CN113938671A - Image content analysis method and device, electronic equipment and storage medium - Google Patents

Image content analysis method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113938671A
CN113938671A CN202010675459.7A CN202010675459A CN113938671A CN 113938671 A CN113938671 A CN 113938671A CN 202010675459 A CN202010675459 A CN 202010675459A CN 113938671 A CN113938671 A CN 113938671A
Authority
CN
China
Prior art keywords
image
subregion
weight
content analysis
sub
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.)
Granted
Application number
CN202010675459.7A
Other languages
Chinese (zh)
Other versions
CN113938671B (en
Inventor
马欣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Lynxi Technology Co Ltd
Original Assignee
Beijing Lynxi Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Lynxi Technology Co Ltd filed Critical Beijing Lynxi Technology Co Ltd
Priority to CN202010675459.7A priority Critical patent/CN113938671B/en
Priority to PCT/CN2021/106200 priority patent/WO2022012573A1/en
Publication of CN113938671A publication Critical patent/CN113938671A/en
Application granted granted Critical
Publication of CN113938671B publication Critical patent/CN113938671B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N17/00—Diagnosis, testing or measuring for television systems or their details
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
    • H04N19/154—Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides an image content analysis method, an image content analysis device, an electronic device and a storage medium, wherein the method comprises the following steps: dividing the decoded first image into regions to obtain S image subregions; calculating a quality score for each image sub-region; acquiring a total score of the first image according to the quality score of each image subregion; performing a content analysis operation on the first image in the case that the total score is greater than or equal to a preset threshold; discarding the first image if the total score is less than the preset threshold. The invention can reduce the power consumption of image content analysis.

