CN115375886A - Data acquisition method and system based on cloud computing service - Google Patents
Data acquisition method and system based on cloud computing service Download PDFInfo
- Publication number
- CN115375886A CN115375886A CN202210884329.3A CN202210884329A CN115375886A CN 115375886 A CN115375886 A CN 115375886A CN 202210884329 A CN202210884329 A CN 202210884329A CN 115375886 A CN115375886 A CN 115375886A
- Authority
- CN
- China
- Prior art keywords
- image data
- data acquisition
- image
- target
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a data acquisition method and system based on cloud computing service, and relates to the technical field of data processing. In the invention, an image data set sent by each target data acquisition terminal device in a plurality of data acquisition terminal devices is respectively obtained, and at least two image data sets corresponding to at least two target data acquisition terminal devices are obtained; determining image importance degree information corresponding to each of at least two image data sets; and for each image data set of at least two image data sets, screening multiple frames of images to be processed included in the image data set based on the image importance degree information corresponding to the image data set to obtain a target image data set corresponding to the image data set. Based on the method, the problem that the screening reliability of the acquired image data is poor in the prior art can be solved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a data acquisition method and system based on cloud computing service.
Background
With the continuous development of image processing technology, the application field of the image processing technology is continuously expanded, for example, image monitoring based on image data acquisition is correspondingly applied in more fields. However, in the prior art, screening is generally performed only depending on the similarity between image data, so that there is a problem that the screening reliability is poor.
Disclosure of Invention
In view of the above, the present invention provides a data acquisition method and system based on cloud computing service to solve the problem of poor screening reliability of image data in the prior art.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a data acquisition method based on cloud computing service is applied to a cloud computing server, the cloud computing server is in communication connection with a plurality of data acquisition terminal devices, and the data acquisition method based on the cloud computing service comprises the following steps:
respectively acquiring an image data set sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices, wherein each image data set comprises a plurality of frames of images to be processed;
determining image importance degree information corresponding to each image data set in the at least two image data sets;
and for each image data set of the at least two image data sets, based on the image importance degree information corresponding to the image data set, performing screening processing on multiple frames of images to be processed included in the image data set to obtain a target image data set corresponding to the image data set, wherein each target image data set includes at least one frame of image to be processed.
In some preferred embodiments, in the data acquisition method based on cloud computing service, the step of respectively obtaining an image data set sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices includes:
judging whether image data acquisition processing is needed, and generating corresponding image data acquisition notification information when the image data acquisition processing is needed;
the image data acquisition notification information is respectively sent to each target data acquisition terminal device in the plurality of data acquisition terminal devices, wherein each target data acquisition terminal device is used for acquiring image data of the corresponding data acquisition area after receiving the image data acquisition notification information to obtain a corresponding image data set;
and respectively acquiring an image data set acquired and sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices based on the image data acquisition notification information to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices.
In some preferred embodiments, in the data collecting method based on cloud computing service, the step of determining whether image data collecting processing is required, and generating corresponding image data collecting notification information when the image data collecting processing is required includes:
judging whether an image data acquisition request instruction is received or not, and determining that image data acquisition processing is required when the image data acquisition request instruction is received;
when image data acquisition processing is needed, analyzing the image data acquisition request instruction to obtain at least two pieces of target equipment identity information corresponding to the image data acquisition request instruction, and determining at least two corresponding pieces of target data acquisition terminal equipment in the plurality of data acquisition terminal equipment based on the at least two pieces of target equipment identity information;
and generating image data acquisition notification information of the at least two target data acquisition terminal devices.
In some preferred embodiments, in the data acquisition method based on cloud computing service, the step of generating the image data acquisition notification information of the at least two target data acquisition terminal devices includes:
determining a data acquisition area corresponding to each of the at least two target data acquisition terminal devices, respectively determining an internal path of each target area in the data acquisition area corresponding to each target data acquisition terminal device, and determining a connection path of each target area connected between the data acquisition areas corresponding to each two target data acquisition terminal devices;
traversing each target area internal path and each target area connecting path to obtain at least one path traversal combination, wherein each path traversal combination does not comprise two identical target area internal paths or two identical target area connecting paths;
for each path traversal combination in the at least one path traversal combination, counting the total path length of each target area internal path and/or each target area connection path included in the path traversal combination, and determining a path traversal combination with the maximum corresponding total path length in the at least one path traversal combination as the target path traversal combination;
determining the total passing time length of each target area internal path and/or each target area connecting path included in the target path traversal combination, and calculating the product of the total passing time length and a preset time length redundancy parameter to obtain a corresponding total passing time length updating value, wherein the time length redundancy parameter is greater than or equal to 1;
and generating image data acquisition notification information of the at least two target data acquisition terminal devices based on the total passage time length updating value, wherein each target data acquisition terminal device is used for acquiring image data of a corresponding data acquisition area based on the total passage time length updating value after receiving the image data acquisition notification information to obtain a corresponding image data set, so that the total time length of the images to be processed included in the image data set is the total passage time length updating value.
In some preferred embodiments, in the data acquisition method based on the cloud computing service, the step of determining, for each of the at least two image data sets, image importance degree information corresponding to the image data set includes:
for each two target data acquisition terminal devices in the at least two target data acquisition terminal devices, determining historical region correlation degree information between two data acquisition regions corresponding to the two target data acquisition terminal devices, wherein the historical region correlation degree information is determined based on two historical target image data sets acquired by the corresponding two target data acquisition terminal devices;
and determining image importance degree information corresponding to the image data set corresponding to each target data acquisition terminal device based on historical region correlation degree information between the data acquisition regions corresponding to each two target data acquisition terminal devices in the at least two target data acquisition terminal devices.
In some preferred embodiments, in the data acquisition method based on cloud computing service, the step of determining, based on historical region correlation degree information between data acquisition regions corresponding to each two target data acquisition terminal devices of the at least two target data acquisition terminal devices, image importance degree information corresponding to an image data set corresponding to each target data acquisition terminal device includes:
for each target data acquisition terminal device in the at least two target data acquisition terminal devices, determining an average value of the historical region correlation degree information between the target data acquisition terminal device and two data acquisition regions corresponding to each other target data acquisition terminal device to obtain historical region correlation degree average value information corresponding to the target data acquisition terminal device;
and for each target data acquisition terminal device, determining image importance degree information corresponding to an image data set corresponding to the target data acquisition terminal device based on historical region correlation degree mean value information corresponding to the target data acquisition terminal device, wherein positive correlation exists between the image importance degree information and the historical region correlation degree mean value information.
In some preferred embodiments, in the data acquisition method based on cloud computing service, the step of, for each image data set of the at least two image data sets, performing screening processing on multiple frames of images to be processed included in the image data set based on the image importance information corresponding to the image data set to obtain a target image data set corresponding to the image data set includes:
for each image data set in the at least two image data sets, performing similarity calculation operation on every two frames of images to be processed in multiple frames of images to be processed included in the image data set to obtain image similarity between every two frames of images to be processed included in the image data set;
for each image data set of the at least two image data sets, determining a screening proportionality coefficient corresponding to the image data set based on image importance degree information corresponding to the image data set, wherein the screening proportionality coefficient is positively correlated with the image importance degree information;
for each image data set of the at least two image data sets, respectively calculating an average value of image similarity between each frame of image to be processed and each other frame of image to be processed in a plurality of frames of images to be processed included in the image data set to obtain an image similarity average value corresponding to the image to be processed, respectively determining a relative size relationship between the image similarity average value corresponding to each frame of image to be processed and a preset similarity threshold value, and determining the image to be processed of which the corresponding image similarity average value is greater than or equal to the similarity threshold value as a target image to be processed;
and for each image data set of the at least two image data sets, based on an image similarity mean value corresponding to each frame of target images to be processed, sequencing each frame of target images to be processed corresponding to the image data set to obtain a sequence of images to be processed corresponding to the image data set, and based on a screening scale coefficient corresponding to the image data set, screening the sequence of images to be processed to obtain a target image data set corresponding to the image data set, wherein a ratio of the number of frames of the images to be processed included in the image data set to the number of frames of the images to be processed included in the target image data set is less than or equal to the screening scale coefficient.
The embodiment of the invention also provides a data acquisition system based on cloud computing service, which is applied to a cloud computing server, wherein the cloud computing server is in communication connection with a plurality of data acquisition terminal devices, and the data acquisition system based on the cloud computing service comprises:
the image data acquisition module is used for respectively acquiring an image data set sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices, wherein each image data set comprises a plurality of frames of images to be processed;
the image importance degree determining module is used for determining image importance degree information corresponding to each image data set in the at least two image data sets;
and the image data screening processing module is used for screening multiple frames of images to be processed included in the image data set according to the image importance degree information corresponding to the image data set aiming at each of the at least two image data sets to obtain a target image data set corresponding to the image data set, wherein each target image data set includes at least one frame of image to be processed.
In some preferred embodiments, in the data acquisition system based on cloud computing service, the image data acquisition module is specifically configured to:
judging whether image data acquisition processing is needed, and generating corresponding image data acquisition notification information when the image data acquisition processing is needed;
the image data acquisition notification information is respectively sent to each target data acquisition terminal device in the plurality of data acquisition terminal devices, wherein each target data acquisition terminal device is used for acquiring image data of the corresponding data acquisition area after receiving the image data acquisition notification information to obtain a corresponding image data set;
and respectively acquiring an image data set acquired and sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices based on the image data acquisition notification information to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices.
In some preferred embodiments, in the data acquisition system based on cloud computing service, the image data screening processing module is specifically configured to:
for each image data set in the at least two image data sets, performing similarity calculation operation on every two frames of images to be processed in multiple frames of images to be processed included in the image data set to obtain image similarity between every two frames of images to be processed included in the image data set;
for each image data set of the at least two image data sets, determining a screening proportionality coefficient corresponding to the image data set based on image importance degree information corresponding to the image data set, wherein the screening proportionality coefficient is positively correlated with the image importance degree information;
for each image data set of the at least two image data sets, respectively calculating an average value of image similarity between each frame of image to be processed and each other frame of image to be processed in a plurality of frames of images to be processed included in the image data set to obtain an image similarity average value corresponding to the image to be processed, respectively determining a relative size relationship between the image similarity average value corresponding to each frame of image to be processed and a preset similarity threshold value, and determining the image to be processed of which the corresponding image similarity average value is greater than or equal to the similarity threshold value as a target image to be processed;
and for each image data set of the at least two image data sets, based on an image similarity mean value corresponding to each frame of target images to be processed, sequencing each frame of target images to be processed corresponding to the image data set to obtain a sequence of images to be processed corresponding to the image data set, and based on a screening scale coefficient corresponding to the image data set, screening the sequence of images to be processed to obtain a target image data set corresponding to the image data set, wherein a ratio of the number of frames of the images to be processed included in the image data set to the number of frames of the images to be processed included in the target image data set is less than or equal to the screening scale coefficient.
The data acquisition method and system based on the cloud computing service provided by the embodiment of the invention can firstly respectively acquire the image data set sent by each target data acquisition terminal device in a plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to the at least two target data acquisition terminal devices, and then can determine the image importance degree information corresponding to the image data set aiming at each image data set in the at least two image data sets, so that the multi-frame images to be processed included in the image data sets can be screened and processed aiming at each image data set in the at least two image data sets based on the image importance degree information corresponding to the image data sets to obtain the target image data set corresponding to the image data set. Therefore, when the screening processing is carried out, the image importance degree information corresponding to the image data set is used as the basis for carrying out the screening processing, so that the screening processing reliability is higher, and the problem that the screening reliability of the acquired image data is poor in the prior art is solved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a block diagram of a cloud computing server according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart illustrating steps included in a data acquisition method based on cloud computing services according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of modules included in a data acquisition system based on a cloud computing service according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a cloud computing server. Wherein the cloud computing server may include a memory and a processor.
In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software function (computer program) which can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the data collection method based on the cloud computing service provided by the embodiment of the present invention (described later).
For example, in some possible embodiments, the memory may be, but is not limited to, a random access memory, a read only memory, a programmable read only memory erasable read only memory, an electrically erasable read only memory, and the like. The processor can be a general-purpose processor, and comprises a central processing unit, a network processor, a system on chip and the like; but also a digital signal processor.
Also, the configuration shown in fig. 1 is merely an illustration, and the cloud computing server may further include more or less components than those shown in fig. 1 or have a different configuration than that shown in fig. 1, for example, may include an input/output module for receiving various inputs (input devices) and providing various outputs (output devices). One particular output mechanism may include a presentation device and an associated graphical user interface.
With reference to fig. 2, an embodiment of the present invention further provides a data acquisition method based on a cloud computing service, which is applicable to the cloud computing server. The method steps defined by the flow related to the data acquisition method based on the cloud computing service can be realized by the cloud computing server. And the cloud computing server is in communication connection with a plurality of data acquisition terminal devices.
The specific process shown in FIG. 2 will be described in detail below.
Step S110, respectively obtaining an image data set sent by each target data acquisition terminal device of the plurality of data acquisition terminal devices, and obtaining at least two image data sets corresponding to at least two target data acquisition terminal devices.
In the embodiment of the present invention, the cloud computing server may respectively obtain the image data sets sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices, so as to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices. Wherein each of the image data sets comprises a plurality of frames of images to be processed.
Step S120, determining, for each of the at least two image data sets, image importance information corresponding to the image data set.
In this embodiment of the present invention, the cloud computing server may determine, for each image data set of the at least two image data sets, image importance information corresponding to the image data set.
Step S130, for each image data set of the at least two image data sets, based on the image importance information corresponding to the image data set, performing a screening process on multiple frames of images to be processed included in the image data set to obtain a target image data set corresponding to the image data set.
In this embodiment of the present invention, the cloud computing server may, for each image data set of the at least two image data sets, perform screening processing on multiple frames of images to be processed included in the image data set based on the image importance information corresponding to the image data set, so as to obtain a target image data set corresponding to the image data set. Wherein each target image data set comprises at least one frame of image to be processed.
Based on the data acquisition method, an image data set sent by each target data acquisition terminal device in the multiple data acquisition terminal devices can be obtained first, so as to obtain at least two image data sets corresponding to the at least two target data acquisition terminal devices, and then, for each image data set in the at least two image data sets, the image importance degree information corresponding to the image data set can be determined, so that for each image data set in the at least two image data sets, based on the image importance degree information corresponding to the image data set, multiple frames of images to be processed included in the image data set are subjected to screening processing, so as to obtain a target image data set corresponding to the image data set. Therefore, when the screening processing is carried out, the image importance degree information corresponding to the image data set is used as the basis for carrying out the screening processing, so that the screening processing reliability is higher, and the problem that the screening reliability of the acquired image data is poor in the prior art is solved.
For example, in some possible embodiments, step S110 may include the following:
firstly, judging whether image data acquisition processing is needed, and generating corresponding image data acquisition notification information when the image data acquisition processing is needed;
secondly, the image data acquisition notification information is respectively sent to each target data acquisition terminal device in the plurality of data acquisition terminal devices, wherein each target data acquisition terminal device is used for acquiring image data of the corresponding data acquisition area after receiving the image data acquisition notification information to obtain a corresponding image data set;
then, an image data set acquired and sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices based on the image data acquisition notification information is acquired respectively, and at least two image data sets corresponding to at least two target data acquisition terminal devices are obtained.
