CN112307985A - Image identification method, system, electronic equipment and storage medium - Google Patents
Image identification method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112307985A CN112307985A CN202011205359.4A CN202011205359A CN112307985A CN 112307985 A CN112307985 A CN 112307985A CN 202011205359 A CN202011205359 A CN 202011205359A CN 112307985 A CN112307985 A CN 112307985A
- Authority
- CN
- China
- Prior art keywords
- image
- processed
- moving target
- tracking
- radar
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Image Analysis (AREA)
Abstract
One or more embodiments of the present specification provide an image recognition method, system, electronic device, and storage medium, including: acquiring a first image to be processed, wherein the first image to be processed is one of tracking images obtained by positioning and capturing a moving target by an image capturing device through a tracking radar; carrying out similarity judgment on the first image to be processed; if not, acquiring a second image to be processed from the tracking image, and judging the similarity of the second image to be processed, wherein the second image to be processed meets the definition condition; and if so, determining the identification result according to the judgment result. One or more embodiments of the present disclosure accurately position and accurately distinguish a target by a tracking radar, so that an image capturing device may shoot the target multiple times, and thus may perform image recognition on the same target through multiple pictures, thereby avoiding a situation where a single picture is blurred and cannot be recognized, improving accuracy of image detection of a moving target, and improving tracking continuity of the target.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of image recognition technologies, and in particular, to an image recognition method, an image recognition system, an electronic device, and a storage medium.
Background
With the development of modern imaging technology, image recognition technology has become popular and is flooded in every corner of life. The purpose is mainly to determine the identity of the object image or the object displayed in the object area more accurately and quickly in various fields, such as: face recognition, contraband recognition, and the like.
However, the prior art has a plurality of problems in the field of image recognition. Taking face recognition as an example, the face recognition process depends on the quality of the acquired image to a great extent, all samples of the algorithm are from the image, and the image is difficult to recognize if the image is blurred or the position is shifted. In the prior art, face recognition and tracking generally have good recognition performance under a controllable condition, but in a mobile environment, a face image is more obviously influenced by factors such as ambient illumination, expressions, postures, local shielding and the like. Tracking fails when the human face changes greatly, and therefore, applying the face recognition technology to a mobile environment still faces many problems and challenges.
Disclosure of Invention
In view of the above, an object of one or more embodiments of the present disclosure is to provide an image recognition method, an image recognition system, an electronic device, and a storage medium, so as to solve the problems of inaccurate recognition and failed recognition when a position of a target image changes.
In view of the above, one or more embodiments of the present specification provide an image recognition method applied to a processor, including:
acquiring a first image to be processed, wherein the first image to be processed contains a moving target, and the first image to be processed is any one of a plurality of tracking images obtained by continuously positioning and capturing the moving target by an image capturing device based on a tracking radar;
judging whether the first image to be processed is similar to any image in a preset image library or not;
if the first image to be processed is not similar to any image in the preset image library, acquiring a second image to be processed from the plurality of tracking images, and judging whether the second image to be processed is similar to any image in the preset image library or not, wherein the second image to be processed meets a preset definition condition;
and determining the identification result of the moving target according to the judgment result of whether the second image to be processed is similar to any image in the preset image library.
In some embodiments, before determining whether the first image to be processed is similar to any image in a preset image library, the method includes:
detecting the definition of the first image to be processed;
and if the definition does not reach a preset threshold value, executing the step of obtaining a second image to be processed from the plurality of tracking images.
In some embodiments, the determining, according to a determination result of whether the second image to be processed is similar to any image in the preset image library, an identification result of the moving target includes:
if the second image to be processed is not similar to any image in the preset image library, sending a first instruction to the tracking radar, and/or sending a second instruction to the image capturing device, so that the tracking radar improves the positioning frequency of the moving target according to the first instruction, and the image capturing device improves the image capturing frequency of the moving target according to the second instruction.
In some embodiments, the acquiring a first to-be-processed image, the first to-be-processed image including a moving target, the first to-be-processed image being any one of a plurality of tracking images captured by an image capturing device based on continuous positioning of the moving target by a tracking radar, includes:
judging whether the number of the tracking images meets a preset number threshold value or not;
and if so, selecting any one of the tracking images as the first image to be processed.
Based on the same concept, one or more embodiments of the present specification further provide an image recognition method applied to a tracking radar, including:
continuously positioning a moving target to generate positioning information;
sending the positioning information to an image capturing device, enabling the image capturing device to obtain the image of the moving target according to the positioning information, and generating a plurality of tracking images; enabling a processor to select one of the plurality of tracking images as a first image to be processed and causing the processor to perform the method according to any one of claims 1 to 4.
In some embodiments, the continuously positioning the moving object and generating the positioning information includes:
scanning a target area to generate a radar coordinate system corresponding to the target area;
when the moving target is identified in the target area, marking the moving target to generate a target identifier;
and generating the positioning information according to the target identification and the position coordinates of the moving target in the radar coordinate system.
