CN113132615B - Object image acquisition method, device, electronic equipment and storage medium - Google Patents
Object image acquisition method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113132615B CN113132615B CN201911419630.1A CN201911419630A CN113132615B CN 113132615 B CN113132615 B CN 113132615B CN 201911419630 A CN201911419630 A CN 201911419630A CN 113132615 B CN113132615 B CN 113132615B
- Authority
- CN
- China
- Prior art keywords
- image
- image information
- target object
- quality
- acquiring
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a method, a device, electronic equipment and a storage medium for acquiring an object image, wherein the method comprises the following steps: acquiring first image information of a target object, and judging whether the image quality of the first image information meets a first quality condition; if the image quality of the first image information does not meet a first quality condition, extracting residual features in the first image information; and acquiring second image information of the target object according to the residual characteristics, and acquiring the target object image based on the second image information when the image quality of the second image information meets a second quality condition. Extracting the residual characteristics of the target object through the target object which does not meet the quality condition, and secondarily acquiring the target object according to the residual characteristics to obtain second image information which meets the quality condition, so that for one target object, the image with higher quality can be ensured to be acquired, and the image quality of the acquired target object is improved.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a method and apparatus for acquiring an object image, an electronic device, and a storage medium.
Background
Along with the rapid development of artificial intelligence, the application of machine vision is wider and wider, such as image recognition, image archive search and the like applied to the security field, and recognition, search or profiling is performed after the target object is captured based on a camera. However, due to various reasons, such as light, installation position and setting angle of the camera, position and posture of the target object, shielding of other objects, etc., the quality of the captured image of the target object is poor, which affects subsequent recognition, searching or profiling. Therefore, the quality of the object image obtained by the existing image acquisition method is not high.
Disclosure of Invention
The embodiment of the invention provides an object image acquisition method which can improve the image quality of an acquired target object.
In a first aspect, an embodiment of the present invention provides a method for acquiring an object image, including:
acquiring first image information of a target object, and judging whether the image quality of the first image information meets a first quality condition;
if the image quality of the first image information does not meet a first quality condition, extracting residual features in the first image information;
and acquiring second image information of the target object according to the residual characteristics, wherein the image quality of the second image information meets a second quality condition, and acquiring the target object image based on the second image information when the image quality of the second image information meets the second quality condition.
Optionally, the determining whether the image quality of the first image information meets a first quality condition includes:
inputting the first image information into a pre-trained quality evaluation network, and acquiring image quality characteristics of preset dimensions, wherein the preset dimensions comprise at least one of a light dimension, a position dimension, a gesture dimension and an integrity dimension;
judging whether the image quality characteristics of the preset dimension meet a first quality condition or not, wherein the first quality condition corresponds to at least one of a light condition, a position condition, a gesture condition and an integrity condition.
Optionally, the extracting the residual feature in the first image information includes:
and extracting at least one of contour features, size features and attribute features of the target object as residual features through a pre-trained feature extraction network.
Optionally, the acquiring the first image information of the target object includes:
acquiring first image information of a target object through first image acquisition equipment;
the obtaining second image information of the target object according to the residual feature includes:
and after the interval time, acquiring second image information of the target object through the first image acquisition equipment according to the residual characteristics.
Optionally, the acquiring the first image information of the target object includes:
acquiring first image information of a target object through first image acquisition equipment;
the obtaining second image information of the target object according to the residual feature includes:
if the target object is separated from the acquisition range of the first image acquisition equipment, the residual characteristics are sent to second image acquisition equipment;
acquiring second image information of the target object through the second image acquisition equipment;
the second image acquisition equipment is image acquisition equipment within a preset range of the first image acquisition equipment.
Optionally, after the second image information of the target object is acquired, the method further includes:
simultaneously displaying the first image information and the second image information in an image display interface; or (b)
Displaying first image information and a switching identifier by default in an image display interface, and switching the first image information into the second image information for display through the switching identifier; or (b)
And displaying the second image information and the switching identification by default in an image display interface, and switching the second image information into the first image information for display through the switching identification.
Optionally, after the second image information of the target object is acquired, the method further includes:
storing the first image information into a first database, and adding a first image ID of the first image information;
storing the second image information into a second database, and adding a second image ID of the second image information;
a mapping between the first image ID and the second image ID is established such that the first image ID and the second image ID form an index relationship.
In a second aspect, an embodiment of the present invention provides an object image acquiring apparatus, including:
the first acquisition module is used for acquiring first image information of a target object and judging whether the image quality of the first image information meets a first quality condition or not;
the extraction module is used for extracting residual features in the first image information if the image quality of the first image information does not meet a first quality condition;
and the second acquisition module is used for acquiring second image information of the target object according to the residual characteristics, wherein the image quality of the second image information meets a second quality condition, and when the image quality of the second image information meets the second quality condition, the target object image is acquired based on the second image information.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the image acquisition device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the steps in the object image acquisition method provided by the embodiment of the invention are realized when the processor executes the computer program.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the object image acquiring method provided by the embodiments of the present invention.
In the embodiment of the invention, first image information of a target object is acquired, and whether the image quality of the first image information meets a first quality condition is judged; if the image quality of the first image information does not meet a first quality condition, extracting residual features in the first image information; and acquiring second image information of the target object according to the residual characteristics, wherein the image quality of the second image information meets a second quality condition, and acquiring the target object image based on the second image information when the image quality of the second image information meets the second quality condition. Extracting the residual characteristics of the target object through the target object which does not meet the quality condition, and secondarily acquiring the target object according to the residual characteristics to obtain second image information which meets the quality condition, so that for one target object, the image with higher quality can be ensured to be acquired, and the image quality of the acquired target object is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for acquiring an object image according to an embodiment of the present invention;
FIG. 2 is a flowchart of another object image acquisition method according to an embodiment of the present invention;
FIG. 3 is a flowchart of another object image acquisition method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an object image acquiring apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural view of another object image acquiring apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of another object image acquiring apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of another object image acquiring apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural view of another object image acquiring apparatus according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flowchart of a method for acquiring an object image according to an embodiment of the present invention, as shown in fig. 1, including the following steps:
101. first image information of a target object is acquired, and whether the image quality of the first image information meets a first quality condition is judged.
The target object may be a person image, a vehicle image, a face image, a ship image, an animal image, or the like. The first image information refers to image information including the target object, and the first image information may be acquired by capturing by an image acquisition device or may be acquired by a video uploaded by a user. For example, when the image capturing device captures an image, after the target object is detected, the image capturing device is adjusted to capture an image of the target object, so as to obtain first image information of the target object.
The image quality refers to the image quality of the area where the target object is located, and is affected by light, the installation position and the setting angle of the camera, the position and the posture where the target object is located, shielding of other objects, and the like. The higher the image quality is, the smaller the degree of influence of the light rays, the mounting position and the setting angle of the camera, the position and the posture of the target object, the shielding of other objects and the like on the target object is. The image quality described above may be measured by the quality score extracted by the pre-trained image quality assessment network.
Among these, the above light effects are as follows: direct irradiation of strong light to a camera causes blurred shooting, reflection of a human image by transparent glass, reflection of a target object by other specular objects, backlight of the target object, and the like.
The above-mentioned camera mounting position and setting angle influence say: the shooting range with higher position is long, the shooting target object can not be identified actually, the shooting range with lower position is short, the shooting target object is incomplete, the focal length of the camera is not adjusted, the shooting target object is fuzzy, and the like.
The position and posture of the target object influence such as: target object sideways, target object head up, target object head down, target object turning around, target object main features are not or partially not within the camera range, etc.
Other object occlusion effects as described above are: the front of the camera is covered by a shielding object (tree branches, leaves, billboards and the like), a ground fixed object is covered by a lamp post, a billboard, trees and the like, and the face of a person is covered by a mask, a sunglasses, a sunhat, a scarf, a collar and the like.
The pre-trained image quality evaluation network can be used for comprehensively evaluating the image quality or classifying and evaluating various evaluation items. For example, when the image quality evaluation network is trained, the sample data is marked by a comprehensive quality label to obtain a corresponding sample data set, and the image quality evaluation network trained by the sample data set can evaluate the comprehensive quality of the image. When the image quality evaluation network is trained, the sample data are classified and labeled through the classification labels, and the image quality evaluation network is trained through sample data sets of different categories and corresponding loss functions, so that the trained image quality evaluation network can evaluate the classification quality of the images.
In one possible embodiment, the classification label may be a binary classification label, that is, the classification label corresponds to two values of 0 and 1, for example, if one sample of data is greatly affected by light, its light classification label is 0, otherwise, if it is less affected by light, its label is 1; if the influence of the installation position and the setting angle of the camera on one sample of data is larger, the installation classification label of the sample of data is 0, and if the influence of the installation position and the setting angle of the camera is smaller, the installation classification label of the sample of data is 1; if the influence of the position and the gesture of the target object on one sample of data is larger, the gesture classification label is 0, otherwise, if the influence of the position and the gesture of the target object is smaller, the gesture classification label is 1; if the occlusion of one sample data is larger, the occlusion classification label is 0, otherwise, if the occlusion is smaller, the occlusion classification label is 1. After training the quality evaluation network through the classification tag, when the image is inferred, the quality evaluation network outputs vectors corresponding to the dimensions of the classification number, for example, a (A, B, C, D) four-dimensional vector is correspondingly output by taking the light A, the camera mounting position and the setting angle B, the position and the gesture C where the target object is located and the shielding D as classifications, and the image quality information of the target object can be represented by the vectors, for example, the vectors output by the image evaluation network are (1, 0, 1), and the influence of the position and the gesture where the target object is located is larger.
The first quality condition may be selected according to an image quality evaluation network, and when the image quality evaluation network adopts comprehensive evaluation, the first quality condition may be a quality threshold, and when the image quality of the first image information is greater than the quality threshold, it is indicated that the image quality of the first image information satisfies the first quality condition, and the image quality is higher; when the image quality of the first image information is smaller than the quality threshold, it is indicated that the image quality of the first image information does not satisfy the first quality condition, and the image quality is poor. In addition, when the image quality evaluation network adopts classification evaluation, the first quality condition may be an evaluation value of each classification dimension, for example, the classification dimension corresponds to a light dimension, a position and a setting angle of the camera, a position and an attitude of the target object, a position dimension, an attitude dimension, an integrity dimension and the like blocked by other objects, and the first quality condition may be that each dimension is 1, that is, the influence of each dimension is smaller.
Optionally, if the pre-trained quality evaluation network is a classification evaluation network, inputting the first image information into the pre-trained quality evaluation network to obtain an image quality feature of a preset dimension, where the preset dimension includes at least one of a light dimension, a position dimension, a gesture dimension and an integrity dimension, and similarly, the first quality condition corresponds to at least one of a light condition, a position condition, a gesture condition and an integrity condition; and judging whether the image quality characteristics of the preset dimension meet a first quality condition. Therefore, the quality of the image can be evaluated in more dimensions through the classification evaluation network, so that the evaluation result is more accurate.
102. And if the image quality of the first image information does not meet the first quality condition, extracting residual features in the first image information.
In this step, if the image quality of the first image information does not meet the first quality condition, it is indicated that the image quality of the first image information is poor, which is unfavorable for subsequent image recognition, image retrieval or image archiving.
The feature extraction may be performed according to a pre-trained feature extraction network to extract the residual feature, where the residual feature is a main feature of the non-target object, and the residual feature may be at least one of a contour feature, a size feature, and an attribute feature of the target object. Taking a portrait as a target object for example, the main feature of the portrait is a face feature, and the residual feature may be one or more of a personnel body shape (outline feature), a personnel height (size feature) and a personnel clothing feature (attribute feature).
103. And acquiring second image information of the target object according to the residual characteristics, and acquiring the target object image based on the second image information when the image quality of the second image information meets a second quality condition.
In this step, the image quality of the second image information satisfies the second quality condition, which indicates that the second image information meets the image quality requirement, and when the second image quality does not satisfy the second quality condition, the second image information is circulated as new first image information, the residual feature is continuously extracted, and the new second image information is obtained according to the residual feature, where the second quality condition may be the same as the first quality condition or different from the first quality condition. The target image may be obtained by extracting the target object from the second image information, or may be obtained by directly using the second image information as the target image.
The second image information refers to image information including the target object, and is collected only when the image quality of the first image information is poor. If the first image information meets the first quality condition, the second image information of the target object is not acquired.
The second image information may be acquired by acquiring the target object through the image acquisition device after waiting for an interval time. Specifically, the first image information may be acquired by the first image acquisition device on the target object, and the second image information may also be acquired by the first image acquisition device on the target object. It should be noted that, the above-mentioned interval time is to eliminate the influence of factors affecting the image quality, such as light, mounting position and setting angle of the camera, position and posture of the target object, and shielding of other objects.
In a possible embodiment, the first image information of the target object is acquired by the first image acquisition device, and after an interval, the acquired images are again detected and identified according to the residual characteristics. The residual features are equivalent to providing prior information for the second detection and identification, namely, during detection, the features corresponding to the residual features are selected and extracted, whether the features are similar or not is judged, if the features are similar, the detection and identification of the images are carried out, if the features are dissimilar, the fact that the acquired images do not have target objects is indicated, and the target objects are possibly not in the snapping range of the image acquisition equipment is indicated, at the moment, the residual features extracted by the first image acquisition equipment can be sent to the second image acquisition equipment, and the second image acquisition equipment is used for carrying out the second snapping and the detection and identification on the target objects. The second image capturing device is an image capturing device within a preset range of the first image capturing device, for example, an image capturing device within a range of 2 km of the first image capturing device.
In the embodiment of the invention, first image information of a target object is acquired, and whether the image quality of the first image information meets a first quality condition is judged; if the image quality of the first image information does not meet a first quality condition, extracting residual features in the first image information; and acquiring second image information of the target object according to the residual characteristics, wherein the image quality of the second image information meets a second quality condition. Extracting the residual characteristics of the target object through the target object which does not meet the quality condition, and secondarily acquiring the target object according to the residual characteristics to obtain second image information which meets the quality condition, so that for one target object, the image with higher quality can be ensured to be acquired, and the image quality of the acquired target object is improved.
It should be noted that, the method for acquiring the object image provided by the embodiment of the invention can be applied to devices such as a mobile terminal, a monitor, a computer, a server and the like which need to acquire the object image.
Referring to fig. 2, fig. 2 is a flowchart of a method for obtaining an object image according to an embodiment of the present invention, as shown in fig. 2, including the following steps:
201. first image information of a target object is acquired, and whether the image quality of the first image information meets a first quality condition is judged.
202. And if the image quality of the first image information does not meet the first quality condition, extracting residual features in the first image information.
203. And acquiring second image information of the target object according to the residual characteristics, and acquiring the target object image based on the second image information when the image quality of the second image information meets a second quality condition.
204. And simultaneously displaying the first image information and the second image information in the image display interface.
205. And displaying the first image information and the switching identification by default in an image display interface, and switching the first image information into the second image information for display through the switching identification.
206. And displaying the second image information and the switching identification by default in the image display interface, and switching the second image information into the first image information for display through the switching identification.