Description

Image content analysis method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an image content analysis method and apparatus, an electronic device, and a storage medium.
Background
With the development of image processing technology, the application of image processing technology is becoming more and more extensive, wherein image content analysis is a common image processing technology at present. At present, the main process of image content analysis is to acquire video images from a camera, decode the video images, and then analyze the content of each decoded image. Because each decoded image needs to be subjected to content analysis, the power consumption of the image content analysis is relatively high.
Disclosure of Invention
The embodiment of the invention provides an image content analysis method and device, electronic equipment and a storage medium, and aims to solve the problem of high power consumption of image content analysis.
In a first aspect, an embodiment of the present invention provides an image content analysis method, including:
dividing the decoded first image into regions to obtain S image subregions, wherein S is an integer greater than 1;
calculating a quality score for each image sub-region;
acquiring a total score of the first image according to the quality score of each image subregion;
performing a content analysis operation on the first image in the case that the total score is greater than or equal to a preset threshold;
discarding the first image if the total score is less than the preset threshold.
In a second aspect, an embodiment of the present invention provides an image content analysis apparatus, including:
the image decoding device comprises a dividing module, a decoding module and a decoding module, wherein the dividing module is used for dividing a decoded first image into S image sub-regions to obtain S image sub-regions, and S is an integer larger than 1;
the calculating module is used for calculating the quality score of each image subregion;
the acquisition module is used for acquiring the total score of the first image according to the quality score of each image subregion;
the analysis module is used for executing content analysis operation on the first image under the condition that the total score is greater than or equal to a preset threshold value;
a discarding module, configured to discard the first image if the total score is less than the preset threshold.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the image content analysis method comprises a memory, a processor and a program or an instruction which is stored on the memory and can run on the processor, wherein the program or the instruction realizes the steps in the image content analysis method provided by the embodiment of the invention when being executed by the processor.
In a fourth aspect, an embodiment of the present invention provides a readable storage medium, where a program or instructions are stored on the readable storage medium, and when the program or instructions are executed by a processor, the program or instructions implement the steps in the image content analysis method provided by the embodiment of the present invention.
In the embodiment of the invention, the first image after decoding is subjected to region division to obtain S image subregions; calculating a quality score for each image sub-region; acquiring a total score of the first image according to the quality score of each image subregion; performing a content analysis operation on the first image in the case that the total score is greater than or equal to a preset threshold; discarding the first image if the total score is less than the preset threshold. Therefore, only the images with the total scores larger than or equal to the preset threshold value are subjected to content analysis, so that the power consumption of the image content analysis can be reduced.
Drawings
Fig. 1 is a flowchart of an image content analysis method according to an embodiment of the present invention;
FIG. 2 is a block diagram of an implementation of image content analysis provided by an embodiment of the present invention;
FIG. 3 is a diagram illustrating image partitioning according to an embodiment of the present invention;
FIG. 4 is a flow chart of another method for analyzing image content according to an embodiment of the present invention;
fig. 5 is a block diagram of an image content analysis apparatus according to an embodiment of the present invention;
fig. 6 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used are interchangeable under appropriate circumstances such that embodiments of the application can be practiced in sequences other than those illustrated or described herein, and the terms "first" and "second" used herein generally do not denote any order, nor do they denote any order, for example, the first object may be one or more.
Referring to fig. 1, fig. 1 is a flowchart of an image content analysis method according to an embodiment of the present invention, as shown in fig. 1, including the following steps:
step 101, performing region division on the decoded first image to obtain S image sub-regions, wherein S is an integer greater than 1.
The first image may be any frame of image obtained by decoding an image acquired by a camera, and further, the first image may be a current image, for example: the output image frame is decoded when step 101 is performed. In addition, the first image may be an image collected by an internal or external camera of the electronic device. Of course, this is not limited, for example: the image may also be received over a network and the decoding may be performed locally or remotely.
The dividing of the regions may be dividing according to preset dividing positions to obtain S regions, where S may be a preset integer greater than 1, for example: 2. 4 or 6 may be specifically set according to an application scenario.
And 102, calculating the quality score of each image subregion.
This step may be a separate calculation of the quality score for each image sub-region, in particular based on the image content in each image sub-region.
And 103, acquiring a total score of the first image according to the quality score of each image sub-region.
This step may be summing the quality scores of the image sub-regions to obtain a total score of the first image, or may be summing the quality scores of the image sub-regions multiplied by corresponding weights to obtain a total score of the first image.
The total score of the first image is obtained according to the quality score of each image subregion, so that the quality score of the first image is more accurate.
And 104, executing content analysis operation on the first image under the condition that the total score is greater than or equal to a preset threshold value.
The preset threshold may be an empirical value set by a user based on experience, or may be a threshold learned based on a historical image content analysis result, and the like, which is not limited herein.