Based on the same concept, one or more embodiments of the present specification further provide an image recognition method applied to an image capturing apparatus, including:
acquiring positioning information of a moving target sent by a tracking radar;
acquiring an image of a moving target according to the positioning information, and generating a plurality of tracking images; enabling a processor to select one of the plurality of tracking images as a first image to be processed and causing the processor to perform the method according to any one of claims 1 to 4.
In some embodiments, the positioning information comprises: reflecting the position coordinates of the position of the moving target and the target identification corresponding to the moving target;
the obtaining of the image of the moving target according to the positioning information and the generation of a plurality of tracking images comprise:
converting the position coordinates between a radar coordinate system and a capturing coordinate system to generate conversion coordinates in the capturing coordinate system, wherein the radar coordinate system corresponds to the tracking radar, and the capturing coordinate system corresponds to the image capturing equipment;
and capturing an image according to the converted coordinates, and binding the captured image with the target identifier to generate the tracking image.
In some embodiments, the obtaining an image of a moving target according to the positioning information and generating a plurality of tracking images includes:
acquiring the moving speed of the moving target fed back by the tracking radar;
calculating an error interval of the moving range of the moving target based on the moving speed and the reaction time of the image capturing device;
determining the current position information of the moving target, and determining whether the position information is within the error interval;
if yes, the currently captured image containing the moving target is used as the tracking image.
Based on the same concept, one or more embodiments of the present specification further provide an image recognition system, including: a tracking radar, an image capture device, and a processor; wherein
The tracking radar configured to perform the method as applied to the tracking radar as defined in any one of the above;
the image capture device configured to perform the method as claimed in any one of the above applied to an image capture device;
the processor configured to perform the method as claimed in any of the above applied to a processor.
Based on the same idea, one or more embodiments of the present specification further provide an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method applied to the processor as described in any one of the above, or implementing the method applied to a tracking radar as described in any one of the above, or implementing the method applied to an image capturing device as described in any one of the above when executing the program.
Based on the same concept, one or more embodiments of the present specification also provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to implement the method applied to a processor as described in any one of the above, or to implement the method applied to a tracking radar as described in any one of the above, or to implement the method applied to an image capture device as described in any one of the above.
As can be seen from the above description, one or more embodiments of the present specification provide an image recognition method, system, electronic device, and storage medium, including: acquiring a first image to be processed, wherein the first image to be processed is one of tracking images obtained by positioning and capturing a moving target by an image capturing device through a tracking radar; carrying out similarity judgment on the first image to be processed; if not, acquiring a second image to be processed from the tracking image, and judging the similarity of the second image to be processed, wherein the second image to be processed meets the definition condition; and if so, determining the identification result according to the judgment result. One or more embodiments of the present disclosure accurately position and accurately distinguish a moving target by a tracking radar, so that an image capturing device may take multiple shots of the moving target, and may perform image recognition on the same moving target by using multiple pictures, thereby avoiding a situation where a single picture is blurred and cannot be recognized, improving accuracy of image detection of the moving target, and improving tracking continuity of the moving target.
Drawings
In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.
Fig. 1 is a flowchart illustrating an image recognition method applied to a processor according to one or more embodiments of the present disclosure;
fig. 2 is a schematic flowchart of an image recognition method applied to a mobile radar according to one or more embodiments of the present disclosure;
FIG. 3 is a flowchart illustrating an image recognition method applied to an image capture device according to one or more embodiments of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to one or more embodiments of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present specification more apparent, the present specification is further described in detail below with reference to the accompanying drawings in combination with specific embodiments.
It should be noted that technical terms or scientific terms used in the embodiments of the present specification should have a general meaning as understood by those having ordinary skill in the art to which the present disclosure belongs, unless otherwise defined. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that a element, article, or method step that precedes the word, and includes the element, article, or method step that follows the word, and equivalents thereof, does not exclude other elements, articles, or method steps. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As described in the background section, for example, in face recognition, face recognition is a series of related technologies that typically use a camera or a video camera to capture an image or a video stream containing a face, automatically detect and track the face in the image, and then perform face recognition on the detected face. The recognition process depends greatly on the quality of the acquired image, the sampling of the algorithm is completely from the image, and the image is difficult to recognize if the image is fuzzy or the position is deviated. At this time, other pictures may be analyzed through the tracking image, thereby increasing the image recognition rate. The current face tracking method comprises the following steps: model-based methods or methods based on the combination of motion and models, methods of skin color model tracking. These methods rely to some extent on images and do not substantially solve the problem.
Meanwhile, the radar tracking technology is mature day by day, and the radar tracking technology adopts an electromagnetic wave principle, is not influenced by environments such as illumination, rainy days and the like, can continuously track a moving target, continuously and accurately measure the coordinates of the moving target and output the coordinate position (direction, elevation angle, slope distance, radial speed and the like). These numbers play a driving role in the synthesis of image features during movement.
In combination with the above practical situations, one or more embodiments of the present disclosure provide an image recognition scheme, so that an image capture device can capture multiple shots of a moving target by accurately positioning and accurately distinguishing the moving target through a tracking radar, and thus, the same moving target can be image-recognized through multiple pictures, thereby avoiding the situation that the moving target cannot be recognized due to blur of a single picture, improving the accuracy of image detection of the moving target, and improving the tracking continuity of the moving target.
Referring to fig. 1, a schematic flowchart of an image recognition method applied to a processor according to an embodiment of the present disclosure specifically includes the following steps:
This step is intended to obtain a tracking image captured by an image capturing device, i.e. the first image to be processed. The first image to be processed is obtained by positioning the moving target through the tracking radar, so that the image capturing device can continuously capture images of the moving target through the positioning, and one of the continuously captured tracking images is determined to be the first image to be processed. Therefore, the tracking radar can be used for accurately positioning the moving target, so that the image capturing device can find the moving target all the time, the moving target can be continuously captured, the situation that a certain image cannot be identified due to blurring can be avoided by acquiring a large number of images in a moving environment, the image detection accuracy of the moving target is improved, and the tracking continuity of the target is improved.
The tracking radar is a radar which continuously tracks a moving target and measures the coordinates of the moving target, and can also provide the motion track of the moving target. In the tracking radar, not only a monopulse technology is adopted, but also a phased array technology, a pulse Doppler technology, a pulse compression technology, a moving target display technology, a radar imaging technology and the like are simultaneously adopted so as to meet the requirements of multiple functions and high performance, and angle tracking and distance tracking can be carried out. The main working principle is as follows: the antenna scans at a fixed rate, and distance, angle and speed information of the moving object can be obtained in each scan. Under the search mode, the result of each scanning is independent, and the relevant processing is not carried out among all frames; the difference of tracking is that the radar needs to determine whether the current moving target is a new moving target, so the inter-frame moving target data needs to be processed relatively to realize the confirmation and tracking of the moving target. Hereinafter, the image capturing apparatus is an apparatus capable of capturing an image of an object by a camera, such as a video camera or a still camera. The moving object may be a moving body, thing, or the like that the user wants to observe.
The characteristic that each moving target entering into the scanning range can be accurately distinguished and positioned by utilizing the tracking radar is utilized, and the position of each moving target is distinguished and continuously determined. Then, the tracking radar transmits the position information of each moving target and the identification for discrimination to the image capturing device, so that the image capturing device can perform image capturing on each moving target, and can discriminate each moving target according to the corresponding identification. The tracking radar and the image capturing equipment can be connected through a serial port or a network port, a communication protocol is formulated, and the two parties communicate information. Finally, the image capture device captures a certain number of tracking images for each moving object so that the processor can acquire one of the tracking images.
In some application scenarios, the timing of the processor acquiring the first to-be-processed image may be defined, for example: when the moving target moves a certain distance in a radar scanning area, acquiring the moving target, or when the moving target reaches a certain range of a radar, starting to acquire the moving target; or when the moving target moves in the radar scanning area for a certain time, obtaining the moving target, and the like; or the image capture device captures a sufficient number of tracking images, etc. In a specific application scenario, in order to determine the timing for acquiring the first to-be-processed image. The acquiring of the first image to be processed, where the first image to be processed includes a moving target, and the first image to be processed is any one of a plurality of tracking images obtained by capturing the moving target based on continuous positioning of a tracking radar by an image capturing device, includes: judging whether the number of the tracking images meets a preset number threshold value or not; and if so, selecting any one of the tracking images as the first image to be processed.
In a specific application scene, for example, a human body or a human face is identified, a tracking radar is used as an active party, a moving target area or a scanning range is scanned once every 60ms, each moving target can be distinguished by a radar tracking technology, a unique ID (Identity document) is generated for each moving target, coordinate information and the ID are sent to a camera (image capture device) at regular intervals according to the processing speed of the camera, the camera processing system immediately takes a snapshot after receiving a signal and is bound with the ID, so that the ID has a plurality of photos (tracking images), and each moving target is distinguished and captures a plurality of photos in the moving process. Meanwhile, it can be seen that the identity identifier is not necessarily used in the scheme, the tracking radar can only transmit the position information of one moving target to the image capturing device each time, and the image capturing device only shoots the moving target on the position information, so that each moving target is naturally distinguished, and the process of setting the distinguishing identifier is omitted. Thereafter, when the tracking radar determines the position of the moving target object, the determination of the position point may be performed based on the coordinate system of the radar itself, or the determination of the position point may be performed based on the coordinate system of the image capturing device, and the conversion between the two coordinate systems may occur on the tracking radar, on the image capturing device, or the like.
And 102, judging whether the first image to be processed is similar to any image in a preset image library.
The step aims to compare the similarity of the first image to be processed with each image in a preset image library and judge whether the images are similar. Wherein, it has many preset images to store in the image storehouse to predetermine, and the expression form of predetermineeing the image storehouse can be: a standard certificate photo image library of employees, a front clear photo image library of paintings, and so on. Then, the similarity between the first image to be processed and each image in the preset image library is compared, and whether the similarity between the first image to be processed and each image in the preset image library meets the condition is determined, for example: and if the similarity of the face image reaches 90 or above, determining that the image content is consistent with the currently compared image content. The identity of the object in the first image to be processed can then be determined.
Meanwhile, in order to improve the efficiency of the first comparison, images which are not easy to identify similarity, such as blurred images, can be screened out before comparison. That is, before the similarity comparison, the image definition may be confirmed, for example, a definition threshold may be set. When the first image to be processed is too fuzzy and the definition does not reach the standard, the image can be directly determined to be not similar to the images in the preset image library, and the like.
In some application scenarios, before the determining whether the first image to be processed is similar to any image in a preset image library, the method may include: detecting the definition of the first image to be processed; and if the definition does not reach a preset threshold value, executing the step of obtaining a second image to be processed from the plurality of tracking images. Namely, the definition of the first image to be processed is judged first, the similarity is judged only when the judgment is passed, if the definition is low, the similarity judgment is directly determined to fail, and the second image to be processed is directly selected.
Taking face recognition as an example in a specific application scene, transmitting a first image to be processed to a third-party device or module, recognizing information such as image definition and face position, returning face position coordinates and face image definition values in the image, when the definition values are greater than 80, determining that the image is clear, cutting or framing the face image, sending the face image to a background face recognition interface, comparing the image with all images in a background face library according to the characteristics of the image, returning a similar image, and if the similarity of a similar head image is greater than 90, determining that the recognition is successful and the face is recognized.
The method comprises the steps of acquiring a second image to be processed which meets the definition condition when the similarity judgment of the first image to be processed fails, and comparing the similarity to judge whether the images are similar or not. In the determination process of step 102, if the determination fails, the image of the moving target captured by the image capturing device is called out, a certain amount or all of the images are acquired, and the definition values of the images are confirmed by a third-party device or module. Then, the definition condition can be that all the images are sorted according to the definition values, and the highest one or more images are determined; or sharpness above a certain threshold, etc. In some application scenes, an image with the highest definition is determined as a second image to be processed, and similarity comparison is performed on the second image to be processed and any image in the preset image library again. In another application scenario, a plurality of images meeting the condition can be selected, similarity comparison can be performed on each image, the images can be compared at the same time, and the whole similarity judgment is considered to be successful as long as one image passes the judgment; or the comparison may be performed in sequence, and when the current image similarity determination fails, the determination of the next image is performed until the determination is passed or the determination of all images is completed.
In some application scenarios, if the comparison of the first to-be-processed image in step 102 fails, which indicates that the situation at that time is more complicated, image tracing is started, because the ID of the image or the corresponding moving target is known, all tracking images of the ID can be acquired, a background face detection interface is called for each image, sorting is performed according to the returned face coordinates and the definition threshold, three images with the highest definition are taken out, the image with the highest definition is firstly sent to the background interface for face recognition, if the similarity value is greater than 90, the recognition is successful, if the similarity value is failed, the image with the highest definition in the other two images is used for trial comparison, and so on.
And 104, determining the identification result of the moving target according to the judgment result of whether the second image to be processed is similar to any image in the preset image library.
This step is intended to generate and output a result of recognition of the moving object based on the result of similarity determination of the second image to be processed. If the similarity judgment is successful, the related information of the person or the object in the image to be processed can be determined according to the related information of the image which is specifically similar to the image to be processed. For example: copyright information such as identity information of a person corresponding to the face recognition, author information of a painting corresponding to the image painting recognition, and the like. Furthermore, the relation or mapping between the relevant information and the image to be recognized and the moving target can be established, so that the identity of the moving target can be determined. The identification result may include information of successful identification, specific identity information of the moving object, and the like. If the similarity determination fails, an identification result that the moving object has not been identified is generated, and in order to improve the probability of successful comparison after two times of comparison, the mobile object or other devices may be adjusted according to the identification result, and the moving object that has failed in identification is focused or the image of the moving object is specially processed, for example: the tracking radar is enabled to increase the positioning frequency of the moving target, the image capturing device is enabled to increase the image capturing frequency of the moving target, the processor is enabled to lower the threshold value for passing judgment, the processor is enabled to carry out image sharpening on the image of the moving target, and the like.
In some application scenarios, specifically, determining the recognition result of the moving target according to the determination result of whether the second image to be processed is similar to any image in the preset image library includes: if the second image to be processed is not similar to any image in the preset image library, sending a first instruction to the tracking radar, and/or sending a second instruction to the image capturing device, so that the tracking radar improves the positioning frequency of the moving target according to the first instruction, and the image capturing device improves the image capturing frequency of the moving target according to the second instruction. That is, when the moving target cannot be identified in both of the two identifications, the tracking radar may be notified to increase the sampling frequency of the moving target, and the image capturing device may be notified to increase the number of times of image capturing trigger for the moving target, so as to acquire more images of the moving target, and provide a greater possibility for performing similarity determination again later.
