CN113793366A - Image processing method, device, equipment and storage medium - Google Patents
Image processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113793366A CN113793366A CN202111015049.0A CN202111015049A CN113793366A CN 113793366 A CN113793366 A CN 113793366A CN 202111015049 A CN202111015049 A CN 202111015049A CN 113793366 A CN113793366 A CN 113793366A
- Authority
- CN
- China
- Prior art keywords
- image sequence
- image
- images
- frame
- target object
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 230000033001 locomotion Effects 0.000 claims abstract description 78
- 238000012545 processing Methods 0.000 claims abstract description 43
- 230000009471 action Effects 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 40
- 230000008859 change Effects 0.000 claims description 25
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 13
- 238000004422 calculation algorithm Methods 0.000 abstract description 11
- 238000004364 calculation method Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 13
- 238000004458 analytical method Methods 0.000 description 9
- 238000012937 correction Methods 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 238000011410 subtraction method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present disclosure relates to an image processing method, apparatus, device, and storage medium, the method including: acquiring an image sequence; the images in the image sequence comprise a target object; the image sequence comprises continuous multi-frame images which are used for collecting a target object in an active state in a video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes a preset action in the video; determining a difference frame image between two adjacent frames of images in the image sequence to obtain a difference frame image sequence; performing binarization processing on the difference frame image sequence based on the target identification parameter to obtain a binary image sequence; the target identification parameter characterizes a pixel value range of the target object, and the binary image sequence characterizes a motion state of the target object. The image processing method provided by the disclosure can realize the detection of the moving object through quick and simple calculation, has extremely low use cost and low algorithm complexity, and is easy to understand and realize by developers.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an image processing method, an image processing apparatus, an image processing device, and a storage medium.
Background
Currently, in an application scenario of infant monitoring, an infant monitor acquires an infant image in real time, and then judges whether an infant in the image is in a dangerous condition based on a motion detection algorithm. The baby monitor realizes the functions through a motion detection technology, the motion detection mainly aims at extracting a change area from a background image from a real-time sequence image, the current commonly used motion detection algorithm comprises a background subtraction method, a time difference method and an optical flow method, the current algorithm has good noise immunity to dynamic background change or motion of a camera, and a moving target can be effectively extracted and tracked even under a complex environment, but the complexity of the current motion detection algorithm is higher, certain understanding cost is required, a certain threshold is provided for a user, and in the scene of baby monitoring with stable background and light, the detection efficiency can be reduced due to the calculation complexity of the current algorithm, so that the alarm is not timely.
Therefore, under the scenario that the universality requirement is not very high, how to provide a real-time motion detection scheme which is fast and simple to implement and has low calculation cost is an urgent problem to be solved.
Disclosure of Invention
The present disclosure provides an image processing method, apparatus, device, and storage medium, which have low algorithm complexity, easy implementation, low implementation investment cost, and very high efficiency when applied in a specific application scenario. The technical scheme of the disclosure is as follows:
according to a first aspect of embodiments of the present disclosure, there is provided an image processing method, including:
acquiring an image sequence; the images in the image sequence comprise a target object; the image sequence comprises continuous multi-frame images which are used for collecting a target object in an active state in a video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes a preset action in the video;
determining a difference frame image between two adjacent frames of images in the image sequence to obtain a difference frame image sequence;
performing binarization processing on the difference frame image sequence based on the target identification parameter to obtain a binary image sequence; the target identification parameter characterizes a pixel value range of the target object, and the binary image sequence characterizes a motion state of the target object.
In an exemplary embodiment, when the image sequence includes a plurality of consecutive frames of images, the target object in the video in the active state is captured in a period, the method further includes:
taking the binary image sequence as a binary image sequence corresponding to the current period;
determining the frame number of the image acquired in the next period according to the binary image sequence corresponding to the current period;
and according to the frame number of the image acquired in the next period, executing the step of acquiring the image sequence until obtaining the binary image sequence, and obtaining the binary image sequence corresponding to the next period.
In an exemplary embodiment, determining the number of frames of the image acquired in the next period according to the binary image sequence corresponding to the current period comprises:
determining the number of target pixels in a binary image for each binary image in a binary image sequence corresponding to a current period, wherein the pixel value of each target pixel is a first preset value;
determining a change degree value corresponding to the binary image according to the number of the target pixels and the total number of pixels in the binary image;
determining the number of binary images with the change degree value larger than or equal to a preset degree value according to the change degree value corresponding to each binary image in the binary image sequence corresponding to the current period;
if the number exceeds the preset number, determining the frame number of the image acquired in the next period according to the increase amplitude of the preset frame number and the frame number of the image sequence corresponding to the current period; the preset number is determined based on the total number of the binary images in the binary image sequence corresponding to the current period.
In an exemplary embodiment, when the image sequence includes a plurality of consecutive frames of images that capture a target object in a video that performs a preset action, acquiring the image sequence includes:
and receiving a motion guidance request and continuous multi-frame images sent by a user account, wherein the motion guidance request is used for indicating that guidance information corresponding to a preset action is generated based on the continuous multi-frame images.
In an exemplary embodiment, after acquiring the sequence of images, the method further comprises:
carrying out preprocessing operation on the image sequence to obtain a preprocessed image sequence; the pre-processing operation includes at least one of: rasterization, resolution adjustment and noise reduction.
In an exemplary embodiment, the two adjacent frame images include a first frame image and a second frame image;
determining a difference frame image between two adjacent frame images in the image sequence, comprising:
determining a first number matrix based on a pixel value of each pixel in the first frame image;
determining a second digital matrix based on the pixel value of each pixel in the second frame image;
subtracting the first digital matrix from the second digital matrix to obtain a third digital matrix; the third digital matrix characterizes the pixel value of each pixel in the difference frame image.
In one exemplary embodiment, the target identification parameter includes a pixel threshold of a preset color channel;
based on the target identification parameter, carrying out binarization processing on the difference frame image sequence to obtain a binary image sequence, wherein the binarization processing comprises the following steps:
determining pixels of which the pixel values meet a pixel threshold value in the difference frame images as target pixels aiming at each difference frame image in the difference frame image sequence;
and adjusting the pixel value of the target pixel to a first preset value, and adjusting the pixel value of each pixel except the target pixel in the difference frame image to a second preset value to obtain a binary image corresponding to the difference frame image.
According to a second aspect of the embodiments of the present disclosure, there is provided an image processing apparatus including:
an acquisition module configured to perform acquiring a sequence of images; the images in the image sequence comprise a target object; the image sequence comprises continuous multi-frame images which are used for collecting a target object in an active state in a video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes a preset action in the video;
the first determining module is configured to determine a difference frame image between two adjacent frames of images in the image sequence to obtain a difference frame image sequence;
the first processing module is configured to execute binarization processing on the difference frame image sequence based on the target identification parameter to obtain a binary image sequence; the target identification parameter characterizes a pixel value range of the target object, and the binary image sequence characterizes a motion state of the target object.
In an exemplary embodiment, when the image sequence includes a plurality of consecutive frames of images, the target object in the video in the active state is captured in a period, the apparatus further includes:
a second determining module configured to perform the processing of taking the binary image sequence as a binary image sequence corresponding to the current period;
the third determining module is configured to execute the binary image sequence corresponding to the current period and determine the frame number of the image acquired in the next period;
and the execution module is configured to execute the steps of acquiring the image sequence until obtaining the binary image sequence according to the frame number of the image acquired in the next period, and obtaining the binary image sequence corresponding to the next period.
In an exemplary embodiment, the third determining module includes:
the first determining unit is configured to execute the steps of determining the number of target pixels in a binary image aiming at each binary image in a binary image sequence corresponding to the current period, wherein the pixel value of each target pixel is a first preset value;
a second determining unit configured to determine a change degree value corresponding to the binary image according to the number of the target pixels and the total number of pixels in the binary image;
a third determining unit configured to execute determining the number of binary images of which the change degree value is greater than or equal to a preset degree value according to the change degree value corresponding to each binary image in the binary image sequence corresponding to the current period;
a fourth determining unit configured to determine the number of frames of the image acquired in the next period according to the increase amplitude of the preset number of frames and the number of frames of the image sequence corresponding to the current period if the number exceeds the preset number; the preset number is determined based on the total number of the binary images in the binary image sequence corresponding to the current period.
In an exemplary embodiment, when the image sequence includes a plurality of consecutive frames of images of a target object performing a preset action in the video, the obtaining module is configured to perform:
receiving a motion guidance request and an image sequence sent by a user account; the image sequence comprises continuous multi-frame images of a target object executing a preset action, and the motion guidance request is used for indicating that guidance information corresponding to the preset action is generated based on the continuous multi-frame images.
In an exemplary embodiment, the apparatus further comprises:
the preprocessing module is configured to execute preprocessing operation on the image sequence to obtain a preprocessed image sequence; the pre-processing operation includes at least one of: rasterization, resolution adjustment and noise reduction.
In an exemplary embodiment, the two adjacent frame images include a first frame image and a second frame image;
a first determination module configured to perform:
determining a first number matrix based on a pixel value of each pixel in the first frame image;
determining a second digital matrix based on the pixel value of each pixel in the second frame image;
subtracting the first digital matrix from the second digital matrix to obtain a third digital matrix; the third digital matrix characterizes the pixel value of each pixel in the difference frame image.
In one exemplary embodiment, the target identification parameter includes a pixel threshold of a preset color channel;
a first processing module configured to perform:
determining pixels of which the pixel values meet a pixel threshold value in the difference frame images as target pixels aiming at each difference frame image in the difference frame image sequence;
and adjusting the pixel value of the target pixel to a first preset value, and adjusting the pixel value of each pixel except the target pixel in the difference frame image to a second preset value to obtain a binary image corresponding to the difference frame image.
In an exemplary embodiment, the apparatus further comprises:
and the motion state analysis module is configured to determine the motion state of the target object according to the binary image sequence and analyze the motion state of the target object.
In an exemplary embodiment, the apparatus further comprises:
and the motion correction module is configured to execute corresponding correction suggestion if the analysis result of analyzing the motion state of the target object comprises that the motion state of the target object is a state to be corrected.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the image processing method as described above in the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the image processing method of the first aspect described above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program, wherein the computer program is configured to implement the image processing method of the first aspect when executed by a processor.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
by acquiring a sequence of images; the images in the image sequence comprise a target object; the image sequence comprises continuous multi-frame images which are used for collecting a target object in an active state in a video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes a preset action in the video; determining a difference frame image between two adjacent frames of images in the image sequence to obtain a difference frame image sequence; performing binarization processing on the difference frame image sequence based on the target identification parameter to obtain a binary image sequence; the target identification parameter characterizes a pixel value range of the target object, and the binary image sequence characterizes a motion state of the target object. The image processing method provided by the disclosure can realize the detection of the moving object through quick and simple calculation, has extremely low use cost and low algorithm complexity, and is easy to understand and realize by developers.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a schematic diagram of an application environment, according to an exemplary embodiment;
FIG. 2 is a flow diagram illustrating a method of image processing according to an exemplary embodiment;
FIG. 3 is a flow diagram illustrating a method for determining a difference frame image between two adjacent frame images in an image sequence according to an exemplary embodiment;
FIG. 4 is a flowchart illustrating a process for binarizing a difference frame image sequence based on target identification parameters to obtain a binary image sequence according to an exemplary embodiment;
FIG. 5 is a schematic diagram of a binary image sequence shown in accordance with an exemplary embodiment;
FIG. 6 is a flow diagram illustrating another method of image processing according to an exemplary embodiment;
FIG. 7 is a flowchart illustrating a method for determining a frame number of an image acquired in a next cycle according to a binary image sequence corresponding to a current cycle in accordance with an exemplary embodiment;
FIG. 8 is a block diagram illustrating an image processing apparatus according to an exemplary embodiment;
FIG. 9 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
In some specific application scenes, for example, the light intensity of a light source is stable, no stroboflash or stroboflash frequency is integral multiple of the sampling rate of a camera, or the recognition requirement degree of a moving object is not very high due to the fact that the color of the moving object is obviously different from the surrounding environment, and the like, the existing motion detection algorithm is high in complexity such as a background subtraction method, a time difference method, an optical flow method and the like, needs to understand cost to a certain extent, and has a certain threshold for a user; and the algorithms need a large amount of calculation, and the efficiency is low.
In view of this, the present disclosure provides an image processing method, an image processing apparatus, an image processing device, and a storage medium, which can obtain a practical detection result through fast and simple calculation based on a specific requirement (mainly a requirement on light and object color), and have a very low use cost, so that a general developer can understand and implement the detection result.
Referring to fig. 1, a schematic diagram of an application environment of an image processing method according to an exemplary embodiment is shown, where the application environment may include a server 01 and a terminal 02. Alternatively, the server 01 and the terminal 02 may be connected through a wireless link or a wired link, and the disclosure is not limited herein.
In an alternative embodiment, the server 01 may be configured to obtain the binary image sequence from the acquired image sequence. Specifically, the server 01 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like. Optionally, the operating system running on the server 01 may include, but is not limited to, IOS, Linux, Windows, Unix, Android system, and the like.
In an alternative embodiment, the terminal 02 may assist the server 01 in obtaining the device of the image sequence. The terminal may be a provider of the image sequence for transmitting the image sequence to the server 01. Optionally, after the server 01 obtains the binary image sequence, the binary image sequence may be sent to the other terminal 02 for displaying on the other terminal 02. Specifically, the terminal 02 may include, but is not limited to, image capturing devices such as a digital camera and a gopro motion camera, and electronic devices of smart phones, desktop computers, tablet computers, notebook computers, smart speakers, digital assistants, Augmented Reality (AR)/Virtual Reality (VR) devices, smart wearable devices, and the like; the operating system running on the electronic device may include, but is not limited to, an android system, an IOS system, linux, windows, and the like.
In addition, it should be noted that fig. 1 is only one application environment of the image processing method provided by the present disclosure, and in practical applications, other application environments may also be included, for example, obtaining a binary image sequence may also be implemented on the terminal 02.
Fig. 2 is a flowchart illustrating an image processing method according to an exemplary embodiment, as shown in fig. 2, for example, the image processing method is used in the server of fig. 1, and includes the following steps:
in step S201, an image sequence is acquired; the images in the image sequence comprise the target object.
The image sequence comprises continuous multi-frame images which are used for collecting the target object in the active state in the video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes the preset action in the video.
In the embodiment of the disclosure, the image sequence may be acquired from the terminal by the server. The terminal may be an image capturing device, for example, a target object may be captured by a camera disposed on the terminal. The target object may be a predetermined object whose motion state is desired to be observed, or may be any suspicious object that needs to be detected from the environment.
In the embodiment of the disclosure, to obtain the rough motion content of the target object from the image sequence, for example, the motion state of the infant is known from the monitoring video shot by the infant monitoring system, or a suspicious moving object is captured from the monitoring video shot by the alarm monitoring system, or whether the motion of the user is standard or not is known from the motion video uploaded by the user in a dance and fitness scene.
In an alternative embodiment, the acquiring of the sequence of images may comprise the steps of:
receiving a motion guidance request and an image sequence sent by a user account; the image sequence comprises continuous multi-frame images of a target object executing a preset action, and the motion guidance request is used for indicating that guidance information corresponding to the preset action is generated based on the continuous multi-frame images.
The user account is an account registered in advance in the server, and the server can provide relevant motion guidance for a user corresponding to the user account, for example, in scenes such as dance and fitness, for a user who cannot determine whether dance motions or fitness motions are normal or not due to non-professional training or other reasons, the motion guidance function provided by the server can be used. Specifically, a user may use a device with a camera, such as a mobile phone, to shoot a continuous multi-frame image of a preset action completely executed by himself or herself or others, where the preset action may include any dance action or body-building action, then send a motion guidance request to a server, and upload a sequence of shot images, and the server obtains a corresponding sequence of binary images based on the sequence of images in response to the motion guidance request, and then generates corresponding guidance information according to the sequence of binary images, where the guidance information may include a suggestion on whether the preset action is standard or not and how to correct the preset action if the preset action is not standard.
It should be noted that the user information (including but not limited to user device information, user personal information, etc.) referred to in the present disclosure is information authorized by the user or sufficiently authorized by each party.
In an alternative embodiment, after acquiring the sequence of images, the method of the present disclosure may further include the steps of:
carrying out preprocessing operation on the image sequence to obtain a preprocessed image sequence; the pre-processing operation includes at least one of: rasterization, resolution adjustment and noise reduction.
Rasterization, also known as rasterization, is the process of converting an image represented in vector graphics format into a bitmap for display or printer output. The present disclosure considers that the format of the acquired image sequence may be vector diagram, i.e. object-oriented image or drawing image, and the elements constituting the vector diagram are some points, lines, rectangles, polygons, circles, arcs, etc., which are all calculated by mathematical formulas, and the image in this format must be rasterized and converted into bitmap with grid structure for the subsequent processing.
And the resolution adjustment is used for unifying the sizes of the images in the image sequence, so that the image processing efficiency can be improved.
Noise reduction (also called denoising), because a digital Image is often affected by interference of imaging equipment and external environment noise and the like in the digitization and transmission processes, before the Image is processed, the Image can be denoised as required to reduce the interference.
In step S203, a difference frame image between two adjacent frames of images in the image sequence is determined, resulting in a difference frame image sequence.
In the embodiment of the present disclosure, the two adjacent frames of images refer to two frames of images obtained by temporally continuous shooting. And determining the object with the changed position at any moment according to the difference frame image between the two adjacent frame images.
In an alternative embodiment, the two adjacent frames of images include a first frame of image and a second frame of image; the above-mentioned determining a difference frame image between two adjacent frame images in the image sequence may comprise the following steps as in fig. 3:
in step S301, a first number matrix is determined based on a pixel value of each pixel in the first frame image.
In step S303, a second digital matrix is determined based on the pixel value of each pixel in the second frame image.
In step S305, subtracting the first digital matrix from the second digital matrix to obtain a third digital matrix; the third digital matrix characterizes the pixel value of each pixel in the difference frame image.
In a specific embodiment, the first frame image is marked as a C frame (control frame), and is cached and recorded, the second frame image is marked as a T frame (target frame), and the difference frame image is obtained after real-time calculation rendering is performed by using a technology capable of processing and rendering images in real time, such as openGL and metal. The input parameters are rasterized data of C frame and T frame, namely a first digital matrix: c matrix, and a second digital matrix: a T matrix; then, subtracting the C matrix from the T matrix to obtain a third digital matrix corresponding to the difference frame image: a Dp (D-previous) matrix; where the digital matrix is a multi-dimensional vector composed of pixel values of all pixels in the image.
In step S205, a binarization process is performed on the difference frame image sequence based on the target identification parameter, so as to obtain a binary image sequence.
The target identification parameter represents a pixel value range of the target object, and the binary image sequence represents a motion state of the target object.
In the embodiment of the present disclosure, the target identification parameter includes a pixel threshold of a preset color channel, and the preset color channel may include red, green, and blue color channels. The target identification parameters need to be obtained by debugging according to the actual application scene, specifically, an artificial parameter adjusting method can be used, a set of automatic parameter adjusting algorithm can be trained for automatic parameter adjustment, and the determination mode of the target identification parameters is not limited in the disclosure. The target identification parameters may characterize the corresponding pixel value ranges of the target object on the red, green, and blue color channels.
And carrying out binarization processing on the difference frame image sequence based on the target identification parameters, wherein the motion state of the target object can be clearly observed in the obtained binary image sequence.
In an optional implementation mode, subjective evaluation is performed on the binary image, and corresponding target identification parameters are adjusted. For example, when the information in the binary image is lost too much (is not visible), the problem can be solved by turning down the target identification parameter, and conversely, when the noise in the binary image is too much (is disordered), more information can be removed by turning up the target identification parameter; for a scene with little change, the step of adjusting the target identification parameters only needs to be executed once.
In an optional embodiment, the above binarizing the difference frame image sequence based on the target identification parameter to obtain a binary image sequence may include the following steps as in fig. 4:
in step S401, for each difference frame image in the difference frame image sequence, a pixel in the difference frame image whose pixel value satisfies a pixel threshold is determined as a target pixel.
In step S403, the pixel value of the target pixel is adjusted to a first preset value, and the pixel values of the pixels except the target pixel in the difference frame image are adjusted to a second preset value, so as to obtain a binary image corresponding to the difference frame image.
Based on the above specific embodiment, a filter (filter) is used to erase the signals in the Dp matrix whose values do not satisfy the pixel threshold, and the remaining signals satisfying the pixel threshold are all amplified to the maximum value, so that binarization of the difference frame image can be realized, and the output result is a binary image; when applied to the RGB color space, the first preset value may be (255 ), the second preset value may be (0,0,0), the corresponding binary image is a black-and-white image, and the white area is the target object, as shown in fig. 5, fig. 5 is a schematic diagram of an exemplary binary image sequence provided by the present disclosure, where the binary image sequence shows that the target object (person) is in a state of waving its hand downward.
In the embodiment of the disclosure, the terminal image acquisition device can acquire images of moving target objects in real time, that is, the image sequence includes continuous multi-frame images which are acquired from the moving target objects in the video within a period; at this time, in step S201, the server periodically executes the image sequence of the preset number of frames acquired from the terminal, and calculates a binary image sequence corresponding to each period. In order to ensure that the target object has continuous image input in the moving process, the server can dynamically adjust the frame number of the image sequence acquired in each period to adapt to different changing speeds of the target object.
Based on this, in an optional embodiment, after step S205, the method of the present disclosure further includes the following steps in fig. 6:
in step S601, the binary image sequence is used as the binary image sequence corresponding to the current cycle.
In step S603, the number of frames of an image acquired in the next cycle is determined according to the binary image sequence corresponding to the current cycle.
In a specific embodiment, the determining the number of frames of the image acquired in the next period according to the binary image sequence corresponding to the current period may include the following steps in fig. 7:
in step S701, for each binary image in the binary image sequence corresponding to the current period, the number of target pixels in the binary image is determined, and the pixel value of the target pixel is a first preset value.
In step S703, a change degree value corresponding to the binary image is determined according to the number of target pixels and the total number of pixels in the binary image.
The change degree value may be a ratio of the number of the target pixels to the total number of pixels in the binary image, and represents a proportion of the target object in the binary image, and the change degree value may also represent a difference degree between two adjacent frames of images in the original image sequence.
In step S705, the number of binary images having a variation degree value greater than or equal to a preset degree value is determined according to the variation degree value corresponding to each binary image in the binary image sequence corresponding to the current period.
After the change degree value corresponding to each binary image is determined, each change degree value is compared with a preset degree value, whether the target object is in a rapid change state is further judged according to the size relation between the change degree value and the preset degree value, and therefore the frame number of the image acquired by the server is correspondingly adjusted dynamically, the requirement can be met, the waste of computing resources and power consumption of the server due to the fact that the image sequence is continuously acquired by the high acquired frame number is avoided, and the image processing efficiency can be improved.
It should be noted that, in the frame number of the image acquired by the dynamic adjustment server, the frame number may be obtained by adjusting the acquisition frame rate of the terminal image acquisition device, or by adjusting the sampling frequency of the server itself.
In step S707, if the number exceeds the preset number, determining the number of frames of the image acquired in the next period according to the increase of the preset number of frames and the number of frames of the image sequence corresponding to the current period; the preset number is determined based on the total number of the binary images in the binary image sequence corresponding to the current period.
Counting the number of binary images with the change degree value larger than or equal to a preset degree value in the binary image sequence corresponding to the current period, and if the number exceeds the preset number, increasing the number of frames of the images acquired in the next period by a certain preset frame number increase range on the basis of the number of frames of the image sequence corresponding to the current period; wherein the preset number may be 1/2 of the total number of binary images in the binary image sequence corresponding to the current period.
The frame number of the image acquired in the next period is increased, and the increase can be realized by increasing the acquisition frame rate of the image acquisition equipment or adjusting the sampling frequency of the server; taking an example of increasing the acquisition frame rate of the image acquisition equipment, in a first period, the frame rate is 4 frames/s, the server acquires an image sequence once in a period of 5 seconds, the image sequence acquired by the server in the first period includes 20 frames of images, the server performs processing based on the 20 frames of images to obtain a binary image sequence corresponding to the first period, and the number of binary images in the binary image sequence is 19 frames; then, calculating a corresponding change degree value for each binary image; if the number of binary images with the change degree value larger than or equal to the preset degree value in 19 frames of binary images is 11 frames and exceeds the preset number by 10 frames, the acquisition frame rate of the image acquisition equipment is increased by 2 frames/s according to the increase range of the preset frame number, that is, the acquisition frame rate of the image acquisition equipment is adjusted to 6 frames/s, and the number of frames of the image acquired in the corresponding next period is 30 frames.
In step S605, the step of acquiring the image sequence is executed until obtaining the binary image sequence according to the frame number of the image acquired in the next cycle, so as to obtain the binary image sequence corresponding to the next cycle.
Based on the number of frames of the image acquired in the next period after the adjustment, the above steps S201 to S205 are repeatedly executed to obtain the binary image sequence corresponding to the next period, so that the target object in the fast changing state can be adapted to obtain the complete motion state of the target object.
The image processing method provided by the embodiment of the disclosure can be applied to application scenes such as monitoring of a factory building and detection of baby activities, can quickly detect the movement of an object, is convenient for subsequent warning or reminding in time, and can enable consumers to roughly know the content of the object activities because complex identification is not needed and the calculation cost and the reaction speed are far faster than those of traditional intelligent identification modes such as a neural network.
According to the image processing method provided by the embodiment of the disclosure, the finally obtained binary image sequence can be used as a display frame or a recording frame. And because the binary image has only two kinds of color information in total, the information which does not need to be concerned is deleted, and only the content related to the activity of the target object is reserved, so that the non-publicity of places and the privacy of users can be greatly protected for some sensitive places or individuals.
In addition, in an application scene of video transmission, compared with a processing mode of inputting an original image sequence, the image processing method provided by the embodiment of the disclosure finally obtains a binary image sequence by removing most irrelevant information, so that transmitted video data can have a chance to reach a very high compression rate and a very high fidelity rate.
Fig. 8 is a block diagram illustrating an image processing apparatus according to an exemplary embodiment. Referring to fig. 8, the apparatus includes an obtaining module 801, a first determining module 802, and a first processing module 803, wherein:
an acquisition module 801 configured to perform acquiring a sequence of images; the images in the image sequence comprise a target object; the image sequence comprises continuous multi-frame images which are used for collecting a target object in an active state in a video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes a preset action in the video;
a first determining module 802, configured to perform determining a difference frame image between two adjacent frames of images in an image sequence, resulting in a difference frame image sequence;
a first processing module 803, configured to perform binarization processing on the difference frame image sequence based on the target identification parameter, resulting in a binary image sequence; the target identification parameter characterizes a pixel value range of the target object, and the binary image sequence characterizes a motion state of the target object.
In an exemplary embodiment, when the image sequence includes a plurality of consecutive frames of images, the target object in the video in the active state is captured in a period, the apparatus further includes:
a second determining module configured to perform the processing of taking the binary image sequence as a binary image sequence corresponding to the current period;
the third determining module is configured to execute the binary image sequence corresponding to the current period and determine the frame number of the image acquired in the next period;
and the execution module is configured to execute the steps of acquiring the image sequence until obtaining the binary image sequence according to the frame number of the image acquired in the next period, and obtaining the binary image sequence corresponding to the next period.
In an exemplary embodiment, the third determining module includes:
the first determining unit is configured to execute the steps of determining the number of target pixels in a binary image aiming at each binary image in a binary image sequence corresponding to the current period, wherein the pixel value of each target pixel is a first preset value;
a second determining unit configured to determine a change degree value corresponding to the binary image according to the number of the target pixels and the total number of pixels in the binary image;
a third determining unit configured to execute determining the number of binary images of which the change degree value is greater than or equal to a preset degree value according to the change degree value corresponding to each binary image in the binary image sequence corresponding to the current period;
a fourth determining unit configured to determine the number of frames of the image acquired in the next period according to the increase amplitude of the preset number of frames and the number of frames of the image sequence corresponding to the current period if the number exceeds the preset number; the preset number is determined based on the total number of the binary images in the binary image sequence corresponding to the current period.
In an exemplary embodiment, when the image sequence includes a plurality of consecutive frames of images of a target object performing a preset action in a video, the obtaining module 801 is configured to perform:
and receiving a motion guidance request continuous multi-frame images sent by a user account, wherein the motion guidance request is used for indicating that guidance information corresponding to the preset action is generated based on the continuous multi-frame images.
In an exemplary embodiment, the apparatus further comprises:
the preprocessing module is configured to execute preprocessing operation on the image sequence to obtain a preprocessed image sequence; the pre-processing operation includes at least one of: rasterization, resolution adjustment and noise reduction.
In an exemplary embodiment, the two adjacent frame images include a first frame image and a second frame image;
a first determining module 802 configured to perform:
determining a first number matrix based on a pixel value of each pixel in the first frame image;
determining a second digital matrix based on the pixel value of each pixel in the second frame image;
subtracting the first digital matrix from the second digital matrix to obtain a third digital matrix; the third digital matrix characterizes the pixel value of each pixel in the difference frame image.
In one exemplary embodiment, the target identification parameter includes a pixel threshold of a preset color channel;
a first processing module 803 configured to perform:
determining pixels of which the pixel values meet a pixel threshold value in the difference frame images as target pixels aiming at each difference frame image in the difference frame image sequence;
and adjusting the pixel value of the target pixel to a first preset value, and adjusting the pixel value of each pixel except the target pixel in the difference frame image to a second preset value to obtain a binary image corresponding to the difference frame image.
In an exemplary embodiment, the image processing apparatus further includes a motion state analysis module:
and the motion state analysis module is configured to determine the motion state of the target object according to the binary image sequence and analyze the motion state of the target object.
In scenes such as dancing and body-building, some users have the requirement that whether the movement of the users is normal or not cannot be determined due to the fact that the users do not receive professional training or other reasons, and meanwhile, the users do not want to be known by others to obtain professional pointing.
In view of this, the image processing apparatus provided in the embodiment of the present disclosure may help the user to improve the normalization of some activities of the user through the motion state analysis module on the premise of protecting the privacy of the user. For example, a user may record a dance motion or a fitness motion in advance to form an image sequence, and then upload the image sequence to the image processing apparatus, where the image sequence including the dance motion or the fitness motion of the user sequentially passes through the obtaining module 801, the first determining module 802, and the first processing module 803 to obtain a corresponding binary image sequence, so as to remove background information and privacy information related to the user and only keep content related to the user motion, thereby protecting the user privacy; the obtained binary image sequence continues to be processed by the motion state analysis module, and the processing process may include analyzing the user's motion based on the standard motion to obtain a result whether the user's motion is standard or not.
In an exemplary embodiment, the image processing apparatus further includes:
and the motion correction module is configured to execute corresponding correction suggestion if the analysis result of analyzing the motion state of the target object comprises that the motion state of the target object is a state to be corrected.
In a specific embodiment, the motion state analysis module includes a display device, the display device is configured to display the binary image sequence, and the displayed binary image sequence may be analyzed and determined in a manual manner; for example, the display device displays the processed binary image sequence including the user's motion, and then the displayed content is analyzed by the expert or the coach, and if the motion of the analyzed user is not standard, the corresponding corrective advice is manually input by the expert or the coach.
In another specific implementation mode, a large number of videos corresponding to standard dance motions or standard fitness motions are stored in a database in advance, the motion state analysis module automatically calls the videos corresponding to the standard motions from the database through a preset program, and then compares the videos with a binary image sequence containing the motions of a user to obtain a result of whether the motions of the user are standard or not, and generates information that the motion state of a target object is a to-be-corrected state when the motions of the target object are not standard;
and the motion correction module is used for responding to the information that the motion state of the target object is the state to be corrected, further analyzing the binary image sequence containing the action of the user through a preset program to generate a corresponding correction suggestion, and sending the guidance task information and the binary image sequence containing the action of the user to a terminal bound by an expert or a coach to obtain the correction suggestion fed back by the expert or the coach.
With regard to the apparatus in the above embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.
In one exemplary embodiment, there is also provided an electronic device, comprising a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement any one of the image processing methods provided in the embodiments of the present disclosure when executing the instructions stored on the memory.
The electronic device may be a terminal, a server, or a similar computing device, taking the electronic device as a server as an example, fig. 9 is a block diagram of an electronic device for image Processing shown in an exemplary embodiment, and as shown in fig. 9, the server 900 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 910 (the processors 910 may include but are not limited to Processing devices such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 930 for storing data, and one or more storage media 920 (e.g., one or more mass storage devices) for storing an application program 923 or data 922. Memory 930 and storage media 920 may be, among other things, transient or persistent storage. The program stored in the storage medium 920 may include one or more modules, each of which may include a series of instruction operations in a server. Still further, the central processor 910 may be configured to communicate with the storage medium 920, and execute a series of instruction operations in the storage medium 920 on the server 900. The server 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input-output interfaces 940, and/or one or more operating systems 921, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so forth.
The input/output interface 940 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the server 900. In one example, the input/output Interface 940 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the input/output interface 940 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
It will be understood by those skilled in the art that the structure shown in fig. 9 is only an illustration and is not intended to limit the structure of the electronic device. For example, server 900 may also include more or fewer components than shown in FIG. 9, or have a different configuration than shown in FIG. 9.
In an exemplary embodiment, a computer-readable storage medium comprising instructions, such as the memory 930 comprising instructions, executable by the processor 910 of the apparatus 900 to perform the method described above is also provided. Alternatively, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, there is also provided a computer program product comprising a computer program which, when executed by a processor, implements any one of the image processing methods provided in the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. An image processing method, comprising:
acquiring an image sequence; an image in the sequence of images includes a target object; the image sequence comprises continuous multi-frame images which are used for collecting a target object in an active state in a video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes a preset action in the video;
determining a difference frame image between two adjacent frames of images in the image sequence to obtain a difference frame image sequence;
performing binarization processing on the difference frame image sequence based on the target identification parameter to obtain a binary image sequence; the target identification parameter characterizes a pixel value range of the target object, and the binary image sequence characterizes a motion state of the target object.
2. The image processing method according to claim 1, wherein when the image sequence includes a plurality of consecutive frames of images that capture a target object that is active in a video over a period, the method further comprises:
taking the binary image sequence as a binary image sequence corresponding to the current period;
determining the frame number of the image acquired in the next period according to the binary image sequence corresponding to the current period;
and according to the frame number of the image acquired in the next period, executing the step of acquiring the image sequence until obtaining a binary image sequence, and obtaining the binary image sequence corresponding to the next period.
3. The image processing method according to claim 2, wherein the determining the number of frames of the image acquired in the next period according to the binary image sequence corresponding to the current period comprises:
determining the number of target pixels in the binary image for each binary image in the binary image sequence corresponding to the current period, wherein the pixel value of the target pixel is a first preset value;
determining a change degree value corresponding to the binary image according to the number of the target pixels and the total number of pixels in the binary image;
determining the number of binary images with the change degree value larger than or equal to a preset degree value according to the change degree value corresponding to each binary image in the binary image sequence corresponding to the current period;
if the number exceeds the preset number, determining the frame number of the image acquired in the next period according to the increase amplitude of the preset frame number and the frame number of the image sequence corresponding to the current period; the preset number is determined based on the total number of binary images in the binary image sequence corresponding to the current period.
4. The image processing method according to claim 1, wherein when the image sequence includes a plurality of consecutive frames of images that capture a target object in a video that performs a preset action, the acquiring the image sequence includes:
receiving a motion guidance request and the continuous multi-frame images sent by a user account, wherein the motion guidance request is used for indicating that guidance information corresponding to the preset action is generated based on the continuous multi-frame images.
5. The image processing method according to any one of claims 1 to 4, wherein after the acquiring of the sequence of images, the method further comprises:
carrying out preprocessing operation on the image sequence to obtain a preprocessed image sequence; the pre-processing operation comprises at least one of: rasterization, resolution adjustment and noise reduction.
6. The image processing method according to claim 1, wherein the two adjacent frame images include a first frame image and a second frame image;
the determining a difference frame image between two adjacent frame images in the image sequence comprises:
determining a first number matrix based on a pixel value of each pixel in the first frame image;
determining a second digital matrix based on the pixel value of each pixel in the second frame image;
subtracting the first digital matrix from the second digital matrix to obtain a third digital matrix; the third digital matrix characterizes a pixel value of each pixel in the difference frame image.
7. An image processing apparatus characterized by comprising:
an acquisition module configured to perform acquiring a sequence of images; an image in the sequence of images includes a target object; the image sequence comprises continuous multi-frame images which are used for collecting a target object in an active state in a video in a period, or the image sequence comprises continuous multi-frame images which are used for collecting the target object which executes a preset action in the video;
the first determining module is configured to determine a difference frame image between two adjacent frames of images in the image sequence to obtain a difference frame image sequence;
the first processing module is configured to execute binarization processing on the difference frame image sequence based on a target identification parameter to obtain a binary image sequence; the target identification parameter characterizes a pixel value range of the target object, and the binary image sequence characterizes a motion state of the target object.
8. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the image processing method of any one of claims 1 to 6.
9. A computer-readable storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the image processing method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the image processing method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015049.0A CN113793366A (en) | 2021-08-31 | 2021-08-31 | Image processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111015049.0A CN113793366A (en) | 2021-08-31 | 2021-08-31 | Image processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113793366A true CN113793366A (en) | 2021-12-14 |
Family
ID=79182445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111015049.0A Pending CN113793366A (en) | 2021-08-31 | 2021-08-31 | Image processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113793366A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549371A (en) * | 2022-04-26 | 2022-05-27 | 中国科学技术大学 | Image analysis method and device |
| CN116188821A (en) * | 2023-04-25 | 2023-05-30 | 青岛尘元科技信息有限公司 | Copyright detection method, system, electronic device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739557A (en) * | 2010-01-26 | 2010-06-16 | 重庆大学 | Motion cycle analysis-based method and device for identifying abnormal human behavior |
| CN104700430A (en) * | 2014-10-05 | 2015-06-10 | 安徽工程大学 | Method for detecting movement of airborne displays |
| CN106781167A (en) * | 2016-12-29 | 2017-05-31 | 深圳新基点智能股份有限公司 | The method and apparatus of monitoring object motion state |
| CN110532988A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Behavior monitoring method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN111860030A (en) * | 2019-04-24 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Behavior detection method, behavior detection device, behavior detection equipment and storage medium |
| CN112633208A (en) * | 2020-12-30 | 2021-04-09 | 海信视像科技股份有限公司 | Lip language identification method, service equipment and storage medium |
-
2021
- 2021-08-31 CN CN202111015049.0A patent/CN113793366A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739557A (en) * | 2010-01-26 | 2010-06-16 | 重庆大学 | Motion cycle analysis-based method and device for identifying abnormal human behavior |
| CN104700430A (en) * | 2014-10-05 | 2015-06-10 | 安徽工程大学 | Method for detecting movement of airborne displays |
| CN106781167A (en) * | 2016-12-29 | 2017-05-31 | 深圳新基点智能股份有限公司 | The method and apparatus of monitoring object motion state |
| CN111860030A (en) * | 2019-04-24 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Behavior detection method, behavior detection device, behavior detection equipment and storage medium |
| CN110532988A (en) * | 2019-09-04 | 2019-12-03 | 上海眼控科技股份有限公司 | Behavior monitoring method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN112633208A (en) * | 2020-12-30 | 2021-04-09 | 海信视像科技股份有限公司 | Lip language identification method, service equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 丁金铸;谈国新;: "基于视频序列中的运动目标检测技术", 湖南工程学院学报(自然科学版), no. 03, pages 50 - 53 * |
| 张起贵;张光伟;: "一种视频序列中运动目标检测算法", 昆明理工大学学报(理工版), no. 04 * |
| 王让定, 陈金儿, 朱斌: "基于MCLT变换的音频数字水印技术", 计算机研究与发展, no. 08 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549371A (en) * | 2022-04-26 | 2022-05-27 | 中国科学技术大学 | Image analysis method and device |
| CN114549371B (en) * | 2022-04-26 | 2022-09-09 | 中国科学技术大学 | Image analysis method and device |
| CN116188821A (en) * | 2023-04-25 | 2023-05-30 | 青岛尘元科技信息有限公司 | Copyright detection method, system, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600888B (en) | Automatic forest fire detection method and system | |
| CN109299703B (en) | Method and device for carrying out statistics on mouse conditions and image acquisition equipment | |
| WO2020125631A1 (en) | Video compression method and apparatus, and computer-readable storage medium | |
| CN113793366A (en) | Image processing method, device, equipment and storage medium | |
| US20180144476A1 (en) | Cascaded-time-scale background modeling | |
| EP3707895B1 (en) | Static video recognition | |
| CN112492297B (en) | Video processing method and related equipment | |
| US20230196516A1 (en) | Video denoising method and mobile terminal, and storage medium | |
| EP3723049A1 (en) | System and method for anonymizing content to protect privacy | |
| CN108898079A (en) | A kind of monitoring method and device, storage medium, camera terminal | |
| CN110858316A (en) | Classifying time series image data | |
| CN111191507A (en) | Safety early warning analysis method and system for smart community | |
| US20230206093A1 (en) | Music recommendation method and apparatus | |
| CN110795998B (en) | People flow detection method and device, electronic equipment and readable storage medium | |
| CN115761571A (en) | Video-based target retrieval method, device, equipment and storage medium | |
| CN111259763A (en) | Target detection method and device, electronic equipment and readable storage medium | |
| CN105554040A (en) | Remote video monitoring method and system | |
| CN112307323B (en) | Information pushing method and device | |
| CN109961060B (en) | Method and apparatus for generating crowd density information | |
| CN114491466B (en) | Intelligent training system based on private cloud technology | |
| WO2022121886A1 (en) | Method and apparatus for identifying dress code for electric power operations | |
| CN111353330A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN113328520A (en) | Intelligent operation and maintenance method, system and device for power transmission and storage medium | |
| CN112967328A (en) | Image depth information local dynamic generation method and device | |
| CN111062337B (en) | People stream direction detection method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |