so that the accuracy and robustness of recognition are improved; each identification characteristic can be flexibly set, and the playability is high. The application effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the present application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which may be made by those skilled in the art without departing from the spirit and technical spirit of the present disclosure be covered by the claims of the present application.
Claims (12)
1. A method of object recognition, the method comprising:
respectively acquiring a first optical image and a first depth image containing a target to be recognized, wherein the first depth image is an image containing distance information of the target to be recognized;
extracting a first marker image containing a first identification marker from the first optical image, and correcting the characteristic parameters of the first identification marker in the first marker image according to the first depth image, wherein the first identification marker comprises a first part of the target to be identified;
extracting a target identification parameter of the first identification marker based on the corrected first marker image;
and comparing the target identification parameters with prestored target authentication parameters to generate a target identification result.
2. The object recognition method according to claim 1, characterized in that; said step of extracting from said first optical image a first marker image comprising a first identifying marker, comprising:
and inputting the first optical image to a pre-trained marker image model, and acquiring an image containing a first part of the target to be recognized as the first marker image.
3. The object recognition method according to claim 2, wherein the step of correcting the feature parameter of the first recognition marker in the first marker image according to the first depth image comprises:
determining, from the first depth image, a characteristic parameter of the first location in the first marker image as a first distance;
acquiring a second depth image of the same first part of the target to be recognized in a feature recognition library, and correcting a first distance in the first marker image into a second distance corresponding to the second image;
the first distance refers to distance information of the first position in the first depth image, and the second distance refers to distance information of the first position in the second depth image.
4. The target identification method according to claim 1, wherein the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result comprises:
responding to the target identification parameter is consistent with a prestored target authentication parameter, and the target identification result is that target identification is successful;
responding to the fact that the target identification parameters are not accordant with prestored target authentication parameters, and determining that the target identification result is target identification failure;
wherein the target recognition result comprises an identity recognition result.
5. The object recognition method according to claim 4, wherein the object recognition parameters include biometric parameters of the object to be recognized; the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result includes:
responding to the biological characteristic parameters to accord with the pre-stored biological characteristic parameters, and judging that the target identification result is successful;
and responding to the fact that the biological characteristic parameters do not accord with the pre-stored biological characteristic parameters, and the target identification result is target identification failure.
6. The target recognition method according to claim 5, wherein the target recognition parameters further include a posture characteristic parameter of the target to be recognized; the step of comparing the target identification parameter with a pre-stored target authentication parameter to generate a target identification result includes:
responding to the biological characteristic parameters and the posture characteristic parameters, wherein the biological characteristic parameters and the posture characteristic parameters are consistent, and the target recognition result is successful;
and responding to the fact that the biological characteristic parameters do not accord with the pre-stored biological characteristic parameters or the gesture characteristic parameters do not accord with the pre-stored gesture characteristic parameters, and determining that the target recognition result is target recognition failure.
7. The object recognition method of claim 1, further comprising:
extracting a second marker image containing a second identification marker from the first optical image, and correcting the characteristic parameters of the second identification marker in the second marker image according to the first depth image, wherein the second identification marker comprises a first article associated with the target to be identified or a second article associated with the scene;
extracting a target identification parameter of the second identification marker based on the corrected second marker image;
and comparing the target identification parameters of the first identification marker and the second identification marker with pre-stored target authentication parameters to generate a target identification result.
8. The target recognition method of claim 7, wherein the target recognition parameters of the second recognition marker are a material object characteristic parameter and a posture characteristic parameter.
9. The object recognition method of claim 1, wherein prior to the step of extracting a first identifying marker from the first optical image, the method further comprises:
pre-processing the first optical image and the first depth image, the pre-processing comprising at least: and carrying out image fusion and denoising treatment on the first optical image and the first depth image.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the object recognition method of any one of claims 1 to 9.
11. An electronic device, comprising: a processor and a memory;
the memory is configured to store a computer program, and the processor is configured to execute the computer program stored by the memory to cause the electronic device to perform the object recognition method according to any one of claims 1 to 9.
12. The utility model provides an intelligence wearing equipment which characterized in that, intelligence wearing equipment includes:
the optical camera is used for collecting an optical image containing a test target;
the depth camera is used for collecting a depth image containing a test target;
one or more processors in communication with the optical camera, the depth camera; and a memory configured to store instructions that, when executed by the one or more processors, cause the one or more processors to perform steps comprising:
respectively acquiring a first optical image and a first depth image containing a target to be recognized, wherein the first depth image is an image containing distance information of the target to be recognized;
extracting a first marker image containing a first identification marker from the first optical image, and correcting the characteristic parameters of the first identification marker in the first marker image according to the first depth image, wherein the first identification marker comprises a first part of the target to be identified;
extracting a target identification parameter of the first identification marker based on the corrected first marker image;
and comparing the target identification parameters with prestored target authentication parameters to generate a target identification result.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211047463.4A CN115471416A (en) | 2022-08-29 | 2022-08-29 | Object recognition method, storage medium, and apparatus |
| PCT/CN2022/143573 WO2024045454A1 (en) | 2022-08-29 | 2022-12-29 | Target identification method, storage medium and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211047463.4A CN115471416A (en) | 2022-08-29 | 2022-08-29 | Object recognition method, storage medium, and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115471416A true CN115471416A (en) | 2022-12-13 |
Family
ID=84369225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211047463.4A Pending CN115471416A (en) | 2022-08-29 | 2022-08-29 | Object recognition method, storage medium, and apparatus |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115471416A (en) |
| WO (1) | WO2024045454A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024045454A1 (en) * | 2022-08-29 | 2024-03-07 | 湖北星纪魅族科技有限公司 | Target identification method, storage medium and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764180A (en) * | 2018-05-31 | 2018-11-06 | Oppo广东移动通信有限公司 | Face identification method, device, electronic equipment and readable storage medium storing program for executing |
| CN109241890B (en) * | 2018-08-24 | 2020-01-14 | 北京字节跳动网络技术有限公司 | Face image correction method, apparatus and storage medium |
| JP6631736B1 (en) * | 2019-03-07 | 2020-01-15 | 富士通クライアントコンピューティング株式会社 | Biometric authentication device, biometric authentication system and program |
| CN111325691B (en) * | 2020-02-20 | 2023-11-10 | Oppo广东移动通信有限公司 | Image correction method, apparatus, electronic device, and computer-readable storage medium |
| CN113420700B (en) * | 2021-07-02 | 2022-10-25 | 支付宝(杭州)信息技术有限公司 | Palm biological characteristic acquisition device and method |
| CN115471416A (en) * | 2022-08-29 | 2022-12-13 | 湖北星纪时代科技有限公司 | Object recognition method, storage medium, and apparatus |
-
2022
- 2022-08-29 CN CN202211047463.4A patent/CN115471416A/en active Pending
- 2022-12-29 WO PCT/CN2022/143573 patent/WO2024045454A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024045454A1 (en) * | 2022-08-29 | 2024-03-07 | 湖北星纪魅族科技有限公司 | Target identification method, storage medium and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024045454A1 (en) | 2024-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102606785B1 (en) | Systems and methods for simultaneous localization and mapping | |
| US10679146B2 (en) | Touch classification | |
| CN109584276B (en) | Key point detection method, device, equipment and readable medium | |
| CN109947886B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| US9990557B2 (en) | Region selection for image match | |
| KR20200111617A (en) | Gesture recognition method, device, electronic device, and storage medium | |
| CN110986969B (en) | Map fusion method and device, equipment and storage medium | |
| CN112506340B (en) | Equipment control method, device, electronic equipment and storage medium | |
| CN103679788B (en) | The generation method and device of 3D rendering in a kind of mobile terminal | |
| WO2021097750A1 (en) | Human body posture recognition method and apparatus, storage medium, and electronic device | |
| CN108830787A (en) | The method, apparatus and electronic equipment of anamorphose | |
| JP2023549240A (en) | Image generation method, image generation device, computer equipment, and computer program | |
| WO2019174398A1 (en) | Method, apparatus, and terminal for simulating mouse operation by using gesture | |
| US20140232748A1 (en) | Device, method and computer readable recording medium for operating the same | |
| US11461921B2 (en) | Program, system, electronic device, and method for recognizing three-dimensional object | |
| CN107944381A (en) | Face tracking method, device, terminal and storage medium | |
| CN111199169A (en) | Image processing method and device | |
| CN115471416A (en) | Object recognition method, storage medium, and apparatus | |
| CN109147001A (en) | A kind of method and apparatus of nail virtual for rendering | |
| CN112766406A (en) | Article image processing method and device, computer equipment and storage medium | |
| Ueng et al. | Vision based multi-user human computer interaction | |
| Chen et al. | Static hand gesture recognition based on finger root-center-angle and length weighted mahalanobis distance | |
| CN110069126B (en) | Virtual object control method and device | |
| JP2015032256A (en) | Image processing device and database construction device therefor | |
| WO2023273227A1 (en) | Fingernail recognition method and apparatus, device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: No. B1337, Chuanggu Initiation Zone, Taizihu Cultural Digital Creative Industry Park, No. 18 Shenlong Avenue, Wuhan Economic and Technological Development Zone, Wuhan, Hubei Province, 430058 Applicant after: Hubei Xingji Meizu Technology Co.,Ltd. Address before: No. B1337, Chuanggu Start-up Zone, Taizi Lake Cultural Digital Creative Industry Park, No. 18 Shenlong Avenue, Wuhan Economic and Technological Development Zone, Wuhan City, Hubei Province 430000 Applicant before: Hubei Xingji times Technology Co.,Ltd. |
|
| CB02 | Change of applicant information |