Finally, the recognition result can be output for storage, display or reprocessing. According to different application scenes and implementation requirements, the specific output mode of the recognition result can be flexibly selected.
For example, for an application scenario in which the method of the present embodiment is executed on a single device, the recognition result may be directly output in a display manner on a display section (display, projector, etc.) of the current device, so that the operator of the current device can directly see the content of the recognition result from the display section.
For another example, for an application scenario executed on a system composed of multiple devices by the method of this embodiment, the identification result may be sent to other preset devices as recipients in the system through any data communication manner (wired connection, NFC, bluetooth, wifi, cellular mobile network, etc.), so that the preset device receiving the identification result may perform subsequent processing on the preset device. Optionally, the preset device may be a preset server, and the server is generally arranged at a cloud end and used as a data processing and storage center, which can store and distribute the recognition result; the receiver of the distribution is terminal equipment, and the holders or operators of the terminal equipment can be current users of the identification equipment, personnel or individuals related to units related to identification objects, and the like.
For another example, for an application scenario executed on a system composed of multiple devices, the method of this embodiment may directly send the recognition result to a preset terminal device through any data communication manner, where the terminal device may be one or more of the foregoing paragraphs.
In some specific application scenarios, after the recognition result is output, in order to reduce the communication amount between the tracking radar and the processor and the image capturing device, the data transmission efficiency is improved. And the tracking radar can stop uploading the data of the moving target corresponding to the identification result according to the successful identification result. And to save picture storage space. The tracking image associated with the successfully identified moving object may be deleted.
In a specific application scenario, after identification is successful, the identity of the corresponding moving target is determined, so that other processing is not needed, only the radar needs to be tracked to determine the position of the moving target, and meanwhile, the determined position does not need to be transmitted to a server, and further, the transmission of related data about the moving target can be stopped. Therefore, the communication quantity is reduced, and the bandwidth is released for other data transmission. After the identification is successful, the images for identification have completed their respective tasks because the identity of the moving object has been confirmed, and can be deleted to free up storage space. In addition, in a specific application scenario, if a moving target is not recognized successfully for a long time, for example, for more than one hour, the tracking image related to the moving target may also be deleted, and the moving target may not be recognized successfully in the whole process, or the moving target may also fail to track due to a situation such as stopping moving, or the identifier of the moving target is replaced. In order to improve the utilization rate of the storage space, the tracking images of the moving targets can be deleted.
An image recognition method provided by applying one or more embodiments of the present specification includes: acquiring a first image to be processed, wherein the first image to be processed is one of tracking images obtained by positioning and capturing a moving target by an image capturing device through a tracking radar; carrying out similarity judgment on the first image to be processed; if not, acquiring a second image to be processed from the tracking image, and judging the similarity of the second image to be processed, wherein the second image to be processed meets the definition condition; and if so, determining the identification result according to the judgment result. One or more embodiments of the present disclosure accurately position and accurately distinguish a moving target by a tracking radar, so that an image capturing device may take multiple shots of the moving target, and may perform image recognition on the same moving target by using multiple pictures, thereby avoiding a situation where a single picture is blurred and cannot be recognized, improving accuracy of image detection of the moving target, and improving tracking continuity of the moving target.
It should be noted that the method of one or more embodiments of the present disclosure may be performed by a single device, such as a computer or server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the devices may perform only one or more steps of the method of one or more embodiments of the present disclosure, and the devices may interact with each other to complete the method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, one or more embodiments of the present specification further provide an image recognition method applied to a mobile radar, which is shown in fig. 2 and specifically includes the following steps:
This step is intended to determine the positioning information of the moving object. The tracking radar is a radar which continuously tracks a moving target and measures the coordinate of the moving target, and can also provide the motion track of the moving target. The positioning information is information reflecting the position of the moving target, and may be a specific position of the moving target determined by establishing a corresponding coordinate system to determine coordinates of the moving target in the coordinate system, and the like. Then, in the field of radar positioning, common allelic methods include a direction finding positioning method, a time difference positioning method, a direction finding time difference positioning method and the like. The positioning information may further include identification information corresponding to each moving target, so that other devices may distinguish each moving target according to the identification information.
This step is intended to send the positioning information to the image capturing device, so that the image capturing device captures the image of the moving target, and after the tracking image is obtained, the processor can select one of the images as a first image to be processed, and the processor performs corresponding processing or response based on the first image to be processed.
The image recognition method applied to the tracking radar of the above embodiment acquires the first image to be processed, which can be acquired by the processor, by sending the positioning information to the image capturing device, so that the processor acquires the first image to be processed; carrying out similarity judgment on the first image to be processed; if not, acquiring a second image to be processed from the tracking image, and judging the similarity of the second image to be processed, wherein the second image to be processed meets the definition condition; and if so, determining the identification result according to the judgment result. One or more embodiments of the present disclosure accurately position and accurately distinguish a moving target by a tracking radar, so that an image capturing device may take multiple shots of the moving target, and may perform image recognition on the same moving target by using multiple pictures, thereby avoiding a situation where a single picture is blurred and cannot be recognized, improving accuracy of image detection of the moving target, and improving tracking continuity of the moving target.
In an alternative embodiment of the present description, each moving object is continuously located for greater convenience. The continuously positioning the moving target to generate the positioning information includes:
scanning a target area to generate a radar coordinate system corresponding to the target area;
when the moving target is identified in the target area, marking the moving target to generate a target identifier;
and generating the positioning information according to the target identification and the position coordinates of the moving target in the radar coordinate system.
The target area is a preset area which needs to be scanned by the radar, and the radar coordinate system is a two-dimensional or three-dimensional coordinate system which is established by the radar by taking the radar or a set point as an origin. Target identification, i.e. a mark symbol that can characterize or point to a moving target, etc., for example: and (4) ID.
Based on the same inventive concept, one or more embodiments of the present specification further provide an image recognition method applied to an image capture device, which is shown in fig. 3 and specifically includes the following steps:
This step aims to obtain positioning information. The tracking radar and the positioning information are similar to the corresponding features in the foregoing embodiments, and are not described herein again.
The step is to acquire a tracking image according to the positioning information, enable the processor to select one of the tracking images as a first image to be processed, and enable the processor to perform corresponding processing or response after the first image to be processed is acquired.
The image recognition method applied to the image capturing device of the above embodiment acquires the first image to be processed through the acquired positioning information, and the first image to be processed can be acquired by the processor, so that the processor acquires the first image to be processed; carrying out similarity judgment on the first image to be processed; if not, acquiring a second image to be processed from the tracking image, and judging the similarity of the second image to be processed, wherein the second image to be processed meets the definition condition; and if so, determining the identification result according to the judgment result. One or more embodiments of the present disclosure accurately position and accurately distinguish a moving target by a tracking radar, so that an image capturing device may take multiple shots of the moving target, and may perform image recognition on the same moving target by using multiple pictures, thereby avoiding a situation where a single picture is blurred and cannot be recognized, improving accuracy of image detection of the moving target, and improving tracking continuity of the moving target.
In an alternative embodiment of the present description, continuous image capture is performed for each moving target for greater convenience. The positioning information includes: reflecting the position coordinates of the position of the moving target and the target identification corresponding to the moving target;
the obtaining of the image of the moving target according to the positioning information and the generation of a plurality of tracking images comprise:
converting the position coordinates between a radar coordinate system and a capturing coordinate system to generate conversion coordinates in the capturing coordinate system, wherein the radar coordinate system corresponds to the tracking radar, and the capturing coordinate system corresponds to the image capturing equipment;
and capturing an image according to the converted coordinates, and binding the captured image with the target identifier to generate the tracking image.
When the tracking radar identifies moving targets, a coordinate system used for marking each moving target is established in a scanning area, namely a radar coordinate system, and a two-dimensional or three-dimensional coordinate system can be established by taking the radar as an origin. Then, when the image capturing device is positioned, the positioning is also carried out through a coordinate system, which is generally a camera coordinate system established by itself or a set point as an origin, and conversion is carried out between the two coordinate systems, and the conversion process can be carried out on a tracking radar, the image capturing device or a processor.
Then, the image capturing device can perform tracking shooting on the same moving target according to the real-time coordinate information and the corresponding target identification, continuously acquire tracking images, and complete continuous image capturing.
In an alternative embodiment of the present specification, in order to prevent the inaccuracy of the position information fed back to the image capturing device by the tracking radar due to the movement of the moving target, the image capturing device is prevented from losing the moving target. The obtaining of the image of the moving target according to the positioning information and the generation of a plurality of tracking images comprise:
acquiring the moving speed of the moving target fed back by the tracking radar;
calculating an error interval of the moving range of the moving target based on the moving speed and the reaction time of the image capturing device;
determining the current position information of the moving target, and determining whether the position information is within the error interval;
if yes, the currently captured image containing the moving target is used as the tracking image.
The moving speed of the moving target can be calculated by the tracking radar itself. Then, according to the determined data reaction time and data transmission time of the image capturing device, a moving distance range interval of a moving target, that is, a distance range error interval in which the moving target may move when the tracking radar acquires the position of the moving target and when the image capturing device photographs the moving target, can be roughly calculated. Therefore, as long as the moving object is within the error interval during shooting, the image capturing apparatus recognizes the moving object as the same moving object, thereby preventing the moving object from being lost. Meanwhile, in a specific application scenario, after the error interval is obtained, the size of the error interval can be appropriately adjusted according to specific conditions, for example, the error interval can be appropriately enlarged, so that the capture range of the image capture device is further enlarged, the time difference is offset, and the fault tolerance rate is improved.
Based on the same inventive concept, one or more embodiments of the present specification further provide an image recognition system, including: a tracking radar, an image capture device, and a processor; wherein
The tracking radar is configured to execute the image recognition method applied to the tracking radar as described in any one of the above embodiments.
The image capturing device is configured to execute the image recognition method applied to the image capturing device as described in any one of the above embodiments.
The processor is configured to execute the image recognition method applied to the processor as described in any one of the above embodiments.
The system of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
One or more embodiments of the present specification further provide an electronic device based on the same inventive concept. The electronic device comprises a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor executes the program to realize an image recognition method applied to the processor as described in any one of the above embodiments, or realize an image recognition method applied to a tracking radar as described in any one of the above embodiments, or realize an image recognition method applied to an image capture device as described in any one of the above embodiments.
Fig. 4 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 410, a memory 420, an input/output interface 430, a communication interface 440, and a bus 450. Wherein processor 410, memory 420, input/output interface 430, and communication interface 440 are communicatively coupled to each other within the device via bus 450.
The processor 410 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present specification.
The Memory 420 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 420 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 420 and called to be executed by the processor 410.
The input/output interface 430 is used for connecting an input/output module to realize information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 440 is used for connecting a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 410, the memory 420, the input/output interface 430, the communication interface 440 and the bus 450, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
The electronic device of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, one or more embodiments of the present specification further provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform an image recognition method applied to a processor as described in any one of the above embodiments, or perform an image recognition method applied to a tracking radar as described in any one of the above embodiments, or perform an image recognition method applied to an image capture device as described in any one of the above embodiments.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, 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 Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic 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.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the spirit of the present disclosure, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures, for simplicity of illustration and discussion, and so as not to obscure one or more embodiments of the disclosure. Further, devices may be shown in block diagram form in order to avoid obscuring the understanding of one or more embodiments of the present description, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the one or more embodiments of the present description are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that one or more embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (12)
1. An image recognition method applied to a processor, comprising:
acquiring a first image to be processed, wherein the first image to be processed contains a moving target, and the first image to be processed is any one of a plurality of tracking images obtained by continuously positioning and capturing the moving target by an image capturing device based on a tracking radar;
judging whether the first image to be processed is similar to any image in a preset image library or not;
if the first image to be processed is not similar to any image in the preset image library, acquiring a second image to be processed from the plurality of tracking images, and judging whether the second image to be processed is similar to any image in the preset image library or not, wherein the second image to be processed meets a preset definition condition;
and determining the identification result of the moving target according to the judgment result of whether the second image to be processed is similar to any image in the preset image library.
2. The method according to claim 1, wherein before determining whether the first image to be processed is similar to any image in a predetermined image library, the method comprises:
detecting the definition of the first image to be processed;
and if the definition does not reach a preset threshold value, executing the step of obtaining a second image to be processed from the plurality of tracking images.
3. The method according to claim 1, wherein determining the recognition result of the moving object according to the determination result of whether the second image to be processed is similar to any image in the preset image library comprises:
if the second image to be processed is not similar to any image in the preset image library, sending a first instruction to the tracking radar, and/or sending a second instruction to the image capturing device, so that the tracking radar improves the positioning frequency of the moving target according to the first instruction, and the image capturing device improves the image capturing frequency of the moving target according to the second instruction.
4. The method according to claim 1, wherein the obtaining a first image to be processed, the first image to be processed containing a moving target, the first image to be processed being any one of a plurality of tracking images captured by an image capturing device based on continuous positioning of the moving target by a tracking radar, comprises:
judging whether the number of the tracking images meets a preset number threshold value or not;
and if so, selecting any one of the tracking images as the first image to be processed.
5. An image recognition method applied to a tracking radar includes:
continuously positioning a moving target to generate positioning information;
sending the positioning information to an image capturing device, enabling the image capturing device to obtain the image of the moving target according to the positioning information, and generating a plurality of tracking images; enabling a processor to select one of the plurality of tracking images as a first image to be processed and causing the processor to perform the method according to any one of claims 1 to 4.
6. The method of claim 5, wherein said continuously positioning the moving object and generating the positioning information comprises:
scanning a target area to generate a radar coordinate system corresponding to the target area;
when the moving target is identified in the target area, marking the moving target to generate a target identifier;
and generating the positioning information according to the target identification and the position coordinates of the moving target in the radar coordinate system.
7. An image recognition method applied to an image capturing apparatus, comprising:
acquiring positioning information of a moving target sent by a tracking radar;
acquiring an image of a moving target according to the positioning information, and generating a plurality of tracking images; enabling a processor to select one of the plurality of tracking images as a first image to be processed and causing the processor to perform the method according to any one of claims 1 to 4.
8. The method of claim 7, wherein the positioning information comprises: reflecting the position coordinates of the position of the moving target and the target identification corresponding to the moving target;
the obtaining of the image of the moving target according to the positioning information and the generation of a plurality of tracking images comprise:
converting the position coordinates between a radar coordinate system and a capturing coordinate system to generate conversion coordinates in the capturing coordinate system, wherein the radar coordinate system corresponds to the tracking radar, and the capturing coordinate system corresponds to the image capturing equipment;
and capturing an image according to the converted coordinates, and binding the captured image with the target identifier to generate the tracking image.
9. The method according to claim 7, wherein the obtaining an image of a moving target according to the positioning information and generating a plurality of tracking images comprises:
acquiring the moving speed of the moving target fed back by the tracking radar;
calculating an error interval of the moving range of the moving target based on the moving speed and the reaction time of the image capturing device;
determining the current position information of the moving target, and determining whether the position information is within the error interval;
if yes, the currently captured image containing the moving target is used as the tracking image.
10. An image recognition system, comprising: a tracking radar, an image capture device, and a processor; wherein
The tracking radar configured to perform the method of any one of claims 5 or 6;
the image capture device configured to perform the method of any of claims 7 to 9;
the processor configured to perform the method of any of claims 1 to 4.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4, or implements the method of any one of claims 5 or 6, or implements the method of any one of claims 7 to 9 when executing the program.
12. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to implement the method of any one of claims 1 to 4, or the method of any one of claims 5 or 6, or the method of any one of claims 7 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011205359.4A CN112307985A (en) | 2020-11-02 | 2020-11-02 | Image identification method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011205359.4A CN112307985A (en) | 2020-11-02 | 2020-11-02 | Image identification method, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112307985A true CN112307985A (en) | 2021-02-02 |
Family
ID=74333782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011205359.4A Withdrawn CN112307985A (en) | 2020-11-02 | 2020-11-02 | Image identification method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112307985A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283617A (en) * | 2021-05-21 | 2021-08-20 | 东华大学 | Clothing reconstruction method and server system thereof |
| CN116703742A (en) * | 2022-11-04 | 2023-09-05 | 荣耀终端有限公司 | Method for identifying blurred image and electronic equipment |
-
2020
- 2020-11-02 CN CN202011205359.4A patent/CN112307985A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283617A (en) * | 2021-05-21 | 2021-08-20 | 东华大学 | Clothing reconstruction method and server system thereof |
| CN116703742A (en) * | 2022-11-04 | 2023-09-05 | 荣耀终端有限公司 | Method for identifying blurred image and electronic equipment |
| CN116703742B (en) * | 2022-11-04 | 2024-05-17 | 荣耀终端有限公司 | Method for identifying blurred image and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10334151B2 (en) | Phase detection autofocus using subaperture images | |
| CN111983635B (en) | Pose determination method and device, electronic equipment and storage medium | |
| CN108537726B (en) | Tracking shooting method and device and unmanned aerial vehicle | |
| US8666145B2 (en) | System and method for identifying a region of interest in a digital image | |
| US9854174B2 (en) | Shot image processing method and apparatus | |
| KR20160019512A (en) | Robust tracking using point and line features | |
| CN110849885B (en) | Hard spot monitoring method, device and system in bow net system | |
| CN105808542B (en) | Information processing method and information processing apparatus | |
| CN111161347B (en) | Method and equipment for initializing SLAM | |
| CN112307985A (en) | Image identification method, system, electronic equipment and storage medium | |
| CN109357679B (en) | Indoor positioning method based on significance characteristic recognition | |
| US9014428B2 (en) | Object detection using difference of image frames | |
| CN109247068A (en) | Method and apparatus for rolling shutter compensation | |
| EP4036759A1 (en) | Pose determination method, apparatus and system | |
| CN110245641A (en) | A kind of target tracking image pickup method, device, electronic equipment | |
| CN105827928A (en) | Focusing area selection method and focusing area selection device | |
| WO2022105027A1 (en) | Image recognition method and system, electronic device, and storage medium | |
| CN114862828A (en) | Light spot searching method and device, computer readable medium and electronic equipment | |
| JP2001266128A (en) | Method and device for obtaining depth information and recording medium recording depth information obtaining program | |
| CN112543284B (en) | Focusing system, method and device | |
| CN111402296B (en) | Target tracking method and related device based on camera and radar | |
| WO2019011017A1 (en) | Method and device for noise processing | |
| CN114040107B (en) | Intelligent automobile image shooting system, intelligent automobile image shooting method, intelligent automobile image shooting vehicle and intelligent automobile image shooting medium | |
| CN109698933B (en) | Data transmission method, camera, electronic device, and computer-readable storage medium | |
| US10282633B2 (en) | Cross-asset media analysis and processing |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210202 |
|
| WW01 | Invention patent application withdrawn after publication |