CN114445751A - Method and device for extracting video key frame image contour features - Google Patents
Method and device for extracting video key frame image contour features Download PDFInfo
- Publication number
- CN114445751A CN114445751A CN202210111054.XA CN202210111054A CN114445751A CN 114445751 A CN114445751 A CN 114445751A CN 202210111054 A CN202210111054 A CN 202210111054A CN 114445751 A CN114445751 A CN 114445751A
- Authority
- CN
- China
- Prior art keywords
- image
- key frame
- video key
- frame image
- binarization processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
- G06T7/13—Edge detection
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Abstract
The present disclosure provides a method, apparatus, device, medium, and product for extracting video keyframe image contour features. The method for extracting the video key frame image contour features comprises the following steps: carrying out binarization processing on the original video key frame image; processing the image after the binarization processing by using a morphological corrosion operation; and performing XOR operation on the image processed by using the morphological erosion operation and the image processed by the binarization processing to obtain an image contour characteristic point coordinate set, and framing four polar coordinates of the upper, lower, left and right sides of the image contour characteristic point coordinate set on the original video key frame image to generate a framed labeled image. According to the scheme, the key outline information of the image is automatically acquired through the digital image processing morphological transformation operation, so that the labor consumption and the time cost are reduced, and the labeling efficiency of the outline characteristics of the image is improved.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, a medium, and a product for extracting a video key frame image contour feature.
Background
With the rapid development of the mobile internet and the 5G technology, the intelligent transformation of entity network points in the financial service industry is widely promoted, and the safe fire management business is an important guarantee for the steady production of each key part. In order to reduce the labor intensity of security, improve the monitoring efficiency and enhance the instant response capability of key early warning, an artificial intelligence technology is urgently needed to identify the scenes of fire protection service such as falling of people, flame and smoke, illegal photographing and facility damage through a video image identification technology, so that the aims of quickly responding and disposing, optimizing the service efficiency and reducing the cost of manpower and material resources are fulfilled.
Disclosure of Invention
In view of the above technical problems, the present disclosure provides a method, an apparatus, a device, a medium, and a product for extracting a video key frame image contour feature, which automatically obtain image key contour information through a digital image processing morphological transformation operation, thereby reducing human consumption and time cost and improving annotation efficiency of the image contour feature.
A first aspect of the present disclosure provides a method for extracting a video key frame image contour feature, where the method includes:
carrying out binarization processing on an original video key frame image;
processing the image after the binarization processing by using a morphological corrosion operation;
carrying out XOR operation on the image processed by using the morphological erosion operation and the image processed by the binarization operation to obtain an image contour feature point coordinate set;
and framing four polar coordinates of the image contour characteristic point coordinate set on the original video key frame image to generate a framed annotation image.
According to an embodiment of the present disclosure, before the binarizing processing on the original video key frame image, the method further includes: an original video key frame image from which image information is readily discernable is obtained from a video stream.
According to the embodiment of the present disclosure, the binarizing processing on the original video key frame image specifically includes: and carrying out binarization processing on the original video key frame image by using a threshold segmentation method.
According to an embodiment of the present disclosure, the processing the binarized image by using a morphological erosion operation specifically includes:
defining corrosion structural elements, and processing the image after the binarization processing based on morphological corrosion operation by using the defined corrosion structural elements.
The second aspect of the present disclosure provides an apparatus for extracting a video key frame image contour feature, the apparatus includes an image binarization module, a morphological erosion operation module, an image exclusive or operation module, and a polar coordinate positioning generation frame selection module, wherein:
the image binarization module is used for carrying out binarization processing on the original video key frame image;
the morphological corrosion operation module is used for processing the image after the binarization processing by using morphological corrosion operation;
the image XOR operation module is used for carrying out XOR operation on the image processed by using the morphological corrosion operation and the image processed by the binarization processing to obtain an image contour feature point coordinate set;
and the polar coordinate positioning generation frame selection module is used for framing four upper, lower, left and right polar coordinates of the image contour feature point coordinate set on the original video key frame image to generate a framed annotation image.
According to an embodiment of the present disclosure, the apparatus further comprises an image acquisition module, wherein:
the image acquisition module is used for acquiring an original video key frame image which is easy to distinguish image information from a video stream.
According to the embodiment of the present disclosure, the binarizing processing on the original video key frame image specifically includes: and carrying out binarization processing on the original video key frame image by using a threshold segmentation method.
According to an embodiment of the present disclosure, the processing the binarized image by using a morphological erosion operation specifically includes:
defining corrosion structural elements, and processing the image after the binarization processing based on morphological corrosion operation by using the defined corrosion structural elements.
A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform a network admission control method as described above.
A fourth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform a network admission control method as described above.
A fifth aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements a network admission control method as described above.
Compared with the prior art, the method, the device, the equipment, the medium and the product for extracting the outline features of the video key frame image can obtain the main outline features in the video key frame image through binaryzation and morphological corrosion operation on the basis of the original video key frame image, so that the problems existing in image data annotation framing in the field of security and fire protection business in the financial industry are solved by combining a related algorithm in digital image processing, the automation of image outline feature data annotation is realized, the annotation efficiency of the image feature data is improved, and the generation efficiency of a model training sample is further improved.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart schematically illustrating a related art artificial intelligence video image recognition method;
FIG. 2 is a flow chart schematically illustrating a method for extracting outline features of a video key frame image according to an embodiment of the present disclosure;
fig. 3 is a block diagram schematically illustrating a structure of an apparatus for extracting a video key frame image contour feature according to an embodiment of the present disclosure; and
fig. 4 schematically shows a block diagram of an electronic device implementing the method for extracting the video key frame image contour feature according to the embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
Before describing the technical solution of the present disclosure, technical terms in the field are explained as follows:
key frame: the video is a digital media file which is generated by arranging a plurality of continuous images in a period of time and by a data storage technology, and the smooth continuous visual effect is formed by performing rapid alternate playing of the images by utilizing the human eye visual persistence principle. The frame is a single image and is the basic unit of the video image, and the key frame is the frame for retaining the key information of the image;
digital image: digital images are image representation techniques that store image information in a two-dimensional digital matrix, as distinguished from analog images. The basic unit of a digital image is a pixel, i.e. an element in a two-dimensional matrix, and the coordinate and value of each element in the image matrix represent the position and the gray scale of the pixel on a two-dimensional space of the digital image;
contour: the contour is a gray difference formed by rapid change of local pixel gray steps in the digital image, and the contour information of the image is obtained by calculating an edge detection algorithm such as relatively continuous gray difference in a certain direction;
feature extraction: the feature is key information capable of describing semantic information included in an image, and is generally structured information such as gray scale distribution change, contour morphology and the like. The feature extraction is a process of processing and extracting key information in an image by using a digital image processing method according to subjective needs.
Referring to fig. 1, the current artificial intelligence video image recognition method includes: aiming at the collected original data set, firstly, an image labeling sample set is generated on the basis of manually labeling the image contour characteristics of the video key frame, the labeling sample set is divided according to the proportion to obtain a training sample set and a verification sample set, and model training and cross verification are carried out on the two sample sets to obtain a final algorithm model.
In the scheme, the obtaining of enough sample data depends on preprocessing processes such as the acquisition of training data and the manual labeling of the image contour features, and the labeling of the sample data cannot be separated from the manual operation of a person and the help of a labeling tool. The existing acquisition of training data and labeling of image contour features mainly comprise the following processes:
selecting and acquiring key frames which are easy to distinguish image information from a video stream;
manually framing key outline information by using a video image annotation tool;
formatting the marked image file;
the preprocessed image data file is used as training data and verification data, and an algorithm model is generated through algorithm model training and cross verification;
and packaging the trained algorithm model into a scene recognition program, and sending the scene recognition program to the integrated system for production.
As described in the foregoing process, in the field of security and fire protection in the financial industry, in order to obtain a mature scene recognition model, manual labeling is often performed in a large amount of sample data to obtain sufficient model training data, and the manual labeling method has the following defects:
(1) because the amount of model training sample data is often large, a large amount of human resources are consumed for manually marking the image contour characteristics;
(2) the insufficient usability of the video image key frame feature marking tool can also cause the increase of workload, and the requirement of quick marking is difficult to meet;
(3) the small local change rate of the image causes visual errors, the accuracy of manually judging the image contour is influenced to a certain extent, and finally the quality of characteristic marking is influenced.
Therefore, the way of manually labeling the image contour features is difficult to meet the actual requirements in the aspects of efficiency, quality, cost and the like, and a more efficient method for extracting the video key frame image contour features is urgently needed.
Compared with the related art, the embodiment of the disclosure provides a method, a device, equipment, a medium and a product for extracting the video key frame image contour feature, wherein the method for extracting the video key frame image contour feature comprises the following steps: acquiring an original video key frame image which is easy to distinguish image information from a video stream; carrying out binarization processing on the original video key frame image; processing the image after the binarization processing by using a morphological corrosion operation; carrying out XOR operation on the image processed by using the morphological erosion operation and the image processed by the binarization processing to obtain an image contour feature point coordinate set; and framing four polar coordinates of the image contour characteristic point coordinate set on the original video key frame image to generate a framed annotation image. According to the scheme, the main outline characteristics in the video key frame image can be obtained through binarization and morphological corrosion operation on the basis of the original video key frame image, so that the problems existing in image data labeling frame selection in the field of security and fire protection business of the financial industry are solved by combining with related algorithms in digital image processing, the automation of image outline characteristic data labeling is realized, the labeling efficiency of the image characteristic data is improved, and the generation efficiency of a model training sample is further improved.
A method, apparatus, device, medium, and product for extracting video key frame image contour features according to embodiments of the present disclosure are described in detail below with reference to fig. 2 to 4.
Fig. 2 schematically shows a flowchart of a method for extracting a video key frame image contour feature according to an embodiment of the present disclosure.
As shown in fig. 2, the embodiment provides a method for extracting a video key frame image contour feature, where the method includes operations S101 to S105, and specifically the following steps:
in operation S101, an original video key frame image from which image information is easily recognized is acquired from a video stream.
In operation S102, a binarization process is performed on the original video key frame image. For example, a binarization image segmentation method is used for carrying out binarization processing on the original video key frame image.
The method for segmenting the binary image is a threshold segmentation method, and the method for segmenting the binary image is used for carrying out binarization processing on an original video key frame image and specifically comprises the following steps: and performing binarization processing on the original video key frame image by using a threshold segmentation method.
The image is subjected to binarization processing by adopting a threshold segmentation method, and the method has the advantages of simple realization, small calculated amount and stable performance. It not only can greatly compress data volume, but also greatly simplifies analysis and processing steps. In the threshold segmentation method, a pixel set of an image is divided according to gray levels, each obtained subset forms a region corresponding to a real scene, the interior of each region has a consistent attribute, and an adjacent region does not have the consistent attribute. Such a division can be achieved by choosing one or more threshold values from the grey scale.
For example, according to the difference of the threshold selection manner, in the threshold segmentation method, the threshold may be divided into a global threshold and a local threshold. The global threshold means that the same threshold is selected for each pixel in the whole image. The local thresholding method assumes that the illumination experienced by an image in a certain area is relatively close. It scans the image with a sliding window and takes the brightness of the center point of the sliding window to compare with the brightness of other areas (called neighborhoods) in the sliding window. If the center point luminance is higher than the neighborhood luminance, the center point is marked as white, otherwise, the center point is marked as black.
In operation S103, the binarized image is processed using a morphological erosion operation.
And the image after the binarization processing is processed by using morphological corrosion operation, specifically: defining corrosion structural elements, and processing the image after the binarization processing based on morphological corrosion operation by using the defined corrosion structural elements.
In operation S104, performing an exclusive or operation on the image processed by using the morphological erosion operation and the image processed by the binarization processing to obtain an image contour feature point coordinate set;
in operation S105, four polar coordinates of the image contour feature point coordinate set are framed on the original video key frame image, and a framed annotation image is generated.
The step adds a polar coordinate positioning function of the image contour feature point coordinate set, and is to select each contour feature in the image by using a standard rectangular image frame so as to convey the result to a user-friendly display.
By means of the method for extracting the outline features of the video key frame image, the main outline features in the video key frame image can be obtained through a binarization image segmentation method and morphological corrosion operation on the basis of an original video key frame image, so that the problems existing in image data annotation framing in the field of security and fire protection business in the financial industry are solved by combining with related algorithms in digital image processing, the automation of image outline feature data annotation is realized, the tagging efficiency of image feature data is improved, and the generation efficiency of model training samples is further improved.
Based on the method for extracting the video key frame image contour features shown in fig. 2, the present disclosure also provides an apparatus for extracting the video key frame image contour features. The apparatus will be described in detail below with reference to fig. 3.
Fig. 3 schematically shows a block diagram of a structure of an apparatus for extracting a video key frame image contour feature according to an embodiment of the present disclosure.
As shown in fig. 3, this embodiment provides an apparatus 300 for extracting a video key frame image contour feature, where the apparatus 300 includes an image acquisition module 301, an image binarization module 302, a morphological erosion operation module 303, an image exclusive-or operation module 304, and a polar coordinate positioning generation frame selection module 305.
The image obtaining module 301 is configured to obtain an original video key frame image from a video stream, where the original video key frame image is easy to distinguish image information.
The image binarization module 302 is configured to perform binarization processing on the original video key frame image. For example, it is used to perform binarization processing on the original video key frame image by using a binarization image segmentation method.
The binarization image segmentation method is a threshold segmentation method, and the image binarization module 302 is specifically configured to: and carrying out binarization processing on the original video key frame image by using a threshold segmentation method.
For example, the image binarization module 302 may perform compression processing on the original video key frame image to obtain an image to be binarized; and then, processing the image to be binarized through a binarization model to obtain a binarized image.
The morphological erosion operation module 303 processes the binarized image by using a morphological erosion operation.
And the image after the binarization processing is processed by using morphological corrosion operation, specifically: defining corrosion structural elements, and processing the image after the binarization processing based on morphological corrosion operation by using the defined corrosion structural elements.
The image exclusive-or operation module 304 is configured to perform exclusive-or operation on the image processed by using the morphological erosion operation and the image processed by the binarization processing to obtain an image contour feature point coordinate set;
the polar coordinate positioning generation and frame selection module 305 is configured to frame four polar coordinates, namely, an upper polar coordinate, a lower polar coordinate, a left polar coordinate, a right polar coordinate, and a left polar coordinate, of the image contour feature point coordinate set on the original video key frame image, and generate a framed annotation image.
The polar coordinate positioning generation frame selection module 305 adds a polar coordinate positioning function to the image contour feature point coordinate set, and is to select each contour feature in the image using a standard rectangular image frame to convey a user-friendly result display.
By means of the extraction device for the video key frame image outline features, the main outline features in the video key frame image can be obtained through a binarization image segmentation method and morphological corrosion operation on the basis of an original video key frame image, so that the problems existing in image data annotation framing in the field of security and fire protection business in the financial industry are solved by combining with related algorithms in digital image processing, the automation of image outline feature data annotation is realized, the image feature data annotation efficiency is improved, and the generation efficiency of model training samples is further improved.
Fig. 4 schematically shows a block diagram of an electronic device suitable for implementing a method for extracting outline features of a video key frame image according to an embodiment of the present disclosure.
As shown in fig. 4, an electronic device 400 according to an embodiment of the present disclosure includes a processor 401 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. Processor 401 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 401 may also include onboard memory for caching purposes. Processor 401 may include a single processing unit or multiple processing units for performing the different actions of the method flows in accordance with embodiments of the present disclosure.
In the RAM403, various programs and data necessary for the operation of the electronic apparatus 400 are stored. The processor 401, ROM402 and RAM403 are connected to each other by a bus 404. The processor 401 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM402 and/or the RAM 403. Note that the programs may also be stored in one or more memories other than the ROM402 and RAM 403. The processor 401 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.
According to an embodiment of the present disclosure, electronic device 400 may also include an input/output (I/O) interface 405, input/output (I/O) interface 405 also being connected to bus 404. Electronic device 400 may also include one or more of the following components connected to I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.
The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM402 and/or RAM403 and/or one or more memories other than ROM402 and RAM403 described above.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the item recommendation method provided by the embodiment of the disclosure.
The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 401. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, downloaded and installed through the communication section 409, and/or installed from the removable medium 411. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program, when executed by the processor 401, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be appreciated by a person skilled in the art that various combinations or/and combinations of features recited in the various embodiments of the disclosure and/or in the claims may be made, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments of the present disclosure and/or the claims may be made without departing from the spirit and teachings of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.
Claims (11)
1. A method for extracting video key frame image contour features is characterized by comprising the following steps:
carrying out binarization processing on an original video key frame image;
processing the image after the binarization processing by using a morphological corrosion operation;
carrying out XOR operation on the image processed by using the morphological erosion operation and the image processed by the binarization processing to obtain an image contour feature point coordinate set;
and framing four polar coordinates of the image contour characteristic point coordinate set on the original video key frame image to generate a framed annotation image.
2. The method for extracting the outline feature of the video key frame image according to claim 1, wherein before the binarizing process of the original video key frame image, the method further comprises: an original video key frame image from which image information is readily discernable is obtained from a video stream.
3. The method for extracting the contour features of the video key frame image according to claim 1 or 2, wherein the binarizing processing is performed on the original video key frame image, specifically: and carrying out binarization processing on the original video key frame image by using a threshold segmentation method.
4. The method for extracting the contour features of the video keyframe image as claimed in claim 1 or 2, wherein the image after the binarization processing is processed by using a morphological erosion operation, specifically:
defining corrosion structural elements, and processing the image after the binarization processing based on morphological corrosion operation by using the defined corrosion structural elements.
5. The device for extracting the outline features of the video key frame image is characterized by comprising an image binarization module, a morphological erosion operation module, an image exclusive or operation module and a polar coordinate positioning generation frame selection module, wherein:
the image binarization module is used for carrying out binarization processing on the original video key frame image;
the morphological corrosion operation module is used for processing the image after the binarization processing by using morphological corrosion operation;
the image XOR operation module is used for carrying out XOR operation on the image processed by using the morphological corrosion operation and the image processed by the binarization processing to obtain an image contour feature point coordinate set;
and the polar coordinate positioning generation frame selection module is used for framing four upper, lower, left and right polar coordinates of the image contour feature point coordinate set on the original video key frame image to generate a framed annotation image.
6. The apparatus for extracting outline features of a key frame image in a video according to claim 5, further comprising an image acquisition module, wherein:
the image acquisition module is used for acquiring an original video key frame image which is easy to distinguish image information from a video stream.
7. The apparatus for extracting the outline features of the video key frame image according to claim 5 or 6, wherein the binarizing process is performed on the original video key frame image, specifically: and carrying out binarization processing on the original video key frame image by using a threshold segmentation method.
8. The apparatus for extracting the contour features of the video keyframe image as claimed in claim 5 or 6, wherein the image after the binarization processing is processed by using a morphological erosion operation, specifically:
defining corrosion structural elements, and processing the image after the binarization processing based on morphological corrosion operation by using the defined corrosion structural elements.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-4.
10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1-4.
11. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210111054.XA CN114445751A (en) | 2022-01-29 | 2022-01-29 | Method and device for extracting video key frame image contour features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210111054.XA CN114445751A (en) | 2022-01-29 | 2022-01-29 | Method and device for extracting video key frame image contour features |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114445751A true CN114445751A (en) | 2022-05-06 |
Family
ID=81371239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210111054.XA Pending CN114445751A (en) | 2022-01-29 | 2022-01-29 | Method and device for extracting video key frame image contour features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114445751A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115457448A (en) * | 2022-11-09 | 2022-12-09 | 安徽米娱科技有限公司 | Intelligent extraction system for video key frames |
-
2022
- 2022-01-29 CN CN202210111054.XA patent/CN114445751A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115457448A (en) * | 2022-11-09 | 2022-12-09 | 安徽米娱科技有限公司 | Intelligent extraction system for video key frames |
| CN115457448B (en) * | 2022-11-09 | 2023-01-31 | 安徽米娱科技有限公司 | Intelligent extraction system for video key frames |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3655923B1 (en) | Weakly supervised anomaly detection and segmentation in images | |
| CN109151501B (en) | Video key frame extraction method and device, terminal equipment and storage medium | |
| CN110148130B (en) | Method and device for detecting part defects | |
| CN110705583A (en) | Cell detection model training method and device, computer equipment and storage medium | |
| JP6240199B2 (en) | Method and apparatus for identifying object in image | |
| CN112418216B (en) | Text detection method in complex natural scene image | |
| CN112287875B (en) | Abnormal license plate recognition method, device, equipment and readable storage medium | |
| CN112861575A (en) | Pedestrian structuring method, device, equipment and storage medium | |
| CN111680610A (en) | Construction scene abnormity monitoring method and device | |
| CN110659546A (en) | Illegal booth detection method and device | |
| CN114943936A (en) | Target behavior identification method and device, electronic equipment and storage medium | |
| CN112651953A (en) | Image similarity calculation method and device, computer equipment and storage medium | |
| CN114220009A (en) | Infrared image-based wire windage yaw identification method and system | |
| CN115205780A (en) | Construction site violation monitoring method, system, medium and electronic equipment | |
| CN115761571A (en) | Video-based target retrieval method, device, equipment and storage medium | |
| CN114445751A (en) | Method and device for extracting video key frame image contour features | |
| CN115131826B (en) | Article detection and identification method, and network model training method and device | |
| CN114298992A (en) | Video frame duplication removing method and device, electronic equipment and storage medium | |
| CN114241354A (en) | Warehouse personnel behavior identification method and device, computer equipment and storage medium | |
| CN111191593A (en) | Image target detection method and device, storage medium and sewage pipeline detection device | |
| CN112464928B (en) | Digital meter reading identification method, device, equipment and storage medium | |
| CN117576632B (en) | Multi-mode AI large model-based power grid monitoring fire early warning system and method | |
| CN111062337B (en) | People stream direction detection method and device, storage medium and electronic equipment | |
| Pan et al. | Accuracy improvement of deep learning 3D point cloud instance segmentation | |
| CN113420716B (en) | Illegal behavior identification and early warning method based on improved Yolov3 algorithm |
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 |