For example, in some possible embodiments, the step of determining whether image data acquisition processing is required, and generating corresponding image data acquisition notification information when image data acquisition processing is required may include the following steps:
firstly, judging whether an image data acquisition request instruction is received or not, and determining that image data acquisition processing is required when the image data acquisition request instruction is received;
secondly, when image data acquisition processing is needed, analyzing the image data acquisition request instruction to obtain at least two pieces of target equipment identity information corresponding to the image data acquisition request instruction, and determining at least two corresponding pieces of target data acquisition terminal equipment in the plurality of data acquisition terminal equipment based on the at least two pieces of target equipment identity information;
then, image data acquisition notification information of the at least two target data acquisition terminal devices is generated.
For example, in some possible embodiments, the step of generating the image data acquisition notification information of the at least two target data acquisition terminal devices may include the following steps:
firstly, determining a data acquisition area corresponding to each of the at least two target data acquisition terminal devices, and respectively determining an internal path of each target area in the data acquisition area corresponding to each target data acquisition terminal device, and determining a connection path of each target area connected between the data acquisition areas corresponding to each two target data acquisition terminal devices (if the data acquisition area is smaller, the internal path of the target area may not be determined);
secondly, traversing each target area internal path and each target area connecting path to obtain at least one path traversal combination, wherein each path traversal combination does not comprise two same target area internal paths or two same target area connecting paths (each path traversal combination comprises at least one path);
then, for each path traversal combination in the at least one path traversal combination, counting the total path length of each target area internal path and/or each target area connection path included in the path traversal combination, and determining a path traversal combination with the largest corresponding total path length in the at least one path traversal combination as the target path traversal combination;
then, determining the total passing time length of each target area internal path and/or each target area connecting path included in the target path traversal combination, and calculating the product of the total passing time length and a preset time length redundancy parameter to obtain a corresponding total passing time length update value, wherein the time length redundancy parameter is greater than or equal to 1;
and finally, generating image data acquisition notification information of the at least two target data acquisition terminal devices based on the total passage time length updating value, wherein each target data acquisition terminal device is used for acquiring image data of a corresponding data acquisition area based on the total passage time length updating value after receiving the image data acquisition notification information to obtain a corresponding image data set, so that the total time length of images to be processed (the interval between time stamps of a first frame of image to be processed and a last frame of image to be processed) included in the image data set is the total passage time length updating value.
For example, in some possible embodiments, step S120 may include the following:
first, for each two target data acquisition terminal devices of the at least two target data acquisition terminal devices, determining historical region correlation degree information between two data acquisition regions corresponding to the two target data acquisition terminal devices, where the historical region correlation degree information is determined based on two historical target image data sets acquired by the corresponding two target data acquisition terminal devices (a specific determination manner is not limited, for example, a positive correlation relationship may be provided with image similarity between the two historical target image data sets, or other reference factors may be combined);
then, based on historical region correlation degree information between data acquisition regions corresponding to every two target data acquisition terminal devices in the at least two target data acquisition terminal devices, image importance degree information corresponding to an image data set corresponding to each target data acquisition terminal device is determined (for example, the greater the historical region correlation degree information is, the greater the corresponding image importance degree information is).
For example, in some possible embodiments, the step of determining, based on the historical region correlation degree information between the data acquisition regions corresponding to each two target data acquisition terminal devices of the at least two target data acquisition terminal devices, the image importance degree information corresponding to the image data set corresponding to each target data acquisition terminal device may include the following steps:
firstly, aiming at each target data acquisition terminal device in the at least two target data acquisition terminal devices, determining the average value of the historical region correlation degree information between the target data acquisition terminal device and two data acquisition regions corresponding to each other target data acquisition terminal device, and obtaining the historical region correlation degree average value information corresponding to the target data acquisition terminal device;
secondly, for each target data acquisition terminal device, determining image importance degree information corresponding to an image data set corresponding to the target data acquisition terminal device based on historical region correlation degree mean value information corresponding to the target data acquisition terminal device, wherein positive correlation exists between the image importance degree information and the historical region correlation degree mean value information.
For example, in some possible embodiments, step S130 may include the following:
firstly, for each image data set in the at least two image data sets, performing similarity calculation operation on every two frames of images to be processed in multiple frames of images to be processed included in the image data set to obtain image similarity between every two frames of images to be processed (in the multiple frames of images to be processed) included in the image data set;
secondly, for each image data set of the at least two image data sets, determining a screening scaling factor corresponding to the image data set based on the image importance information corresponding to the image data set, wherein the screening scaling factor is positively correlated with the image importance information (i.e., the larger the image importance information is, the larger the corresponding screening scaling factor is);
then, for each image data set of the at least two image data sets, respectively calculating an average value of image similarity between each frame of image to be processed and each other frame of image to be processed in a plurality of frames of images to be processed included in the image data set to obtain an image similarity average value corresponding to the image to be processed, respectively determining a relative size relationship between the image similarity average value corresponding to each frame of image to be processed and a preset similarity threshold value, and determining the image to be processed (each frame) of which the corresponding image similarity average value is greater than or equal to the similarity threshold value as a target image to be processed;
finally, for each image data set of the at least two image data sets, based on the image similarity mean value corresponding to each frame of target images to be processed, sequencing each frame of target images to be processed corresponding to the image data set to obtain a sequence of images to be processed corresponding to the image data set, and based on the screening proportionality coefficient corresponding to the image data set, performing screening processing (for example, screening out the corresponding number of images to be processed with the largest image similarity mean value) on the sequence of images to be processed to obtain a target image data set corresponding to the image data set, wherein the ratio between the number of frames of the images to be processed included in the image data set and the number of frames of the images to be processed included in the target image data set is less than or equal to the screening proportionality coefficient.
For example, in some possible embodiments, the similarity calculation operation in the above embodiments may include the following:
firstly, determining the two frames of images to be processed as a first image to be processed and a second image to be processed, performing target object contour recognition processing (such as recognizing contours of people and vehicles) on the first image to be processed to obtain a first target object contour set corresponding to the first image to be processed, and performing target object contour recognition processing on the second image to be processed to obtain a second target object contour set corresponding to the second image to be processed, wherein the first target object contour set and the second target object contour set are respectively formed on the basis of recognized target object contours;
secondly, performing contour screening processing on the first target object contour set to obtain a first target object contour screening set corresponding to the first target object contour set, and performing contour screening processing on the second target object contour set to obtain a second target object contour screening set corresponding to the second target object contour set, wherein when the contour screening processing is performed, if a contour interval between two target object contours is smaller than or equal to a preset contour interval threshold value, one of the two target object contours is screened out, and the screened out target object contour is used as a related object contour of the target object contour which is not screened out;
then, for each target object contour in the first target object contour screening set, determining the number of other target object contours of which the contour interval corresponding to the target object contour in the first target object contour set is smaller than or equal to the contour interval threshold value, and obtaining a first related object contour number statistic value corresponding to the target object contour;
then, for each target object contour in the first target object contour screening set, respectively counting the number of other target object contours, of which the contour interval corresponding to each related object contour in the first target object contour set is smaller than or equal to the contour interval threshold, to obtain a related object contour number statistical value corresponding to each related object contour corresponding to the target object contour, and calculating an average value of the related object contour number statistical values corresponding to each related object contour corresponding to the target object contour to obtain a second related object contour number statistical value corresponding to the target object contour;
further, for each target object contour in the first target object contour screening set, performing weighted fusion processing on a first related object contour number statistical value corresponding to the target object contour and a second related object contour number statistical value corresponding to the target object contour to obtain a related object contour number weighted value corresponding to the target object contour, wherein a weighting coefficient corresponding to the first related object contour number statistical value is greater than a weighting coefficient corresponding to the second related object contour number statistical value;
further, based on a related object contour quantity weighted value corresponding to each target object contour in the first target object contour screening set, at least one target object contour is determined in the first target object contour screening set and serves as at least one representative target object contour corresponding to the first target object contour screening set;
further, in the second target object contour set, determining each target object contour which is the same as the representative target object contour as a coincident target object contour corresponding to the second target object contour set, and determining a ratio between the number of the coincident target object contours and the number of the at least one representative target object contour to obtain a first ratio coefficient corresponding to the representative target object contour;
further, in the second target object contour screening set, determining each target object contour identical to the representative target object contour as a coincident target object contour corresponding to the second target object contour screening set, and determining a ratio between the number of the coincident target object contours and the number of the at least one representative target object contour to obtain a second proportionality coefficient corresponding to the representative target object contour;
and finally, carrying out weighted fusion processing on the first scale coefficient and the second scale coefficient to obtain corresponding fusion scale coefficients, and determining the image similarity between the two frames of images to be processed based on the fusion scale coefficients, wherein the image similarity and the fusion scale coefficients have positive correlation, and the weighting coefficient corresponding to the first scale coefficient is smaller than the weighting coefficient corresponding to the second scale coefficient. (in other embodiments, at least one corresponding representative target object contour may be determined for the second target object contour screening set, so that a coincidence degree between the first target object contour screening set and the second target object contour screening set may be calculated, a coincidence degree between the first target object contour screening set and the second target object contour screening set is calculated, a coincidence degree between the representative target object contour corresponding to the first target object contour screening set and the representative target object contour corresponding to the second target object contour screening set is calculated, and then, weighted fusion processing is performed on the three coincidence degrees to obtain an image similarity between the two frames of images to be processed, or obtain a positive correlation value of the image similarity between the two frames of images to be processed).
With reference to fig. 3, an embodiment of the present invention further provides a data acquisition system based on a cloud computing service, which is applicable to the cloud computing server. The data acquisition system based on the cloud computing service can comprise the following modules (software functional modules):
the image data acquisition module is used for respectively acquiring an image data set sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices, wherein each image data set comprises a plurality of frames of images to be processed;
the image importance degree determining module is used for determining image importance degree information corresponding to each image data set in the at least two image data sets;
and the image data screening processing module is used for screening multiple frames of images to be processed included in the image data set according to the image importance degree information corresponding to the image data set aiming at each of the at least two image data sets to obtain a target image data set corresponding to the image data set, wherein each target image data set includes at least one frame of image to be processed.
For example, in some possible embodiments, the image data acquisition module is specifically configured to: judging whether image data acquisition processing is needed, and generating corresponding image data acquisition notification information when the image data acquisition processing is needed; the image data acquisition notification information is respectively sent to each target data acquisition terminal device in the plurality of data acquisition terminal devices, wherein each target data acquisition terminal device is used for acquiring image data of a corresponding data acquisition area after receiving the image data acquisition notification information to obtain a corresponding image data set; and respectively acquiring an image data set acquired and sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices based on the image data acquisition notification information to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices.
For example, in some possible embodiments, the image data filtering processing module is specifically configured to: for each image data set in the at least two image data sets, performing similarity calculation operation on every two frames of images to be processed in multiple frames of images to be processed included in the image data set to obtain image similarity between every two frames of images to be processed included in the image data set; for each image data set in the at least two image data sets, determining a screening proportionality coefficient corresponding to the image data set based on image importance degree information corresponding to the image data set, wherein the screening proportionality coefficient is positively correlated with the image importance degree information; for each image data set in the at least two image data sets, respectively calculating an average value of image similarity between each frame of image to be processed and each group of other images to be processed in a plurality of frames of images to be processed included in the image data set to obtain an image similarity average value corresponding to the image to be processed, respectively determining a relative size relationship between the image similarity average value corresponding to each frame of image to be processed and a preset similarity threshold value, and determining the image to be processed of which the corresponding image similarity average value is greater than or equal to the similarity threshold value as a target image to be processed; and for each image data set of the at least two image data sets, based on an image similarity mean value corresponding to each frame of target images to be processed, sequencing each frame of target images to be processed corresponding to the image data set to obtain a sequence of images to be processed corresponding to the image data set, and based on a screening scale coefficient corresponding to the image data set, screening the sequence of images to be processed to obtain a target image data set corresponding to the image data set, wherein a ratio of the number of frames of the images to be processed included in the image data set to the number of frames of the images to be processed included in the target image data set is less than or equal to the screening scale coefficient.
In summary, according to the data acquisition method and system based on the cloud computing service provided by the present invention, an image data set sent by each target data acquisition terminal device in a plurality of data acquisition terminal devices may be obtained first, to obtain at least two image data sets corresponding to the at least two target data acquisition terminal devices, and then, for each image data set in the at least two image data sets, image importance degree information corresponding to the image data set may be determined, so that, for each image data set in the at least two image data sets, based on the image importance degree information corresponding to the image data set, a plurality of frames of images to be processed included in the image data set may be subjected to screening processing, to obtain a target image data set corresponding to the image data set. Therefore, when the screening processing is carried out, the image importance degree information corresponding to the image data set is used as the basis for carrying out the screening processing, so that the reliability of the screening processing is higher, and the problem that the screening reliability of the acquired image data is poor in the prior art is solved.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The data acquisition method based on the cloud computing service is applied to a cloud computing server, the cloud computing server is in communication connection with a plurality of data acquisition terminal devices, and the data acquisition method based on the cloud computing service comprises the following steps:
respectively acquiring an image data set sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices, wherein each image data set comprises a plurality of frames of images to be processed;
for each image data set in the at least two image data sets, determining image importance degree information corresponding to the image data set;
and for each image data set of the at least two image data sets, based on the image importance degree information corresponding to the image data set, performing screening processing on multiple frames of images to be processed included in the image data set to obtain a target image data set corresponding to the image data set, wherein each target image data set includes at least one frame of image to be processed.
2. The data acquisition method based on the cloud computing service according to claim 1, wherein the step of respectively obtaining the image data sets sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices comprises:
judging whether image data acquisition processing is needed, and generating corresponding image data acquisition notification information when the image data acquisition processing is needed;
the image data acquisition notification information is respectively sent to each target data acquisition terminal device in the plurality of data acquisition terminal devices, wherein each target data acquisition terminal device is used for acquiring image data of a corresponding data acquisition area after receiving the image data acquisition notification information to obtain a corresponding image data set;
and respectively acquiring an image data set acquired and sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices based on the image data acquisition notification information to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices.
3. The data collection method based on the cloud computing service according to claim 2, wherein the step of determining whether image data collection processing is required and generating corresponding image data collection notification information when the image data collection processing is required comprises:
judging whether an image data acquisition request instruction is received or not, and determining that image data acquisition processing is required when the image data acquisition request instruction is received;
when image data acquisition processing is required, analyzing the image data acquisition request instruction to obtain at least two pieces of target equipment identity information corresponding to the image data acquisition request instruction, and determining at least two corresponding pieces of target data acquisition terminal equipment in the plurality of data acquisition terminal equipment based on the at least two pieces of target equipment identity information;
and generating image data acquisition notification information of the at least two target data acquisition terminal devices.
4. The cloud computing service-based data collection method according to claim 3, wherein the step of generating image data collection notification information of the at least two target data collection terminal devices includes:
determining a data acquisition area corresponding to each of the at least two target data acquisition terminal devices, respectively determining an internal path of each target area in the data acquisition area corresponding to each target data acquisition terminal device, and determining a connection path of each target area connected between the data acquisition areas corresponding to each two target data acquisition terminal devices;
traversing each target area internal path and each target area connecting path to obtain at least one path traversal combination, wherein each path traversal combination does not comprise two same target area internal paths or two same target area connecting paths;
for each path traversal combination in the at least one path traversal combination, counting the total path length of each target area internal path and/or each target area connection path included in the path traversal combination, and determining a path traversal combination with the maximum corresponding total path length in the at least one path traversal combination as the target path traversal combination;
determining the total passing time length of each target area internal path and/or each target area connecting path included in the target path traversal combination, and calculating the product of the total passing time length and a preset time length redundancy parameter to obtain a corresponding total passing time length updating value, wherein the time length redundancy parameter is greater than or equal to 1;
and generating image data acquisition notification information of the at least two target data acquisition terminal devices based on the total passage time length updating value, wherein each target data acquisition terminal device is used for acquiring image data of a corresponding data acquisition area based on the total passage time length updating value after receiving the image data acquisition notification information to obtain a corresponding image data set, so that the total time length of the images to be processed included in the image data set is the total passage time length updating value.
5. The data collection method based on the cloud computing service as claimed in claim 1, wherein the step of determining, for each image data set of the at least two image data sets, the image importance degree information corresponding to the image data set comprises:
for each two target data acquisition terminal devices in the at least two target data acquisition terminal devices, determining historical region correlation degree information between two data acquisition regions corresponding to the two target data acquisition terminal devices, wherein the historical region correlation degree information is determined based on two historical target image data sets acquired by the corresponding two target data acquisition terminal devices;
and determining image importance degree information corresponding to the image data set corresponding to each target data acquisition terminal device based on historical region correlation degree information between the data acquisition regions corresponding to each two target data acquisition terminal devices in the at least two target data acquisition terminal devices.
6. The data collection method based on cloud computing services according to claim 5, wherein the step of determining the image importance degree information corresponding to the image data set corresponding to each target data collection terminal device based on historical region correlation degree information between the data collection regions corresponding to each two target data collection terminal devices of the at least two target data collection terminal devices includes:
for each target data acquisition terminal device in the at least two target data acquisition terminal devices, determining an average value of historical region correlation degree information between the target data acquisition terminal device and two data acquisition regions corresponding to each other target data acquisition terminal device to obtain historical region correlation degree average value information corresponding to the target data acquisition terminal device;
and for each target data acquisition terminal device, determining image importance degree information corresponding to an image data set corresponding to the target data acquisition terminal device based on historical region correlation degree mean value information corresponding to the target data acquisition terminal device, wherein the image importance degree information and the historical region correlation degree mean value information have positive correlation.
7. The data acquisition method based on the cloud computing service according to any one of claims 1 to 6, wherein the step of, for each of the at least two image data sets, performing screening processing on multiple frames of images to be processed included in the image data set based on the image importance information corresponding to the image data set to obtain a target image data set corresponding to the image data set includes:
for each image data set in the at least two image data sets, performing similarity calculation operation on every two to-be-processed images in the multiple to-be-processed images included in the image data set to obtain the image similarity between every two to-be-processed images included in the image data set;
for each image data set of the at least two image data sets, determining a screening proportionality coefficient corresponding to the image data set based on image importance degree information corresponding to the image data set, wherein the screening proportionality coefficient is positively correlated with the image importance degree information;
for each image data set of the at least two image data sets, respectively calculating an average value of image similarity between each frame of image to be processed and each other frame of image to be processed in a plurality of frames of images to be processed included in the image data set to obtain an image similarity average value corresponding to the image to be processed, respectively determining a relative size relationship between the image similarity average value corresponding to each frame of image to be processed and a preset similarity threshold value, and determining the image to be processed of which the corresponding image similarity average value is greater than or equal to the similarity threshold value as a target image to be processed;
and for each image data set of the at least two image data sets, based on an image similarity mean value corresponding to each frame of target images to be processed, sequencing each frame of target images to be processed corresponding to the image data set to obtain a sequence of images to be processed corresponding to the image data set, and based on a screening scale coefficient corresponding to the image data set, screening the sequence of images to be processed to obtain a target image data set corresponding to the image data set, wherein a ratio of the number of frames of the images to be processed included in the image data set to the number of frames of the images to be processed included in the target image data set is less than or equal to the screening scale coefficient.
8. The utility model provides a data acquisition system based on cloud computing service which characterized in that is applied to the cloud computing server, the cloud computing server communication connection has a plurality of data acquisition terminal equipment, the data acquisition system based on cloud computing service includes:
the image data acquisition module is used for respectively acquiring an image data set sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices, wherein each image data set comprises a plurality of frames of images to be processed;
the image importance degree determining module is used for determining image importance degree information corresponding to each image data set in the at least two image data sets;
the image data screening processing module is used for screening multiple frames of images to be processed included in the image data set based on the image importance degree information corresponding to the image data set aiming at each of the at least two image data sets to obtain a target image data set corresponding to the image data set, wherein each target image data set includes at least one frame of image to be processed.
9. The cloud computing service-based data acquisition system of claim 8, wherein the image data acquisition module is specifically configured to:
judging whether image data acquisition processing is needed, and generating corresponding image data acquisition notification information when the image data acquisition processing is needed;
the image data acquisition notification information is respectively sent to each target data acquisition terminal device in the plurality of data acquisition terminal devices, wherein each target data acquisition terminal device is used for acquiring image data of a corresponding data acquisition area after receiving the image data acquisition notification information to obtain a corresponding image data set;
and respectively acquiring an image data set acquired and sent by each target data acquisition terminal device in the plurality of data acquisition terminal devices based on the image data acquisition notification information to obtain at least two image data sets corresponding to at least two target data acquisition terminal devices.
10. The cloud computing service-based data collection system of claim 8, wherein the image data screening processing module is specifically configured to:
for each image data set in the at least two image data sets, performing similarity calculation operation on every two to-be-processed images in the multiple to-be-processed images included in the image data set to obtain the image similarity between every two to-be-processed images included in the image data set;
for each image data set of the at least two image data sets, determining a screening proportionality coefficient corresponding to the image data set based on image importance degree information corresponding to the image data set, wherein the screening proportionality coefficient is positively correlated with the image importance degree information;
for each image data set in the at least two image data sets, respectively calculating an average value of image similarity between each frame of image to be processed and each other frame of image to be processed in a plurality of frames of images to be processed included in the image data set, obtaining an image similarity average value corresponding to the image to be processed, respectively determining a relative size relationship between the image similarity average value corresponding to each frame of image to be processed and a preset similarity threshold value, and determining the image to be processed of which the corresponding image similarity average value is greater than or equal to the similarity threshold value as a target image to be processed;
and for each image data set of the at least two image data sets, sequencing each frame of target images to be processed corresponding to the image data set based on an image similarity mean value corresponding to each frame of target images to be processed to obtain a target image sequence corresponding to the image data set, and screening the image sequences to be processed based on a screening proportionality coefficient corresponding to the image data set to obtain a target image data set corresponding to the image data set, wherein the ratio of the number of frames of the images to be processed included in the image data set to the number of frames of the images to be processed included in the target image data set is less than or equal to the screening proportionality coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210884329.3A CN115375886A (en) | 2022-07-25 | 2022-07-25 | Data acquisition method and system based on cloud computing service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210884329.3A CN115375886A (en) | 2022-07-25 | 2022-07-25 | Data acquisition method and system based on cloud computing service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115375886A true CN115375886A (en) | 2022-11-22 |
Family
ID=84064189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210884329.3A Withdrawn CN115375886A (en) | 2022-07-25 | 2022-07-25 | Data acquisition method and system based on cloud computing service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115375886A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116821777A (en) * | 2023-02-28 | 2023-09-29 | 广东新禾道信息科技有限公司 | Novel basic mapping data integration method and system |
-
2022
- 2022-07-25 CN CN202210884329.3A patent/CN115375886A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116821777A (en) * | 2023-02-28 | 2023-09-29 | 广东新禾道信息科技有限公司 | Novel basic mapping data integration method and system |
| CN116821777B (en) * | 2023-02-28 | 2024-02-13 | 广东新禾道信息科技有限公司 | Novel basic mapping data integration method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114140713A (en) | Image recognition system and image recognition method | |
| CN114724215A (en) | Sensitive image identification method and system | |
| CN114925348B (en) | Security verification method and system based on fingerprint identification | |
| CN113949881B (en) | Business processing method and system based on smart city data | |
| CN114140712A (en) | Automatic image recognition and distribution system and method | |
| CN115375886A (en) | Data acquisition method and system based on cloud computing service | |
| CN116821777B (en) | Novel basic mapping data integration method and system | |
| CN113868471A (en) | Data matching method and system based on monitoring equipment relationship | |
| CN115620243B (en) | Pollution source monitoring method and system based on artificial intelligence and cloud platform | |
| CN114723456A (en) | Payment method and payment system | |
| CN115457467A (en) | Building quality hidden danger positioning method and system based on data mining | |
| CN115345621A (en) | Payment method, system and platform with payment function | |
| CN115147134A (en) | Product anti-counterfeiting tracing method and system based on industrial Internet and cloud platform | |
| CN114720812A (en) | Method and system for processing and positioning faults of power distribution network | |
| CN113537087A (en) | Intelligent traffic information processing method and device and server | |
| CN115700821B (en) | Cell identification method and system based on image processing | |
| CN115620210B (en) | Method and system for determining performance of electronic wire material based on image processing | |
| CN115082709B (en) | Remote sensing big data processing method, system and cloud platform | |
| CN114173152A (en) | Communication video screening method and system | |
| CN114140714A (en) | Data processing method and system for smart city | |
| CN117115749A (en) | Building quality global detection method and system | |
| CN114167763A (en) | Validity confirmation method of intelligent health data | |
| CN117176992A (en) | Internet-based monitoring video processing method and system | |
| CN115618028A (en) | Medical image data storage method and system | |
| CN115422384A (en) | Data processing method based on Internet and data cloud platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221122 |
|
| WW01 | Invention patent application withdrawn after publication |