It should be noted that, the above steps 204, 205, 206 are three different display modes, and may be selected according to different terminals where the image display interface is located, for example, when the terminal where the image display interface is located is a large-screen terminal, the display mode may be adopted in the step 204, and when the terminal where the image display interface is located is a small-screen terminal (such as a mobile phone, MP4, etc.), the display mode may be adopted in the step 205 or the step 206.
In the embodiment of the invention, the residual characteristics of the target object are extracted by the target object which does not meet the quality condition, and the target object is secondarily acquired according to the residual characteristics so as to obtain the second image information meeting the quality condition, so that the display of the image with higher quality can be ensured to be acquired for one target object.
It should be noted that, the method for acquiring the object image provided by the embodiment of the invention can be applied to devices such as a mobile terminal, a computer and the like which need to acquire the object image and have a display interface.
Referring to fig. 3, fig. 3 is a flowchart of a method for obtaining an object image according to an embodiment of the present invention, as shown in fig. 3, including the following steps:
301. first image information of a target object is acquired, and whether the image quality of the first image information meets a first quality condition is judged.
302. And if the image quality of the first image information does not meet the first quality condition, extracting residual features in the first image information.
303. And acquiring second image information of the target object according to the residual characteristics, and acquiring the target object image based on the second image information when the image quality of the second image information meets a second quality condition.
304. The first image information is stored in a first database, and a first image ID of the first image information is added.
305. The second image information is stored in a second database, and a second image ID of the second image information is added.
306. And establishing a mapping between the first image ID and the second image ID so that the first image ID and the second image ID form an index relation.
In the above step, the first database and the second database may be the same database, and the database is used for storing the first image information and the second image information. The database may be a cloud database or a local database.
In the embodiment of the invention, the residual characteristics of the target object are extracted by the target object which does not meet the quality condition, and the target object is secondarily acquired according to the residual characteristics to obtain the second image information which meets the quality condition, so that the image with higher quality can be ensured to be acquired and stored for one target object, and the images can be mutually indexed.
It should be noted that, the method for acquiring the object image provided by the embodiment of the invention can be applied to devices such as a mobile terminal, a monitor, a computer, a server and the like which need to acquire and store the object image.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an object image capturing apparatus according to an embodiment of the present invention, as shown in fig. 4, the apparatus includes:
a first obtaining module 401, configured to obtain first image information of a target object, and determine whether an image quality of the first image information meets a first quality condition;
an extracting module 402, configured to extract residual features in the first image information if the image quality of the first image information does not meet a first quality condition;
a second obtaining module 403, configured to obtain second image information of the target object according to the residual feature, and obtain an image of the target object based on the second image information when the image quality of the second image information meets a second quality condition.
Optionally, as shown in fig. 5, the first obtaining module 401 includes:
the feature extraction unit 4011 is configured to input the first image information into a pre-trained quality evaluation network, and obtain an image quality feature of a preset dimension, where the preset dimension includes at least one of a ray dimension, a position dimension, a gesture dimension, and an integrity dimension;
the determining unit 4012 is configured to determine whether the image quality feature of the preset dimension meets a first quality condition, where the first quality condition corresponds to at least one of a light condition, a position condition, an attitude condition, and an integrity condition.
Optionally, the extracting module 402 is further configured to extract at least one of a contour feature, a dimension feature, and an attribute feature of the target object as a residual feature through a pre-trained feature extraction network.
Optionally, the first obtaining module 401 is further configured to obtain, by using a first image capturing device, first image information of the target object;
the second obtaining module 403 is further configured to obtain, after an interval, second image information of the target object through the first image capturing device according to the residual feature.
Optionally, as shown in fig. 6, the first obtaining module 401 is further configured to obtain, by using a first image capturing device, first image information of the target object;
the second obtaining module 403 includes:
a transmitting unit 4031, configured to transmit the residual feature to a second image capturing device if the target object is out of the capturing range of the first image capturing device;
an acquisition unit 4032 for acquiring second image information of the target object by the second image acquisition apparatus;
the second image acquisition equipment is image acquisition equipment within a preset range of the first image acquisition equipment.
Optionally, as shown in fig. 7, the apparatus further includes:
a first display module 404, configured to display the first image information and the second image information simultaneously in the image display interface; or (b)
The second display module 405 is configured to display, by default, the first image information and a switching identifier in the image display interface, and switch the first image information to the second image information for display by using the switching identifier; or (b)
The third display module 406 is configured to display the second image information and the switching identifier by default in the image display interface, and switch the second image information to the first image information for display by using the switching identifier.
Optionally, as shown in fig. 8, the apparatus further includes:
a first storage module 407, configured to store the first image information in a first database, and add a first image ID of the first image information;
a second storage module 408, configured to store the second image information in a second database, and add a second image ID of the second image information;
a mapping module 409, configured to establish a mapping between the first image ID and the second image ID, so that the first image ID and the second image ID form an index relationship.
It should be noted that, the object image acquiring apparatus provided in the embodiment of the present invention may be applied to a mobile terminal, a monitor, a computer, a server, and other devices that need to acquire an object image.
The object image acquisition device provided by the embodiment of the invention can realize each process realized by the object image acquisition method in the method embodiment, and can achieve the same beneficial effects. In order to avoid repetition, a description thereof is omitted.
Referring to fig. 9, fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 9, including: a memory 902, a processor 901, and a computer program stored on the memory 902 and executable on the processor 901, wherein:
the processor 901 is configured to call a computer program stored in the memory 902, and perform the following steps:
acquiring first image information of a target object, and judging whether the image quality of the first image information meets a first quality condition;
if the image quality of the first image information does not meet a first quality condition, extracting residual features in the first image information;
and acquiring second image information of the target object according to the residual characteristics, and acquiring the target object image based on the second image information when the image quality of the second image information meets a second quality condition.
Optionally, the determining, performed by the processor 901, whether the image quality of the first image information meets a first quality condition includes:
inputting the first image information into a pre-trained quality evaluation network, and acquiring image quality characteristics of preset dimensions, wherein the preset dimensions comprise at least one of a light dimension, a position dimension, a gesture dimension and an integrity dimension;
judging whether the image quality characteristics of the preset dimension meet a first quality condition or not, wherein the first quality condition corresponds to at least one of a light condition, a position condition, a gesture condition and an integrity condition.
Optionally, the extracting residual features in the first image information performed by the processor 901 includes:
and extracting at least one of contour features, size features and attribute features of the target object as residual features through a pre-trained feature extraction network.
Optionally, the first image information of the acquisition target object executed by the processor 901 includes:
acquiring first image information of a target object through first image acquisition equipment;
the obtaining second image information of the target object according to the residual feature includes:
and after the interval time, acquiring second image information of the target object through the first image acquisition equipment according to the residual characteristics.
Optionally, the first image information of the acquisition target object executed by the processor 901 includes:
acquiring first image information of a target object through first image acquisition equipment;
the obtaining second image information of the target object according to the residual feature includes:
if the target object is separated from the acquisition range of the first image acquisition equipment, the residual characteristics are sent to second image acquisition equipment;
acquiring second image information of the target object through the second image acquisition equipment;
the second image acquisition equipment is image acquisition equipment within a preset range of the first image acquisition equipment.
Optionally, after the second image information of the target object is acquired, the processor 901 further executes a method including:
simultaneously displaying the first image information and the second image information in an image display interface; or (b)
Displaying first image information and a switching identifier by default in an image display interface, and switching the first image information into the second image information for display through the switching identifier; or (b)
And displaying the second image information and the switching identification by default in an image display interface, and switching the second image information into the first image information for display through the switching identification.
Optionally, after the second image information of the target object is acquired, the processor 901 further executes a method including:
storing the first image information into a first database, and adding a first image ID of the first image information;
storing the second image information into a second database, and adding a second image ID of the second image information;
a mapping between the first image ID and the second image ID is established such that the first image ID and the second image ID form an index relationship.
It should be noted that, the electronic device provided in the embodiment of the present invention may be applied to a mobile terminal, a monitor, a computer, a server, and other devices that need to acquire an object image.
The electronic device provided by the embodiment of the invention can realize each process of the object image acquisition method in the embodiment of the method, and can achieve the same beneficial effects, and in order to avoid repetition, the description is omitted.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements each process of the object image acquisition method provided by the embodiment of the invention, and can achieve the same technical effect, so that repetition is avoided, and no further description is provided herein.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM) or the like.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (8)
1. A method of acquiring an image of an object, comprising the steps of:
acquiring first image information of a target object, and judging whether the image quality of the first image information meets a first quality condition or not, wherein the target object is a portrait; the determining whether the image quality of the first image information meets a first quality condition includes: inputting the first image information into a pre-trained quality evaluation network to acquire image quality characteristics of an integrity dimension; judging whether the image quality characteristics of the integrity dimension meet a first quality condition or not, wherein the first quality condition is an integrity condition;
if the image quality of the first image information does not meet the first quality condition, extracting at least one of the personnel body type, the personnel height and the personnel clothing of the target object as residual characteristics through a pre-trained characteristic extraction network;
and acquiring second image information of the target object according to the residual characteristics, and acquiring the target object image based on the second image information when the image quality of the second image information meets a second quality condition.
2. The method of claim 1, wherein the acquiring the first image information of the target object comprises:
acquiring first image information of a target object through first image acquisition equipment;
the obtaining second image information of the target object according to the residual feature includes: and after the interval time, acquiring second image information of the target object through the first image acquisition equipment according to the residual characteristics.
3. The method of claim 1, wherein the acquiring the first image information of the target object comprises:
acquiring first image information of a target object through first image acquisition equipment;
the obtaining second image information of the target object according to the residual feature includes: if the target object is separated from the acquisition range of the first image acquisition equipment, the residual characteristics are sent to second image acquisition equipment;
acquiring second image information of the target object through the second image acquisition equipment;
the second image acquisition equipment is image acquisition equipment within a preset range of the first image acquisition equipment.
4. The method of claim 1, wherein after the acquiring the second image information of the target object, the method further comprises:
simultaneously displaying the first image information and the second image information in an image display interface; or displaying the first image information and the switching identification by default in an image display interface, and switching the first image information into the second image information for display through the switching identification; or displaying the second image information and the switching identification by default in an image display interface, and switching the second image information into the first image information for display through the switching identification.
5. The method of claim 1, wherein after the acquiring the second image information of the target object, the method further comprises:
storing the first image information into a first database, and adding a first image ID of the first image information;
storing the second image information into a second database, and adding a second image ID of the second image information;
a mapping between the first image ID and the second image ID is established such that the first image ID and the second image ID form an index relationship.
6. An object image acquisition apparatus, characterized in that the apparatus comprises: the first acquisition module is used for acquiring first image information of a target object and judging whether the image quality of the first image information meets a first quality condition or not, wherein the target object is a portrait; the determining whether the image quality of the first image information meets a first quality condition includes: inputting the first image information into a pre-trained quality evaluation network to acquire image quality characteristics of an integrity dimension; judging whether the image quality characteristics of the integrity dimension meet a first quality condition or not, wherein the first quality condition is an integrity condition;
the extraction module is used for extracting at least one of the personnel body type, the personnel height and the personnel clothing of the target object as residual characteristics through a pre-trained characteristic extraction network if the image quality of the first image information does not meet a first quality condition;
and the second acquisition module is used for acquiring second image information of the target object according to the residual characteristics, wherein the image quality of the second image information meets a second quality condition, and when the image quality of the second image information meets the second quality condition, the target object image is acquired based on the second image information.
7. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the object image acquisition method according to any one of claims 1 to 5 when the computer program is executed.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps in the object image acquisition method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911419630.1A CN113132615B (en) | 2019-12-31 | 2019-12-31 | Object image acquisition method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911419630.1A CN113132615B (en) | 2019-12-31 | 2019-12-31 | Object image acquisition method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113132615A CN113132615A (en) | 2021-07-16 |
| CN113132615B true CN113132615B (en) | 2023-06-13 |
Family
ID=76769444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911419630.1A Active CN113132615B (en) | 2019-12-31 | 2019-12-31 | Object image acquisition method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113132615B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101546376A (en) * | 2009-04-28 | 2009-09-30 | 上海银晨智能识别科技有限公司 | Human biological information acquisition system, human face photo acquisition and quality testing system and method |
| CN103139457B (en) * | 2011-11-22 | 2017-07-25 | 联想(北京)有限公司 | A kind of image obtains control method and electronic equipment |
| CN104378540A (en) * | 2013-08-12 | 2015-02-25 | 联想(北京)有限公司 | Image collecting method and device and electronic equipment |
| CN104298442B (en) * | 2014-09-18 | 2019-05-31 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN108229240A (en) * | 2016-12-09 | 2018-06-29 | 杭州海康威视数字技术股份有限公司 | A kind of method and device of determining picture quality |
| CN108875485A (en) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | A kind of base map input method, apparatus and system |
| CN107743195A (en) * | 2017-10-09 | 2018-02-27 | 惠州Tcl移动通信有限公司 | A kind of photographic method, mobile terminal and storage medium |
| CN108174093A (en) * | 2017-12-28 | 2018-06-15 | 努比亚技术有限公司 | Method, equipment and the computer of moment image can storage mediums |
-
2019
- 2019-12-31 CN CN201911419630.1A patent/CN113132615B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113132615A (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111209868B (en) | Passenger and luggage information association method and device for passenger station | |
| CN110232369B (en) | Face recognition method and electronic equipment | |
| CN109871815B (en) | Method and device for inquiring monitoring information | |
| CN110956060A (en) | Motion recognition method, driving motion analysis method, device and electronic equipment | |
| KR101781358B1 (en) | Personal Identification System And Method By Face Recognition In Digital Image | |
| CN107995982B (en) | A kind of target identification method, device and intelligent terminal | |
| CN109753904A (en) | A kind of face identification method and system | |
| CN112131936A (en) | Inspection robot image identification method and inspection robot | |
| TWI586160B (en) | Real time object scanning using a mobile phone and cloud-based visual search engine | |
| CN115170792B (en) | Infrared image processing method, device and equipment and storage medium | |
| CN111767831B (en) | Method, apparatus, device and storage medium for processing image | |
| CN113269091A (en) | Personnel trajectory analysis method, equipment and medium for intelligent park | |
| CN112052730B (en) | 3D dynamic portrait identification monitoring equipment and method | |
| CN114943923B (en) | Method and system for recognizing explosion flare smoke of cannonball based on video of deep learning | |
| CN111783654A (en) | Vehicle weight identification method and device and electronic equipment | |
| CN112149690A (en) | Tracing method and tracing system based on biological image feature recognition | |
| CN111539257A (en) | Personnel re-identification method, device and storage medium | |
| CN108197563B (en) | Method and device for acquiring information | |
| CN115880765A (en) | Method and device for detecting abnormal behavior of regional intrusion and computer equipment | |
| WO2024012367A1 (en) | Visual-target tracking method and apparatus, and device and storage medium | |
| CN115410240A (en) | Intelligent face pockmark and color spot analysis method and device and storage medium | |
| CN113132615B (en) | Object image acquisition method, device, electronic equipment and storage medium | |
| CN111738043A (en) | Pedestrian re-identification method and device | |
| CN112287945A (en) | Screen fragmentation determination method and device, computer equipment and computer readable storage medium | |
| CN113920306B (en) | Target re-identification method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |