CN114866692A - Image output method and system of large-resolution monitoring camera - Google Patents
Image output method and system of large-resolution monitoring camera Download PDFInfo
- Publication number
- CN114866692A CN114866692A CN202210412672.8A CN202210412672A CN114866692A CN 114866692 A CN114866692 A CN 114866692A CN 202210412672 A CN202210412672 A CN 202210412672A CN 114866692 A CN114866692 A CN 114866692A
- Authority
- CN
- China
- Prior art keywords
- image
- path
- target
- video image
- video
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003672 processing method Methods 0.000 claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 239000002245 particle Substances 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 8
- 238000007499 fusion processing Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/95—Computational photography systems, e.g. light-field imaging systems
- H04N23/951—Computational photography systems, e.g. light-field imaging systems by using two or more images to influence resolution, frame rate or aspect ratio
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image output method and system of a large-resolution monitoring camera, wherein the method comprises the following steps: based on a first image acquired by an image sensor at the moment t, a first path of video image and a second path of video image are synchronously acquired by a first image processing method and a second image processing method respectively; performing characteristic analysis on the acquired first path of video image to predict target parameters of the first image at the t +1 moment; and the second image processing method processes the first image based on the predicted target parameter of the first image at the time t to acquire a second path of video image. The invention realizes the dynamic updating of the second image processing method while outputting the first path of video image based on the changed first image, obtains the second path of video image output by the second image processing method based on the dynamic updating, and realizes the high-quality scene monitoring of coarse granularity and fine granularity at the same time.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to an image output method and system of a large-resolution monitoring camera.
Background
Surveillance cameras place higher demands on resolution in order to view more details. Most of the current monitoring cameras are 200w-400w pixels, and with higher and higher requirements, the resolution of the monitoring cameras is improved to tens of millions or even tens of millions of pixels. For cameras with tens of millions of pixel resolutions, picture transfer is possible, but for video, video compression and video transfer are both challenging. If the resolution is reserved, the compression processing speed cannot keep up, and the transmission speed also needs to be equipped with a high-bandwidth transmission medium, which consumes cost.
Disclosure of Invention
In view of the problems in the prior art, the invention provides an image output method and system for a high-resolution monitoring camera, which can simultaneously perform high-quality scene monitoring of coarse granularity and fine granularity, and take both resolution and transmission speed into consideration. The technical scheme is as follows:
in a first aspect, an image output method of a large-resolution monitoring camera is provided, including:
based on a first image acquired by an image sensor at the moment t, a first path of video image and a second path of video image are synchronously acquired by a first image processing method and a second image processing method respectively, the resolution of the second path of video image is not smaller than that of the first image, and the resolution of the first path of video image is not larger than that of the first image;
acquiring a third path of video image through fusion processing with a second path of video image based on the acquired first path of video image and outputting the third path of video image, and simultaneously performing feature analysis on the acquired first path of video image to predict target parameters of the first image at the t +1 moment;
and the second image processing method processes the first image based on the predicted target parameter of the first image at the time t to acquire a second path of video image.
In a possible implementation manner, the method further includes synchronously displaying the first path of video image and the second path of video image respectively through a display.
In a possible implementation manner, the performing feature analysis on the acquired first path of video image to predict the target parameter of the first image at the time t +1 includes:
performing characteristic analysis on the first path of video image at the time t to obtain target parameters of the first path of video image at the time t;
predicting the target parameter of the first path of video image at the t +1 moment based on the target parameter of the first path of video image at the t moment;
and predicting the target parameter of the first image at the t +1 moment based on the conversion relation between the first image and the first path of video image and the predicted target parameter of the first path of video image at the t +1 moment.
In a possible implementation manner, the performing feature analysis on the first path of video image at the time t to obtain the target parameter of the first path of video image at the time t includes:
acquiring a target pixel area in a first path of video image at the time t, wherein the target pixel area is as follows: forming areas and/or pixel areas with pixel characteristics conforming to preset target characteristics with all pixels with the pixel variation larger than a first preset threshold value at the last moment;
and obtaining the position and size parameters of the best matching target frame for marking the position of the target pixel area based on the target pixel area of the first path of video image.
In a possible implementation manner, the obtaining, based on a target pixel region of a first path of video image, a position and a size parameter of a best matching target frame for labeling a position of the target pixel region includes:
determining that a target in a target pixel area appears for the first time based on the target pixel area of the first path of video image;
acquiring a plurality of candidate target frames based on a target pixel area of the first path of video image;
and comparing the position and the size of the candidate target frames with preset target parameters to obtain a target frame which is best matched with the preset target parameters and obtain the position and the size parameters of the best matched target frame.
Determining that a target in a target pixel area is a non-first-appearing target based on the target pixel area of the first path of video image;
determining a size parameter of a target best matching target frame in the target pixel region based on a historical target frame size of the target in a historical video image of the historical occurrence of the target;
determining a position parameter of a target best matching target box in the target pixel area based on the center position of the target pixel area.
In a possible implementation manner, the comparing, based on the positions and sizes of the multiple candidate target frames and the preset target parameter, the obtaining of the target frame that best matches the preset target parameter includes:
performing a particle swarm optimization algorithm by taking the side length of the candidate target frame and the position parameter of the candidate target frame as a particle and taking a combined function of the proportion of the number of non-target pixels in the candidate target frame and the compatibility of the candidate target frame and the region corresponding to the preset target parameter as a loss function;
and obtaining a target frame which is optimally matched with the preset target parameters based on the optimal solution of the particle swarm optimization algorithm.
In one possible implementation, the second image processing method includes:
acquiring a target region cutting parameter of the first image based on the predicted target parameter of the first image at the time t;
and cropping the first image based on the target area cropping parameters of the first image.
In a second aspect, there is provided an image output system of a large-resolution monitoring camera, including:
the two paths of video output units are used for synchronously acquiring a first path of video image and a second path of video image respectively through a first image processing method and a second image processing method based on a first image acquired by an image sensor at the moment t, the resolution ratio of the second path of video image is not smaller than that of the first image, and the resolution ratio of the first path of video image is not larger than that of the first image;
the fusion output and parameter feedback unit is used for acquiring and outputting a third path of video image through fusion processing with a second path of video image based on the acquired first path of video image, and meanwhile, performing characteristic analysis on the acquired first path of video image to predict target parameters of the first image at the time of t + 1;
and the second image processing method processes the first image based on the predicted target parameter of the first image at the time t to acquire a second path of video image.
In a third aspect, an electronic device is provided, which includes:
a processor;
a memory for storing processor-executable instructions;
wherein the processor implements the image output method of the large-resolution monitoring camera according to the first aspect by executing the executable instructions.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of an image output method of a large resolution monitoring camera according to the first aspect.
The image output method and the system of the large-resolution monitoring camera have the following beneficial effects that: the large-resolution monitoring camera can output two paths of video streams simultaneously, wherein a first path of output video images can be subjected to parameter analysis to update a second image processing method, the second image processing method is dynamically updated while the first path of output video images are output based on a changed first image, and a second path of video images output by the second image processing method based on dynamic update are obtained, wherein the resolution of the second path of video images is greater than that of the first path of video images, namely the monitoring camera in the embodiment of the application can simultaneously output two paths of video images with different resolutions, and perform high-quality scene monitoring of coarse granularity and fine granularity.
Drawings
Fig. 1 is a flowchart of an image output method of a large-resolution monitoring camera according to an embodiment of the present application;
fig. 2 is a structural diagram of an image output system of a large-resolution monitoring camera according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
The embodiment of the application provides an image output method of a high-resolution monitoring camera, which can be used for monitoring a small number of targets in a small scene in one implementation mode, for example, applied to remote indoor monitoring to monitor the moving track of indoor personnel, and comprises the following steps:
based on a first image acquired by an image sensor at the moment t, a first path of video image and a second path of video image are synchronously acquired by a first image processing method and a second image processing method respectively, the resolution of the second path of video image is not smaller than that of the first image, and the resolution of the first path of video image is not larger than that of the first image;
acquiring a third path of video image through fusion processing with a second path of video image based on the acquired first path of video image and outputting the third path of video image, and simultaneously performing feature analysis on the acquired first path of video image to predict target parameters of the first image at the t +1 moment;
and the second image processing method processes the first image based on the predicted target parameter of the first image at the time t to acquire a second path of video image.
The large-resolution monitoring camera in the embodiment of the application can output two paths of video streams simultaneously, wherein a first path of output video images can perform parameter analysis to update the second image processing method, the second image processing method can be dynamically updated while the first path of output video images are output based on the changed first image, and a second path of video images output by the second image processing method based on dynamic update is obtained, wherein the resolution of the second path of video images is greater than that of the first path of video images, that is, the monitoring camera in the embodiment of the application can simultaneously output two paths of video images with different resolutions, and perform high-quality scene monitoring of coarse granularity and fine granularity.
Further, the image output method of the large-resolution monitoring camera in the embodiment of the present application further includes synchronously displaying the first path of video image and the second path of video image respectively through a display.
In the monitoring camera of this application embodiment, there are two kinds of data transmission of SDI and MIPI at the FPGA end, and SDI send module calls the inside IP core of FPGA, and image data fills according to SDI standard system, and SDI is optionally 1080p @25fps, two kinds of systems of 720p @25fps, exports video image and the second way video image of first way and second way respectively through two SDI interfaces, and two SDI interfaces can directly dock the display. Two paths of video images in an MIPI data format output by an FPGA end can be butted into a special video image processing module, and further, the step of obtaining the third path of video image by fusing the first path of video image and the second path of video image and the step of predicting the target parameter of the first image at the moment of t +1 by carrying out feature analysis on the first path of video image in the embodiment of the application can be carried out in the special video image processing module.
Further, the performing feature analysis on the acquired first path of video image to predict the target parameter of the first image at the time t +1 includes:
performing characteristic analysis on the first path of video image at the time t to obtain target parameters of the first path of video image at the time t;
predicting the target parameter of the first path of video image at the t +1 moment based on the target parameter of the first path of video image at the t moment;
and predicting the target parameter of the first image at the t +1 moment based on the conversion relation between the first image and the first path of video image and the predicted target parameter of the first path of video image at the t +1 moment.
In the embodiment of the application, a first path of video image is output by a first image processing method through a first image processing method, a second path of video image is output by a second image processing method, a target parameter of the first image can be obtained through analysis of the reverse process of the first image processing method based on the obtained target parameter of the first path of video image at the current moment and the next moment, a variable parameter of the second image processing method is updated based on the target parameter of the first image at the next moment, and therefore the second image processing method is executed on the first image at the next moment to obtain the second path of video image matched with the first image at the next moment.
Further, the performing feature analysis on the first path of video image at the time t to obtain the target parameter of the first path of video image at the time t includes:
acquiring a target pixel area in a first path of video image at the time t, wherein the target pixel area is as follows: forming areas and/or pixel areas with pixel characteristics conforming to preset target characteristics with all pixels with the pixel variation larger than a first preset threshold value at the last moment;
and obtaining the position and size parameters of the best matching target frame for marking the position of the target pixel area based on the target pixel area of the first path of video image.
The pixel features of the pixel region are in accordance with preset target features, the preset target can be a human face or a vehicle, so that feature analysis is performed based on the pixel region in which the pixel features are in accordance with the preset target features, position and size parameters of a best matching target frame of a target pixel region of a first path of video image at time t are obtained, the best matching target frame based on the position and size parameters can perform regional image cropping on the preset target in the first path of video image, further, a second path of video image meeting a certain resolution requirement is obtained by performing processing based on the cropped preset target region image through subsequent steps of a second image processing method, the subsequent steps of the second image processing method can include image compression, transmission and the like, for example, the second path of video image is zoomed to a standard 1080p/720p resolution for SDI output, the first path of video image is subjected to feature analysis by the special video image processing module to predict target parameters of the first image at the time of t +1, the target parameters are output and fed back to the FPGA, variable parameters in the second image processing method are adjusted, and meanwhile, the first path of video image and the second path of video image can be fused in the special video image processing module to obtain a third path of video image.
Further, the obtaining of the position and size parameters of the best matching target frame for labeling the position of the target pixel region based on the target pixel region of the first path of video image includes:
judging whether a target in a target pixel area is a first-appearing target or not based on the target pixel area of the first path of video image;
and under the condition that the target in the target pixel region is determined to be a non-first-appearing target, determining the size parameter of the target best matching target frame in the target pixel region based on the historical target frame size of the target in the historical video images in which the target appears historically, and determining the position parameter of the target best matching target frame in the target pixel region based on the central position of the target pixel region.
In the embodiment of the application, after the position and size parameters of a target frame are determined for one target in a first path of video images, a second image processing method processes the first path of video images based on the position and size parameters of the target frame to obtain a high-resolution image of a local area containing the target, and outputs a second path of video images.
In a case where it is determined that the target in the target pixel region is a first occurrence:
acquiring a plurality of candidate target frames based on a target pixel area of the first path of video image;
and comparing the position and the size of the candidate target frames with preset target parameters to obtain a target frame which is best matched with the preset target parameters and obtain the position and the size parameters of the best matched target frame.
The method for acquiring a plurality of candidate target frames based on a target pixel area of a first path of video image comprises the following steps:
(1) establishing a coordinate system by taking one point on the edge of the target pixel area as a coordinate origin;
(2) placing the candidate frame with the preset scale at the origin of coordinates to obtain a candidate target frame containing target pixels;
(3) judging whether all the target pixels are in the candidate target frame;
(4) if yes, keeping the position and size parameter information of the candidate target frame;
(5) if not, translating and zooming the candidate target frame by the candidate target frame based on the current coordinate origin position according to the preset position moving parameter and the preset side length coordinate increment to obtain a new candidate target frame;
(6) and (5) repeating the steps (3) and (5) until the number of the target frames retaining the parameter information reaches a second preset value, and acquiring second preset value candidate target frames.
Specifically, in the embodiment of the present application, the candidate target frame is a rectangle, one vertex of the rectangular target frame is placed at the coordinate origin, two sides of the rectangle are respectively placed on a horizontal axis and a vertical axis of a coordinate system, and the position is used as the initial position of the candidate target frame.
Further, the comparing the position and the size of the candidate target frames with the preset target parameters to obtain the target frame best matching the preset target parameters includes:
performing a particle swarm optimization algorithm by taking the side length of the candidate target frame and the position parameter of the candidate target frame as a particle and taking a combined function of the proportion of the number of non-target pixels in the candidate target frame and the compatibility of the candidate target frame and the region corresponding to the preset target parameter as a loss function;
and obtaining a target frame which is optimally matched with the preset target parameters based on the optimal solution of the particle swarm optimization algorithm.
In the embodiment of the application, when the candidate target frame is translated and scaled, in order to quickly obtain the candidate target frame which can cover all target pixels and can satisfy the requirement of good matching with the preset target parameter, a particle swarm optimization algorithm is adopted, the translation and scaling parameters are used as particles, a combined function of the proportion of the number of non-target pixels in the candidate target frame and the compatibility of the region corresponding to the candidate target frame and the preset target parameter is used as a loss function, the particle swarm optimization algorithm is performed, wherein the compatibility of the region corresponding to the candidate target frame and the preset target parameter can be calculated based on the position and size parameters of the candidate target frame and a compatibility index provided by a user, for example, the compatibility index provided by the user can be the requirement on the area size of the target frame, can be the requirement on the length-width ratio of the target frame, and the like, and the compatibility index provided by the user is used as the requirement on the area size of the target frame, and calculating the loss function based on the difference between the area size of the candidate target frame and the area size of the region corresponding to the preset target parameter as a part of the loss function.
Further, the obtaining a predicted target parameter of the first path of video image at the next time based on the target parameter of the first path of video image at the current time includes:
(1) acquiring the position of a target pixel point in a target area at the current moment;
(2) generating a plurality of candidate mobile positions of the target pixel point based on the current position of the target pixel point;
(3) determining the probability value of the target pixel point moving to the candidate mobile position at the next moment based on the similarity of the image characteristics of the candidate mobile position and the image characteristics of the target pixel point position;
(4) acquiring the predicted position of the target pixel point at the next moment based on the candidate mobile position and the corresponding probability value, and forming a candidate target area based on the predicted positions of all the target pixel points at the next moment;
(5) judging whether the candidate target area meets the condition, if not, re-acquiring a plurality of candidate mobile positions based on the current probability value distribution of the candidate mobile positions, and returning to the step (3) until the candidate target area meets the condition;
(6) and acquiring the position of a target pixel point of the first path of video image at the next moment based on the candidate target area.
Specifically, the second image processing method includes:
acquiring a target region cutting parameter of the first image based on the predicted target parameter of the first image at the time t;
and cropping the first image based on the target area cropping parameters of the first image.
In the embodiment of the application, the first image processing method is used for compressing and transmitting the first image and outputting the low-resolution global monitoring video image, the second image processing method is used for cutting the target area of the first image and compressing and transmitting the cut target area model, so that the transmission and display of the important area image in the scene monitoring video in high-resolution data and the retention of the detail characteristics of the local pixel area are realized.
With respect to the embodiment of the method described above, an embodiment of the present invention provides an image output system of a large-resolution monitoring camera, as shown in fig. 2, the system includes:
the two paths of video output units are used for synchronously acquiring a first path of video image and a second path of video image respectively through a first image processing method and a second image processing method based on a first image acquired by an image sensor at the moment t, the resolution ratio of the second path of video image is not smaller than that of the first image, and the resolution ratio of the first path of video image is not larger than that of the first image;
the fusion output and parameter feedback unit is used for acquiring and outputting a third path of video image through fusion processing with a second path of video image based on the acquired first path of video image, and meanwhile, performing characteristic analysis on the acquired first path of video image to predict target parameters of the first image at the time of t + 1;
and the second image processing method processes the first image based on the predicted target parameter of the first image at the time t to acquire a second path of video image.
An embodiment of the present application further provides an electronic device, where the electronic device includes:
a processor;
a memory for storing processor-executable instructions;
the processor executes the executable instructions to realize the image output method of the large-resolution monitoring camera.
Specifically, the electronic device according to the embodiment of the present application includes a processor, a memory, and a communication bus, where the processor and the memory complete communication with each other through the communication bus, and the communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
Embodiments of the present application also provide a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the image output method of the large-resolution monitoring camera are implemented. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The present invention is not limited to the above-described embodiments, and those skilled in the art will be able to make various modifications without creative efforts from the above-described conception, and fall within the scope of the present invention.
Claims (10)
1. An image output method of a large-resolution monitoring camera is characterized by comprising the following steps:
based on a first image acquired by an image sensor at the moment t, a first path of video image and a second path of video image are synchronously acquired by a first image processing method and a second image processing method respectively, the resolution of the second path of video image is not smaller than that of the first image, and the resolution of the first path of video image is not larger than that of the first image;
acquiring a third path of video image through fusion processing with a second path of video image based on the acquired first path of video image and outputting the third path of video image, and simultaneously performing feature analysis on the acquired first path of video image to predict target parameters of the first image at the t +1 moment;
and the second image processing method processes the first image based on the predicted target parameter of the first image at the time t to acquire a second path of video image.
2. The method as claimed in claim 1, further comprising displaying the first path of video image and the second path of video image synchronously via a display.
3. The image output method of a large-resolution monitoring camera according to claim 1, wherein the performing feature analysis on the acquired first path of video image to predict the target parameter of the first image at the time t +1 includes:
performing characteristic analysis on the first path of video image at the time t to obtain target parameters of the first path of video image at the time t;
predicting the target parameter of the first path of video image at the t +1 moment based on the target parameter of the first path of video image at the t moment;
and predicting the target parameter of the first image at the t +1 moment based on the conversion relation between the first image and the first path of video image and the predicted target parameter of the first path of video image at the t +1 moment.
4. The image output method of the large-resolution monitoring camera according to claim 3, wherein the performing feature analysis on the first path of video image at the time t to obtain the target parameter of the first path of video image at the time t includes:
acquiring a target pixel area in a first path of video image at the time t, wherein the target pixel area is as follows: forming areas and/or pixel areas with pixel characteristics conforming to preset target characteristics with all pixels with the pixel variation larger than a first preset threshold value at the last moment;
and obtaining the position and size parameters of the best matching target frame for marking the position of the target pixel area based on the target pixel area of the first path of video image.
5. The image output method of a large-resolution monitoring camera according to claim 4, wherein the obtaining of the position and size parameters of the best matching target frame for labeling the position of the target pixel region based on the target pixel region of the first path of video image comprises:
determining that a target in a target pixel area appears for the first time based on the target pixel area of the first path of video image;
acquiring a plurality of candidate target frames based on a target pixel area of the first path of video image;
and comparing the position and the size of the candidate target frames with preset target parameters to obtain a target frame which is best matched with the preset target parameters and obtain the position and the size parameters of the best matched target frame.
6. The image output method of a large-resolution monitoring camera according to claim 5, wherein the comparing with the preset target parameters based on the positions and sizes of the candidate target frames to obtain the target frame best matching with the preset target parameters comprises:
performing a particle swarm optimization algorithm by taking the side length of the candidate target frame and the position parameter of the candidate target frame as a particle and taking a combined function of the proportion of the number of non-target pixels in the candidate target frame and the compatibility of the candidate target frame and the region corresponding to the preset target parameter as a loss function;
and obtaining a target frame which is optimally matched with the preset target parameters based on the optimal solution of the particle swarm optimization algorithm.
7. The image output method of a large-resolution monitoring camera according to claim 4, wherein the second image processing method comprises:
acquiring a target region cutting parameter of the first image based on the predicted target parameter of the first image at the time t;
and cropping the first image based on the target area cropping parameters of the first image.
8. An image output system of a large-resolution monitoring camera, comprising:
the two paths of video output units are used for synchronously acquiring a first path of video image and a second path of video image respectively through a first image processing method and a second image processing method based on a first image acquired by an image sensor at the moment t, the resolution ratio of the second path of video image is not smaller than that of the first image, and the resolution ratio of the first path of video image is not larger than that of the first image;
the fusion output and parameter feedback unit is used for acquiring and outputting a third path of video image through fusion processing with a second path of video image based on the acquired first path of video image, and meanwhile, performing characteristic analysis on the acquired first path of video image to predict target parameters of the first image at the time of t + 1;
and the second image processing method processes the first image based on the predicted target parameter of the first image at the time t to acquire a second path of video image.
9. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory for storing processor-executable instructions;
wherein the processor implements the method of any one of claims 1-7 by executing the executable instructions.
10. A computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210412672.8A CN114866692A (en) | 2022-04-19 | 2022-04-19 | Image output method and system of large-resolution monitoring camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210412672.8A CN114866692A (en) | 2022-04-19 | 2022-04-19 | Image output method and system of large-resolution monitoring camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114866692A true CN114866692A (en) | 2022-08-05 |
Family
ID=82631802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210412672.8A Pending CN114866692A (en) | 2022-04-19 | 2022-04-19 | Image output method and system of large-resolution monitoring camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114866692A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103179360A (en) * | 2011-12-23 | 2013-06-26 | 联发科技股份有限公司 | Video Processing apparatus |
| CN107249107A (en) * | 2017-05-03 | 2017-10-13 | 西安诺瓦电子科技有限公司 | Video controller and image processing method and device |
| CN107657626A (en) * | 2016-07-25 | 2018-02-02 | 浙江宇视科技有限公司 | The detection method and device of a kind of moving target |
| CN109547724A (en) * | 2018-12-21 | 2019-03-29 | 广州华多网络科技有限公司 | A kind of processing method of video stream data, electronic equipment and storage device |
| WO2020172809A1 (en) * | 2019-02-27 | 2020-09-03 | 深圳市大疆创新科技有限公司 | Method for video playback by photography apparatus and photography apparatus |
| CN111932453A (en) * | 2020-07-20 | 2020-11-13 | 合肥富煌君达高科信息技术有限公司 | High-resolution image generation method and high-speed camera integrated with same |
| CN112508787A (en) * | 2020-12-14 | 2021-03-16 | 磐基技术有限公司 | Target detection method based on image super-resolution |
| CN113099146A (en) * | 2019-12-19 | 2021-07-09 | 华为技术有限公司 | Video generation method and device and related equipment |
| WO2021147702A1 (en) * | 2020-01-22 | 2021-07-29 | 华为技术有限公司 | Video processing method and apparatus |
-
2022
- 2022-04-19 CN CN202210412672.8A patent/CN114866692A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103179360A (en) * | 2011-12-23 | 2013-06-26 | 联发科技股份有限公司 | Video Processing apparatus |
| CN107657626A (en) * | 2016-07-25 | 2018-02-02 | 浙江宇视科技有限公司 | The detection method and device of a kind of moving target |
| CN107249107A (en) * | 2017-05-03 | 2017-10-13 | 西安诺瓦电子科技有限公司 | Video controller and image processing method and device |
| CN109547724A (en) * | 2018-12-21 | 2019-03-29 | 广州华多网络科技有限公司 | A kind of processing method of video stream data, electronic equipment and storage device |
| WO2020172809A1 (en) * | 2019-02-27 | 2020-09-03 | 深圳市大疆创新科技有限公司 | Method for video playback by photography apparatus and photography apparatus |
| CN113099146A (en) * | 2019-12-19 | 2021-07-09 | 华为技术有限公司 | Video generation method and device and related equipment |
| WO2021147702A1 (en) * | 2020-01-22 | 2021-07-29 | 华为技术有限公司 | Video processing method and apparatus |
| CN111932453A (en) * | 2020-07-20 | 2020-11-13 | 合肥富煌君达高科信息技术有限公司 | High-resolution image generation method and high-speed camera integrated with same |
| CN112508787A (en) * | 2020-12-14 | 2021-03-16 | 磐基技术有限公司 | Target detection method based on image super-resolution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106662749B (en) | Preprocessor for full parallax light field compression | |
| EP3335416B1 (en) | Digital photographing apparatus and method of operating the same | |
| US20220222776A1 (en) | Multi-Stage Multi-Reference Bootstrapping for Video Super-Resolution | |
| CN115052104B (en) | Image processing method, electronic device, and non-volatile computer-readable storage medium | |
| US9576335B2 (en) | Method, device, and computer program for reducing the resolution of an input image | |
| US10412374B2 (en) | Image processing apparatus and image processing method for imaging an image by utilization of a pseudo image | |
| US20100283589A1 (en) | Image processing system, image capture device and method thereof | |
| TW201503054A (en) | Image processor and image merging method thereof | |
| CN105578129A (en) | Multipath multi-image video splicing device | |
| CN110809101A (en) | Image zooming processing method and device, electronic equipment and storage medium | |
| US20200242393A1 (en) | Image processing apparatus and image processing method | |
| CN103700062A (en) | Image processing method and device | |
| CN112367559A (en) | Video display method and device, electronic equipment, server and storage medium | |
| CN112927241A (en) | Picture capturing and thumbnail generating method, system, equipment and storage medium | |
| JP2019149785A (en) | Video conversion device and program | |
| CN112948627B (en) | Alarm video generation method, display method and device | |
| US9392146B2 (en) | Apparatus and method for extracting object | |
| CN114866692A (en) | Image output method and system of large-resolution monitoring camera | |
| CN113079342A (en) | Target tracking method and system based on high-resolution image device | |
| KR102008672B1 (en) | System for Performing Linkage Operation of Augmented Reality and Event in Association with Camera and Driving Method Thereof | |
| CN112672057B (en) | Shooting method and device | |
| CN114821544A (en) | Perception information generation method and device, vehicle, electronic equipment and storage medium | |
| JP2002314984A (en) | Monitoring camera system | |
| JP2019009615A (en) | Monitoring camera device, monitoring video distribution method, and monitoring system | |
| US11617024B2 (en) | Dual camera regions of interest display |
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 |