The total score is greater than or equal to the preset threshold value, which means that the quality of the first image meets the preset condition or the quality of the first image is qualified.
It should be noted that, in the embodiment of the present invention, the content analysis operation is not limited, for example: the content analysis operation may be a currently existing content analysis operation or the content analysis operation may be a subsequently evolving content analysis operation.
And 105, discarding the first image when the total score is smaller than the preset threshold.
The total score being smaller than the preset threshold may be understood as that the quality of the first image does not satisfy the preset condition, or that the quality of the first image is not qualified. Discarding the first image may be understood as not performing a content analysis operation on the first image, such as: the first image is deleted or skipped. The image with unqualified quality can be prevented from being sent to the content analysis module for invalid calculation through the step 105.
In the embodiment of the invention, the total score of the image can be calculated according to each image subregion through the steps, if the total score is greater than or equal to the preset threshold value, the content analysis operation is executed on the first image, otherwise, the first image is discarded, and therefore, the power consumption of the image content analysis can be reduced.
It should be noted that the embodiment of the present invention may be applied to electronic devices, such as an embedded device, a mobile phone, a tablet computer, a wearable device, a vehicle, and the like, which is not limited thereto.
As an optional implementation, the obtaining the total score of the first image according to the quality score of each image sub-region includes:
and acquiring a total score of the first image according to the weight and the quality score of each image subregion, wherein the weight of each image subregion corresponds to the position of the image subregion in the first image.
The weight of each image sub-region may be preset depending on the position of the image sub-region in the first image, for example: in an actual monitoring or photographing scene, the upper part of the image often corresponds to the sky or the top of a room, and the lower part of the image often corresponds to a person or a valid object such as a vehicle, so that the weight of the upper part of the image can be set to be smaller than the weight of the lower part of the image. Of course, these are only a simple example. The weight of each image sub-region may be specifically set according to the requirements of the application scenario.
The above-mentioned obtaining the total score of the first image according to the weight and the quality score of each image subregion may be that the quality scores are weighted according to the weight of each image subregion and summed to obtain the total score of the first image. In addition, in the embodiment of the present invention, the larger the weight is, the more important the image sub-region is represented.
In this embodiment, the total score of the first image is obtained according to the weight and the quality score of each image sub-region, so that the total score of the image can be more finely controlled.
Optionally, the weight of the first target image subregion is determined according to a first weight and a second weight, the first weight is preset according to the position of the target image subregion in the image, and the second weight is determined according to the content analysis result of the second image;
the first target image sub-area is any image sub-area in the first image, and the second image is an image captured before the first image.
The first target image sub-region is any image sub-region in the first image, and it is understood that the weight of any image sub-region in the first image may be determined in the manner of the first target image sub-region.
The second image may be an image in the same video as the first image, and the second image is acquired before the first image. For example: the second image is one or more frame images prior to the first image.
The weight of the first target image sub-region is determined according to the first weight and the second weight, and may be that the weight of the first target image sub-region is equal to a sum of the first weight and the second weight, or the weight of the first target image sub-region is a value obtained by normalizing the sum of the first weight and the second weight.
The above-mentioned second weight is determined depending on the content analysis result of the second image, and may be set according to the content analysis result of the second image after the content analysis operation is performed on the second image, and thus, the second weight may also be referred to as a feedback weight.
In this embodiment, since the second weight is determined according to the content analysis result of the second image, the weight of the first target image sub-region can be more accurate.
Optionally, the content analysis result indicates that a second target image subregion of the second image comprises a target object, the position of the second target image subregion in the second image is the same as the position of the first target image subregion in the first image, and the second weight is in negative correlation with the time interval between the first image and the second image.
The target object may be a preset monitored object or an image object conforming to preset characteristics, such as a person, a vehicle, and the like.
The position of the second target image sub-region in the second image may be the same as the position of the first target image sub-region in the first image, and the second target image sub-region may be the same position region in different images.
The above-mentioned second weight being negatively correlated with the temporal interval between said first image and said second image may be such that the above-mentioned second weight is larger when the first image is closer to said second image (the interval between the first image and the second image is smaller or not) and vice versa. Of course, the time interval here may be represented by the number of interval image frames between the first image and the second image. This is achieved in that the closer the first image is to said second image, the greater, i.e. more important, said second weight is, and vice versa, the smaller.
In this embodiment, since the position of the second target image subregion in the second image is the same as the position of the first target image subregion in the first image, and the second weight is negatively correlated with the time interval between the first image and the second image, the accuracy of the weight of the first target image subregion can be further improved.
One embodiment, as follows:
according to the actual service scene, aiming at each image subregion IsImportance of position on first image presets weight alphas. Wherein alpha iss＝αspace+αfeedback。αspaceThe first weight (or referred to as spatial weight) represents the weight of each subregion in image space, and the value range may be 0 ≦ αspace≤1；αfeedbackThe second weight (or referred to as feedback weight) represents the influence of the actual target position on the quality evaluation of the subsequent image, and the value range may be 0.001 ≦ αfeedbackLess than or equal to 0.5. Wherein alpha isfeedbackThe parameter acquisition method may be as follows:
assuming each continuous m frames as a time statistic period, acquiring the position of the target found by the current frame from the content analysis result, and recording the position as a key position, such as the position of the sub-region of the second target image;
calculating the feedback weight of the key position (the position of the first target image subregion) in the time statistical period according to an exponential decay method for the subregion where the target position is located:
Figure BDA0002583871970000061
Figure BDA0002583871970000062
αfeedback(t)＝exp[-θ(t+l)]
alpha abovefeedback(t) denotes alpha in the image subregion over time tfeedbackThe weight decays with time, alpha of the region where the new object is locatedfeedbackThe attenuation is 0.001 after m frames from 0.5.
Further, each image subregion I is obtainedsCorresponding alphas＝αspace+αfeedbackThereafter, normalization processing can be performed to achieve
Figure BDA0002583871970000071
Wherein alpha isiRepresenting the weight of the ith image sub-region.
In the embodiment of the present invention, the second weight is not limited to be set by the above formula, for example: setting the minimum value and the maximum value of the second weight as multiple levels, reducing the value of the second weight by one level every time an image is spaced between the first image and the second image, taking the maximum value as 0.5 and the minimum value as 0.1 as an example, when no spaced image exists between the first image and the second image, setting the second weight as 0.5, and when an image is spaced between the first image and the second image by 1 frame, setting the second weight as 0.4, and then reducing the second weight.
Further, when determining the second weight, it is not limited that the content analysis result indicates that the second target image sub-region of the second image includes a target object, for example: when the second image includes the target object, the second weights of the image sub-regions of the first image may be increased, and vice versa, so as to increase or decrease the overall weight of the first image according to the content analysis result of the second image.
Further, the above-mentioned second image may be an image in which the presence of the target object is found.
Taking fig. 2 as an example, the embodiment of the present invention may include a camera module, a video decoding module, a quality screening module, and a content analysis module, where:
the camera module can be built-in or external hardware of the electronic equipment, and can acquire images in real time;
the video decoding module can be used for decoding the video stream from the camera module and converting the video stream into independent images of each frame;
the quality screening module is used for obtaining the quality scores of the images, the used quality evaluation algorithm packets can be increased and modified according to the service requirements, and one or more different quality evaluation algorithms can be used for carrying out regional independent statistics and comprehensive summarization on the images;
and the content analysis module is used for analyzing the image which is judged to accord with the picture quality by the quality screening module and outputting an analysis result. Meanwhile, the content analysis module feeds back the content analysis result of the found target object to the quality screening module, for example, the content analysis result indicates the area where the target object is located, and the quality screening module performs exponential decay weighting on the image quality of the area in a certain subsequent continuous frame interval.
Thus, the weight of the image can be more accurate through the feedback of the content analysis module.
Of course, in some scenes or for some images, the second weight may not be set, i.e. only the first weight may be set, for example: the target object does not exist in the multi-frame image in front of the first image, and the second weight may not be set.
As an alternative implementation, there is an overlapping region between adjacent image sub-regions in the S image sub-regions.
The overlap region of the adjacent image sub-regions may be an adjacent region of the adjacent image sub-regions.
For example: taking the above S as 4 as an example, assuming that the first image from the video decoding is I, the sub-region division is performed on I by m rows and n columns. After the division, the total number of s is m × n image sub-regions, and the image sub-regions are overlapped with each other by a width of t pixels. The parameters m, n, and t are preset values according to actual service needs, wherein the overlap condition of the partitioned sub-regions is shown in fig. 3.
In the embodiment, because the adjacent image subregions have the overlapping region, when the quality of each subregion is evaluated, the continuity of the evaluated image content of each image subregion can be ensured, so that the accuracy of the overall image evaluation is improved.
As an optional implementation, the calculating the quality score of each image sub-region includes:
for each image sub-region, a quality score is calculated for the image sub-region using one or more image quality discrimination algorithms.
And each algorithm may set a corresponding weight when multiple algorithms are used.
For example: can pass through
Figure BDA0002583871970000081
Total of j 1,2, …, k image quality discrimination algorithms, QsRepresenting a quality score, f, of a certain image sub-regionj(. to) shows a specific algorithm implementation, ωjThe corresponding weight of the algorithm is represented,
Figure BDA0002583871970000082
it should be noted that, in the embodiment of the present invention, the image quality discrimination algorithm includes, but is not limited to, Laplacian algorithm and Sobel algorithm.
In this embodiment, the quality score of the image sub-region can be calculated by a plurality of algorithms, so that the accuracy of the quality score of the image sub-image can be further improved.
Furthermore, in the embodiment of the invention, the quality discrimination algorithm for calculating the quality score of the image sub-region can be modified or replaced according to the actual service requirement or the type of the image, so that the upgrading of the algorithm package is facilitated on the premise of not changing the hardware of the electronic equipment at the later stage, and more image discrimination indexes such as discrimination of brightness, color and the like are increased.
In the embodiment of the invention, the first image after decoding is subjected to region division to obtain S image subregions; calculating a quality score for each image sub-region; acquiring a total score of the first image according to the quality score of each image subregion; performing a content analysis operation on the first image in the case that the total score is greater than or equal to a preset threshold; discarding the first image if the total score is less than the preset threshold. Therefore, only the images with the total scores larger than or equal to the preset threshold value are subjected to content analysis, so that the power consumption of the image content analysis can be reduced.
Referring to fig. 4, fig. 4 is a flowchart of another image content analysis method according to the present invention, as shown in fig. 4, including the following steps:
step 401, decoding and image preprocessing are performed on a video from camera hardware of electronic equipment, and an image I is obtained in a circulating mode;
step 402, performing subregion division on the I image to obtain s image subregions, wherein the resolution of each image subregion is u × v. Presetting weight values according to positions of different subregions in the image
Figure BDA0002583871970000091
For example, the upper part of the image close to the picture is sky and has low importance, and the lower part of the image close to the picture is a person moving area to be monitored and has high importanceTherefore, the spatial weight α can be determined according to the service requirementspace. The quality screening module shown in fig. 2 receives the target position fed back by the subsequent content analysis module, such as the target ROI position obtained by the subsequent Yolo algorithm, and then obtains α by using the exponential decay methodfeedback. For each sub-region alphas＝αspace+αfeedbackAnd carrying out normalization processing to obtain the weight of each image subregion.
And step 403, acquiring the total score of the image by using Laplacian and Sobel algorithms.
Specifically, Laplacian and Sobel algorithms are comprehensively used for ambiguity judgment, and the weights between the two algorithms are respectively omega1And ω2And ω is1+ω2＝1。
Wherein for each sub-area Is：
Using the Laplacian algorithm f1(. The variance value of the image second derivative matrix is obtained as an evaluation index;
using Sobel algorithm f2(. The mean value of the difference matrix of the acquisition image is regarded as the evaluation index;
local evaluation index Q of summary subareass＝ω1×f1(·)+ω2×f2(·)
Then, summarizing all image subregions according to the weight to obtain a total score QTotalSpecifically, the quality scores of the image sub-regions may be multiplied by corresponding weights, and then summed.
And step 404, performing threshold judgment and decision on the total score.
This step may be based on the final total score QTotalWhether the frame image enters a subsequent content analysis link or not is judged, and the following steps can be specifically adopted:
Figure BDA0002583871970000101
wherein, TThresholdRepresenting the above-mentioned preset threshold.
Therefore, qualified images can be sent to the content analysis module for subsequent calculation, and unqualified images are discarded, so that the power consumption of image content analysis is reduced.
Referring to fig. 5, fig. 5 is a structural diagram of an image content analysis apparatus according to an embodiment of the present invention, and as shown in fig. 5, the image content analysis apparatus 500 includes:
a dividing module 501, configured to perform region division on the decoded first image to obtain S image sub-regions, where S is an integer greater than 1;
a calculation module 502 for calculating a quality score for each image sub-region;
an obtaining module 503, configured to obtain a total score of the first image according to the quality score of each image sub-region;
an analysis module 504, configured to perform a content analysis operation on the first image if the total score is greater than or equal to a preset threshold;
a discarding module 505, configured to discard the first image if the total score is smaller than the preset threshold.
Optionally, the obtaining module 503 is configured to obtain a total score of the first image according to the weight and the quality score of each image sub-region, where the weight of each image sub-region corresponds to a position of the image sub-region in the first image.
Optionally, the weight of the first target image subregion is determined according to a first weight and a second weight, the first weight is preset according to the position of the target image subregion in the image, and the second weight is determined according to the content analysis result of the second image;
the first target image sub-area is any image sub-area in the first image, and the second image is an image captured before the first image.
Optionally, the content analysis result indicates that a second target image subregion of the second image comprises a target object, the position of the second target image subregion in the second image is the same as the position of the first target image subregion in the first image, and the second weight is in negative correlation with the time interval between the first image and the second image.
Optionally, there is an overlapping region between adjacent image sub-regions in the S image sub-regions.
The image content analysis device provided by the embodiment of the present invention can implement each process in the method embodiment of fig. 1, and is not described here again to avoid repetition.
The image content analysis device in the embodiment of the present invention may be a device, or may be a component, an integrated circuit, or a chip in an electronic apparatus.
Referring to fig. 6, fig. 6 is a structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device 600 includes: a memory 601, a processor 602, and a program or instructions stored on the memory 601 and executable on the processor 602, the program or instructions implementing the steps in the image content analysis method described above when executed by the processor 602.
The embodiment of the present invention further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction implements each process of the embodiment of the image content analysis method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (12)

1. An image content analysis method, comprising:
dividing the decoded first image into regions to obtain S image subregions, wherein S is an integer greater than 1;
calculating a quality score for each image sub-region;
acquiring a total score of the first image according to the quality score of each image subregion;
performing a content analysis operation on the first image in the case that the total score is greater than or equal to a preset threshold;
discarding the first image if the total score is less than the preset threshold.
2. The method of claim 1, wherein said obtaining a total score for the first image based on the quality score for each image sub-region comprises:
and acquiring a total score of the first image according to the weight and the quality score of each image subregion, wherein the weight of each image subregion corresponds to the position of the image subregion in the first image.
3. The method of claim 2, wherein the weight of the first target image subregion is determined according to a first weight that is preset according to a position of the target image subregion in the image and a second weight that is determined according to a content analysis result of the second image;
the first target image sub-area is any image sub-area in the first image, and the second image is an image captured before the first image.
4. The method of claim 3, wherein the content analysis result indicates that a second target image subregion of the second image comprises a target object, the second target image subregion is located in the second image at the same position as the first target image subregion in the first image, and the second weight is negatively correlated with a temporal interval between the first image and the second image.
5. The method of any one of claims 1 to 4, wherein there is an overlap region between adjacent image sub-regions of the S image sub-regions.
6. An image content analysis apparatus, comprising:
the image decoding device comprises a dividing module, a decoding module and a decoding module, wherein the dividing module is used for dividing a decoded first image into S image sub-regions to obtain S image sub-regions, and S is an integer larger than 1;
the calculating module is used for calculating the quality score of each image subregion;
the acquisition module is used for acquiring the total score of the first image according to the quality score of each image subregion;
the analysis module is used for executing content analysis operation on the first image under the condition that the total score is greater than or equal to a preset threshold value;
a discarding module, configured to discard the first image if the total score is less than the preset threshold.
7. The apparatus of claim 6, wherein the obtaining module is configured to obtain a total score for the first image based on the weight and the quality score for each image subregion, wherein the weight for each image subregion corresponds to a position of the image subregion in the first image.
8. The apparatus of claim 7, wherein the weight of the first target image subregion is determined according to a first weight preset according to a position of the target image subregion in the image and a second weight determined according to a content analysis result of the second image;
the first target image sub-area is any image sub-area in the first image, and the second image is an image captured before the first image.
9. The apparatus of claim 8, wherein the content analysis result indicates that a second target image subregion of the second image comprises a target object, the second target image subregion is located in the second image at the same position as the first target image subregion in the first image, and the second weight is negatively correlated with a temporal interval between the first image and the second image.
10. The apparatus of any one of claims 6 to 9, wherein there is an overlap region for adjacent image sub-regions of the S image sub-regions.
11. An electronic device, comprising: memory, processor and a program or instructions stored on the memory and executable on the processor, which when executed by the processor implement the steps in the image content analysis method as claimed in any one of claims 1 to 5.
12. A readable storage medium, characterized in that the readable storage medium has stored thereon a program or instructions which, when executed by a processor, implement the steps in the image content analysis method according to any one of claims 1 to 5.
CN202010675459.7A 2020-07-14 2020-07-14 Image content analysis method, image content analysis device, electronic equipment and storage medium Active CN113938671B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202010675459.7A CN113938671B (en) 2020-07-14 2020-07-14 Image content analysis method, image content analysis device, electronic equipment and storage medium
PCT/CN2021/106200 WO2022012573A1 (en) 2020-07-14 2021-07-14 Image processing method and apparatus, electronic device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010675459.7A CN113938671B (en) 2020-07-14 2020-07-14 Image content analysis method, image content analysis device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113938671A true CN113938671A (en) 2022-01-14
CN113938671B CN113938671B (en) 2023-05-23

Family

ID=79273766

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010675459.7A Active CN113938671B (en) 2020-07-14 2020-07-14 Image content analysis method, image content analysis device, electronic equipment and storage medium

Country Status (2)

Country Link
CN (1) CN113938671B (en)
WO (1) WO2022012573A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116740063B (en) * 2023-08-14 2023-11-14 山东众志电子有限公司 Glass fiber yarn production quality detection method based on machine vision

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011151653A (en) * 2010-01-22 2011-08-04 Mitsumi Electric Co Ltd Apparatus, method and program for control of image quality
CN104079925A (en) * 2014-07-03 2014-10-01 中国传媒大学 Ultrahigh definition video image quality objective evaluation method based on visual perception characteristic
US20170154415A1 (en) * 2015-11-30 2017-06-01 Disney Enterprises, Inc. Saliency-weighted video quality assessment
US20170178339A1 (en) * 2014-02-11 2017-06-22 Alibaba Group Holding Limited Grading method and device for digital image quality
CN106934790A (en) * 2015-12-30 2017-07-07 浙江大华技术股份有限公司 A kind of evaluation method of image definition, the automatic method for focusing on and related device
CN108108450A (en) * 2017-12-27 2018-06-01 珠海市君天电子科技有限公司 The method and relevant device of image procossing
CN108174185A (en) * 2016-12-07 2018-06-15 中兴通讯股份有限公司 A kind of photographic method, device and terminal
CN108898600A (en) * 2018-07-11 2018-11-27 上饶师范学院 Image quality evaluating method and device
US20180350106A1 (en) * 2017-06-05 2018-12-06 Qualcomm Incorporated Systems and methods for producing image feedback
CN109509201A (en) * 2019-01-04 2019-03-22 北京环境特性研究所 A kind of SAR image quality evaluating method and device
CN110838120A (en) * 2019-11-18 2020-02-25 方玉明 Weighting quality evaluation method of asymmetric distortion three-dimensional video based on space-time information
CN110858286A (en) * 2018-08-23 2020-03-03 杭州海康威视数字技术股份有限公司 Image processing method and device for target recognition
WO2020073505A1 (en) * 2018-10-11 2020-04-16 平安科技（深圳）有限公司 Image processing method, apparatus and device based on image recognition, and storage medium
CN111182212A (en) * 2019-12-31 2020-05-19 Oppo广东移动通信有限公司 Image processing method, image processing apparatus, storage medium, and electronic device
CN111401324A (en) * 2020-04-20 2020-07-10 Oppo广东移动通信有限公司 Image quality evaluation method, device, storage medium and electronic equipment

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101277341B1 (en) * 2011-12-27 2013-06-20 연세대학교 산학협력단 Method for estimating image quality of image sequence, apparatus and method for estimating image quality of image frame
CN109215028A (en) * 2018-11-06 2019-01-15 福州大学 A kind of multiple-objection optimization image quality measure method based on convolutional neural networks
CN109685772B (en) * 2018-12-10 2022-06-14 福州大学 No-reference stereo image quality evaluation method based on registration distortion representation

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011151653A (en) * 2010-01-22 2011-08-04 Mitsumi Electric Co Ltd Apparatus, method and program for control of image quality
US20170178339A1 (en) * 2014-02-11 2017-06-22 Alibaba Group Holding Limited Grading method and device for digital image quality
CN104079925A (en) * 2014-07-03 2014-10-01 中国传媒大学 Ultrahigh definition video image quality objective evaluation method based on visual perception characteristic
US20170154415A1 (en) * 2015-11-30 2017-06-01 Disney Enterprises, Inc. Saliency-weighted video quality assessment
CN106934790A (en) * 2015-12-30 2017-07-07 浙江大华技术股份有限公司 A kind of evaluation method of image definition, the automatic method for focusing on and related device
CN108174185A (en) * 2016-12-07 2018-06-15 中兴通讯股份有限公司 A kind of photographic method, device and terminal
US20180350106A1 (en) * 2017-06-05 2018-12-06 Qualcomm Incorporated Systems and methods for producing image feedback
CN108108450A (en) * 2017-12-27 2018-06-01 珠海市君天电子科技有限公司 The method and relevant device of image procossing
CN108898600A (en) * 2018-07-11 2018-11-27 上饶师范学院 Image quality evaluating method and device
CN110858286A (en) * 2018-08-23 2020-03-03 杭州海康威视数字技术股份有限公司 Image processing method and device for target recognition
WO2020073505A1 (en) * 2018-10-11 2020-04-16 平安科技（深圳）有限公司 Image processing method, apparatus and device based on image recognition, and storage medium
CN109509201A (en) * 2019-01-04 2019-03-22 北京环境特性研究所 A kind of SAR image quality evaluating method and device
CN110838120A (en) * 2019-11-18 2020-02-25 方玉明 Weighting quality evaluation method of asymmetric distortion three-dimensional video based on space-time information
CN111182212A (en) * 2019-12-31 2020-05-19 Oppo广东移动通信有限公司 Image processing method, image processing apparatus, storage medium, and electronic device
CN111401324A (en) * 2020-04-20 2020-07-10 Oppo广东移动通信有限公司 Image quality evaluation method, device, storage medium and electronic equipment

Also Published As

Publication number Publication date
CN113938671B (en) 2023-05-23
WO2022012573A1 (en) 2022-01-20

Similar Documents

Publication Publication Date Title
CN110099222B (en) Exposure adjusting method and device for shooting equipment, storage medium and equipment
CN110839129A (en) Image processing method and device and mobile terminal
CN111770285B (en) Exposure brightness control method and device, electronic equipment and storage medium
US20050286802A1 (en) Method for detecting and selecting good quality image frames from video
CN111988561B (en) Adaptive adjustment method and device for video analysis, computer equipment and medium
Shi et al. Automatic image quality improvement for videoconferencing
CN110263699B (en) Video image processing method, device, equipment and storage medium
CN108335272B (en) Method and device for shooting picture
CN106651797B (en) Method and device for determining effective area of signal lamp
CN112449117B (en) Focusing step length determining method and device, storage medium and electronic device
CN109960969A (en) The method, apparatus and system that mobile route generates
CN113132695A (en) Lens shadow correction method and device and electronic equipment
CN114302226B (en) Intelligent cutting method for video picture
CN111445487A (en) Image segmentation method and device, computer equipment and storage medium
CN113938671A (en) Image content analysis method and device, electronic equipment and storage medium
CN113628259A (en) Image registration processing method and device
US20220114736A1 (en) Method and system for motion segmentation
CN109672829A (en) Method of adjustment, device, storage medium and the terminal of brightness of image
CN105631419B (en) Face identification method and device
CN111147693B (en) Noise reduction method and device for full-size photographed image
CN113613005A (en) Video denoising method and device based on time domain filtering
CN110971825A (en) Image correction method, electronic device and storage medium
CN111754417B (en) Noise reduction method for video image, video matting method, device and electronic system
CN117835053B (en) Switching method and device of wide dynamic mode
CN112822410B (en) Focusing method, focusing device, electronic device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant