CN110022463A - Video interested region intelligent coding method and system are realized under dynamic scene - Google Patents
Video interested region intelligent coding method and system are realized under dynamic scene Download PDFInfo
- Publication number
- CN110022463A CN110022463A CN201910287411.6A CN201910287411A CN110022463A CN 110022463 A CN110022463 A CN 110022463A CN 201910287411 A CN201910287411 A CN 201910287411A CN 110022463 A CN110022463 A CN 110022463A
- Authority
- CN
- China
- Prior art keywords
- picture
- foreground area
- video
- area
- dynamic scene
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000008859 change Effects 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000005055 memory storage Effects 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 238000013461 design Methods 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000006835 compression Effects 0.000 description 6
- 238000007906 compression Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000009123 feedback regulation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- 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
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/167—Position within a video image, e.g. region of interest [ROI]
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The present invention, which provides, realizes video interested region intelligent coding method and system under a kind of dynamic scene.The described method includes: obtaining the batch picture of video image；Picture is spliced, panoramic pictures are obtained；Multiple panoramic pictures are analyzed, the foreground area model of panorama sketch is established；Picture and foreground area model are compared, determines the foreground area of picture；The code rate of foreground area and background area is determined in conjunction with maximum bandwidth according to the dimension scale of foreground area and picture；According to determining code rate, picture is encoded.By real time contrast's picture and corresponding foreground area model, the foreground area of energy automatic identification marking video image recycles area-of-interest intelligent coding coding, so that the camera shooting function of camera site angle change obtains optimal image quality under finite bandwidth；When the technical solution is applied to video monitoring system, a large amount of calculating work are placed on rear end, save the CPU and power consumption resource of video camera, reduce its design and manufacture cost.
Description
Technical field
The present invention relates to video image information processing technology fields, more particularly to realization video sense under a kind of dynamic scene
Interest region intelligent coding method and system.
Background technique
With universal and video monitoring system the extensive application of high-definition video technology, demand of the big flow to high bandwidth
Increasingly increase.Although H.264 the video encoding standard that ITU-T is released has compression ratio relatively high at present, high definition view
Frequency needs the bandwidth of 10Mbps or more to be also still often difficult to meet.
Area-of-interest (Region Of Interest, abbreviation ROI) intelligent coding belongs to intelligent video coding skill
Video pictures are divided into area-of-interest (also referred to as foreground area) and background area by one kind of art, are used to foreground area
The low compression bit rate of high quality is encoded and is encoded to background area using low quality high compression code rate, and area-of-interest view is not being lost
Network bandwidth occupancy is reduced under the premise of frequency quality (reaches saving bandwidth as cost to sacrifice background area video quality
Purpose), and reduce memory space.ROI intelligent coding is directed to fixed static scene (the i.e. camera position and angle of picture
Spend constant) relatively effectively, the part frequently changed in captured scene is automatically recognized as area-of-interest, what other seldom became
Part is background area；And ROI intelligent coding just seems helpless for dynamic scene, especially takes the photograph in holder cruise
As in the shooting use process of head and aerial camera, the content of video pictures is integrally all changing, and ROI intelligent coding is several
Benefit can not be brought.
Therefore, dynamic area and the realization in scene a kind of can need be intelligently identified under dynamic scene at present
The technical solution of ROI intelligently encoding.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide realize video under a kind of dynamic scene
The technical solution of area-of-interest intelligently encoding, so that the video camera that shooting picture is on-fixed scene obtains under finite bandwidth
Optimal picture quality.
In order to achieve the above objects and other related objects, the present invention provides and realizes video interested area under a kind of dynamic scene
Domain intelligent coding method, comprising steps of
Source video information is sampled, the batch picture of video image is obtained；
The picture is spliced, the panoramic pictures under the dynamic scene are obtained；
Analysis identification is carried out multiple described panoramic pictures, and establishes the foreground area model of panorama sketch；
Real time contrast analyzes the picture and the foreground area model, determines the foreground area of the picture；
According to the dimension scale of the foreground area of the picture and the picture, and maximum bandwidth is combined, determines the figure
The code rate of foreground area and background area in piece；And
According to the code rate of foreground area and background area in the picture, area-of-interest is carried out to the picture and is intelligently compiled
Code.
Optionally, true according to the regional change frequency of the video image when being sampled to the source video information
The sample frequency in the fixed region carries out continuous screenshotss operation to the video image to sample, obtains the video image
Batch picture.
Optionally, according to the video acquisition period of the dynamic scene or video acquisition range, image mosaic technology is utilized
Multiple described pictures are spliced, the panoramic pictures under the dynamic scene are obtained.
Optionally, described that multiple described panoramic pictures are analyzed, and establish the step of the foreground area model of panorama sketch
Suddenly include:
Auto-partition is carried out to the panoramic pictures, and extracts area pixel value, is calculated using Binarization methods, edge enhancing
At least one algorithm in method and contour detecting algorithm identifies dynamic area, as foreground area；
Video acquisition time and video acquisition position according to the profile and color difference of each region, and in conjunction with the dynamic scene
It sets, position and label of the foreground area in the panoramic pictures is obtained, using the panoramic pictures after label as institute
Foreground area model is stated, and the foreground area model carries out dynamic more according to the generation frequency of the panoramic pictures after label
Newly.
Optionally, it on the basis of automatically identifying the dynamic area, delimit manually according to the demand of user high preferential
Grade foreground area.
Optionally, on the basis of automatically identifying the dynamic area, based on map level with road, building or place
Delimit the foreground area.
Optionally, on the basis of automatically identifying the dynamic area, contour of object is identified using binarization method, and
According to demand, scene or cost delimit certain objects for the foreground area.
Optionally, the foreground area model carries out dynamic update according to the generation frequency of the panoramic pictures after label
Model formation are as follows: a=1+N*b, wherein a indicate generate the marked panoramic pictures number, N indicate update time
Number, b indicate the number for updating the marked panoramic pictures received every time.
Optionally, the real time contrast analyzes the picture and the foreground area model, determines the prospect of the picture
The step of region includes:
If have not been obtained with the picture in real time the corresponding foreground area model, the picture is not handled
Label；
If getting with the picture corresponding foreground area model in real time, picture described in comparative analysis with it is described
Foreground area model, and video acquisition time and video acquisition position in conjunction with the dynamic scene, obtain the picture and institute
The consistent foreground area of foreground area model is stated, and is marked in the picture.
In addition, in order to achieve the above objects and other related objects, the present invention also provides realize video under a kind of dynamic scene
Area-of-interest intelligently encoding system, comprising:
Picture obtains module, samples to source video information, obtains the batch picture of video image；
Panoramic mosaic module splices the picture, obtains the panoramic pictures under the dynamic scene；
Foreground area identification module carries out analysis identification multiple described panoramic pictures, and establishes the foreground zone of panorama sketch
Domain model；
Model application module carries out real time contrast's analysis to the picture and the foreground area model, determines and mark
The foreground area of the picture；
Data Rate Distribution module obtains the picture that foreground area is marked, according to the foreground area of the picture and institute
The dimension scale of picture is stated, and combines maximum bandwidth, determines the code rate of foreground area and background area in the picture；
Coding/decoding module encodes the picture according to the code rate that the Data Rate Distribution module determines, and solves
Code.
In addition, in order to achieve the above objects and other related objects, the present invention also provides a kind of computer readable storage medium,
It is stored thereon with computer program, any of the above-described the method is realized when which is executed by processor.
In addition, in order to achieve the above objects and other related objects, the present invention also provides a kind of electric terminals, comprising: processing
Device and memory；
The memory is used to execute the computer of the memory storage for storing computer program, the processor
Program, so that the terminal executes any of the above-described the method.
As described above, realizing the technical solution of video interested region intelligently encoding under dynamic scene of the invention, have
Below the utility model has the advantages that
The present invention automatic identification and can be marked dynamic by the corresponding foreground area model of real time contrast's analysis picture
The foreground area of video image under state scene, instead of in the prior art using the mistake for being manually operated manually label prospect
Journey saves cost of labor；Automatic identification marks the foreground area of video image under dynamic scene and then passes through region of interest
Domain intelligent coding is encoded so that the video camera of camera site or angle change can also be obtained under finite bandwidth it is optimal
Picture quality；When the technical solution is applied to video monitoring system, a large amount of calculating work of video pictures can be placed on
Back-end system saves the CPU and power consumption resource of front-end camera, reduces the design and manufacture cost of video camera, to improve
Practicability of the technical solution under more application scenarios.
Detailed description of the invention
Fig. 1 is the flow chart that video interested region intelligent coding method is realized under dynamic scene.
Fig. 2 is the structural schematic diagram that video interested region intelligently encoding system is realized under dynamic scene.
Fig. 3 is the structural schematic diagram that the video monitoring system of area-of-interest intelligently encoding is realized under dynamic scene.
Specific embodiment
As it is aforementioned it is mentioned in the background technology, quiet fixed for shooting picture of existing ROI intelligent coding
State scene is more effective, and does not almost work to the dynamic scene of shooting picture overall variation.
Based on this, the present invention provides a kind of technology that video interested region intelligently encoding can be realized under dynamic scene
Scheme, first identifies and marks the foreground area of video image of the video camera under dynamic scene, then passes through video interested region
Intelligent coding is encoded, so that the video camera of camera site or angle change (take the photograph by such as holder cruise camera or take photo by plane
Camera) optimal picture quality can be also obtained under finite bandwidth.
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.
It please refers to Fig.1 to Fig.3, Fig. 1 is shown as realizing the stream of video interested region intelligent coding method under dynamic scene
Cheng Tu, Fig. 2 are shown as realizing that the structural schematic diagram of video interested region intelligently encoding system, Fig. 3 are dynamic under dynamic scene
The structural schematic diagram of the video monitoring system of area-of-interest intelligently encoding is realized under scene.It should be noted that the present embodiment
Provided in diagram the basic conception that only the invention is illustrated in a schematic way, rather than to limit the enforceable model of the present invention
It encloses, relativeness is altered or modified, also enforceable when being considered as the present invention under the premise of no substantial technological content alteration
Scope.
In this present embodiment, as shown in Figure 1, the present invention, which provides, realizes video interested region intelligence under a kind of dynamic scene
Coding method, comprising steps of
S1, source video information is sampled, obtains the batch picture of video image；
S2, the picture is spliced, obtains the panoramic pictures under the dynamic scene；
S3, analysis identification is carried out multiple described panoramic pictures, and establishes the foreground area model of panorama sketch；
S4, real time contrast analyze the picture and the foreground area model, determine the foreground area of the picture；
S5, foreground area and the dimension scale of the picture according to the picture, and maximum bandwidth is combined, described in determination
The code rate of foreground area and background area in picture；And
S6, according to the code rate of foreground area and background area in the picture, area-of-interest intelligence is carried out to the picture
It can coding.
Meanwhile in this present embodiment, as shown in Fig. 2, being moved the present invention also provides a kind of with what above-mentioned coding method was adapted
Video interested region intelligently encoding system is realized under state scene, realizes that video interested region is intelligently compiled under the dynamic scene
Code system includes that picture obtains module, panoramic mosaic module, foreground area identification module, model application module, Data Rate Distribution mould
Block and coding/decoding module.
In detail, in step sl, module is obtained using the picture to carry out the collected source video information of video camera
Sampling, obtains the batch picture of video image.
In more detail, in step sl, the sampling in the region is determined according to the regional change frequency of the video image
Frequency, the picture obtain module and carry out continuous screenshotss operation to the video image by screenshotss software to sample, and obtain institute
Multiple the described pictures stating the batch picture of video image, and will acquire are sent to the panoramic mosaic module and the model is answered
With module, as shown in Figure 2.
It wherein, can be according to some regional change frequency since regional change frequency each in the video image is different
The sample frequency for providing the area data, further provides storage scheme.In one specific embodiment, it is assumed that the frame amount of video is
20 frames/second, the regional change are 1200 frames, then the sample frequency of corresponding data is 1 time/min.The frequency changed according to different zones
Rate presets the picture and obtains time, sampling period and the quantity for obtaining the picture that module obtains the picture, cleverer
Living convenient, the recognition result and template definition finally obtained is more accurate.
In detail, in step s 2, using the panoramic mosaic module, the picture is spliced, is obtained described dynamic
Complete panoramic pictures under state scene.Wherein, with the video acquisition period of the dynamic scene (such as holder cruise camera
Holder cruises the period) or video acquisition range (such as the flight longitude and latitude of aerial camera) as splicing according to come as described in splicing
Panoramic pictures.
In more detail, in step s 2, it according to the video acquisition period of the dynamic scene or video acquisition range, utilizes
Image mosaic technology splices multiple described pictures, to obtain the panoramic pictures under the dynamic scene.Wherein, to holder
It cruises for camera, complete panoramic pictures can be obtained in the video in period of cruising from one；It, can for aerial camera
To obtain panoramic pictures from longitude and latitude setting panoramic range, such as by the flight path combination live-action map that unmanned plane is set.It spells
The panoramic pictures connect should do appropriate cut and modify in favor of subsequent modeling.
It,, will if its holder cruise period is 3s for a holder cruise camera in one specific embodiment
The period of splicing picture is also set to 3s, multiple the described figures that will be got in the cycle time using described image splicing
Piece is spliced, and the panoramic pictures of the dynamic scene of the holder cruise camera shooting are obtained.Another specific implementation
In example, for an aerial camera, by " longitude 106.47839057611614,29.628149259317723 " position of latitude
Rectilinear flight is set to " longitude 106.48251044916303,29.626209419364315 " position of latitude, then setting acquisition should
The live-action map of range, and splice to obtain the panoramic pictures within the scope of this in conjunction with flight path, when taking photo by plane, camera shooting group reaches two
When the longitude and latitude position of boundary, then splice again, is continuously available new panoramic pictures.
In detail, in step s3, using the foreground area identification module, the panoramic mosaic module is generated more
Zhang Suoshu panoramic pictures are analyzed, and establish the foreground area model of panorama sketch.Wherein, the foreground area identification module master
The dynamic area for analyzing and identifying multiple panoramic pictures, using as foreground area, then according to certain strategy and algorithm
Establish the foreground area model of panorama sketch.
In more detail, in step s3, the identification of foreground area does not need algorithmically very accurate, should be simple as far as possible
Change, for example accounts for the dynamic range of the band covering 80% of picture size 20% in specific region.In one specific embodiment,
The panorama generated by the fully automated delimitation foreground area of given threshold, the panoramic mosaic module is compared by pixel differences
The pixel of picture is 1920*1080, four vertex of the panoramic pictures are (0,0), (100,0), (0,100), (100,
100) when, delimiting the foreground area for marking the panoramic pictures, auto-partition first is carried out to the panoramic pictures, and extract region
Pixel value identifies dynamic area using at least one algorithm in Binarization methods, edge enhancement algorithm and contour detecting algorithm
Domain, as foreground area；Further according to the profile and color difference of each region, and in conjunction with the video acquisition time of the dynamic scene
(such as cruise time of holder cruise camera) and video acquisition position (longitude and latitude of aerial camera, camera angle) letter
Breath, obtain position and label of the foreground area in the panoramic pictures, such as a dynamic area position be (0,0),
(50,0)、(0,50)、(50,50)。
Further, in step s3, delimitation on the basis of identifying the dynamic area, to the foreground area
Can also be according to the demand of user, photographed scene, the shooting factors flexible choice such as cost, including but not limited to following mode of operation:
Delimit high priority foreground area manually according to the demand of user；Based on map level described in the delimitation of road, building or place
Foreground area；Contour of object is identified by the methods of binaryzation, and according to demand, scene or cost by certain objects delimitation be described
Foreground area.
In more detail, in step s3, after delimiting the foreground area for marking the panoramic pictures, by the institute after label
Panoramic pictures are stated as the foreground area model, and the foreground area model is according to the life of the panoramic pictures after label
Dynamic update is carried out at frequency.It is opened for example, it is assumed that the panoramic pictures for having delimited label foreground area update b every time, then institute
Foreground area identification module is stated after receiving the b panoramic pictures, the b panoramic pictures are merged to obtain new
The panoramic pictures of marked foreground area substitute previous foreground area model and are updated as foreground area model.It is right
The model formation answered are as follows: a=1+N*b, wherein a indicates that the number of the marked panoramic pictures generated, N indicate to update
Number, b indicate the number for updating the marked panoramic pictures received every time.
Further, the coding method further comprises the steps of: keeps records of the foreground area model in real time, as next time
The benchmark of analysis modeling, to reduce modeling time next time.
In detail, in step s 4, using the model application module, real time contrast analyzes the picture and the prospect
Regional model determines the foreground area of the picture.Wherein, the picture and the foreground area model are analyzed in real time contrast
When, it is also necessary in conjunction with the video acquisition time (such as cruise time of holder cruise camera) of the dynamic scene and video acquisition
The information such as position (longitude and latitude and camera angle of aerial camera) and the foreground area model real time contrast determine current
The foreground area of picture.
In more detail, the real time contrast analyzes the picture and the foreground area model, before determining the picture
The step S4 of scene area further comprises:
If S41, have not been obtained with the picture in real time the corresponding foreground area model, not to the picture carry out
Processing label；
If S42, getting with the picture corresponding foreground area model in real time, picture described in comparative analysis with
The foreground area model, and in conjunction with the picture corresponding video acquisition time (such as cruise time of holder cruise camera)
With video acquisition position (longitude and latitude and camera angle of aerial camera), the picture and the foreground area model are obtained
Consistent foreground area, and marked in the picture.
In detail, in step s 5, using the Data Rate Distribution module, according to the foreground area of the picture and the figure
The dimension scale of piece, and maximum bandwidth is combined, determine the code rate of foreground area and background area in the picture.Wherein, if institute
Picture is stated not by processing label, i.e., the foreground area of the described picture delimit label, then the code rate of the picture is to be
The code rate for default of uniting, does not distinguish foreground area and background area.
In more detail, in step s 5, according to the size constancy of maximum bandwidth and the picture, if the foreground area
Position is bigger, then foreground image credit rating is lower under finite bandwidth, lower to the code rate ratio of foreground area distribution；
If the position of the foreground area is smaller, foreground image credit rating is higher under finite bandwidth, to the foreground area point
The code rate ratio matched is higher.That is Data Rate Distribution ratio K=prospect code rate/total bitrate=foreground area/gross area.
In detail, in step s 6, using the coding/decoding module, according to foreground area and background in the picture
The code rate in region, according to the technical standards such as H.264, using area-of-interest intelligent coding to foreground area and background area
It is encoded, further decoding after transmission obtains the video of the foreground area of high quality and the background area of lower quality, thus real
The area-of-interest intelligently encoding of video under existing dynamic scene.
In detail, in step s 6, when being encoded to the picture, using the FMO type 2 in H.264 technical standard
(i.e. foreground and background mode) is encoded, more preferential than the NALU of background area described in the NALU priority ratio of the foreground area
Grade is high (wanting height in the code rate distributed when the high regional code of NALU priority the region low with respect to NALU priority)；When decoding,
The expression of NALU priority height can be used smaller compression ratio algorithm and perform image display to corresponding region, therefore to the foreground area
Using smaller compression ratio algorithm, larger compression ratio algorithm process is used to the background area, so that the foreground area is clear
Clear degree is higher than the background area.
In addition, the present embodiment also provides a kind of computer readable storage medium, it is stored thereon with computer program, the program
Any one of the present embodiment method is realized when being executed by processor.
Computer readable storage medium in the present embodiment, those of ordinary skill in the art will appreciate that: it realizes above-mentioned each
The all or part of the steps of embodiment of the method can be completed by the relevant hardware of computer program.Computer program above-mentioned
It can be stored in a computer readable storage medium.The program when being executed, executes the step including above-mentioned each method embodiment
Suddenly；And storage medium above-mentioned includes: the various media that can store program code such as ROM, RAM, magnetic or disk.
In addition, the present embodiment also provides a kind of electric terminal, comprising: processor and memory；
The memory is used to execute the computer of the memory storage for storing computer program, the processor
Program, so that the terminal executes any one of the present embodiment method.
Electric terminal provided in this embodiment, including processor, memory, transceiver and communication interface, memory and logical
Letter interface connect with processor and transceiver and completes mutual communication, and for storing computer program, communication connects memory
For mouth for being communicated, processor and transceiver make electric terminal execute each of method as above for running computer program
Step.
In the present embodiment, memory may include random access memory (Random Access Memory, abbreviation
RAM), it is also possible to further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
Abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.；It can also be digital signal processor
(Digital Signal Processing, abbreviation DSP), specific integrated circuit (Application Specific
Integrated Circuit, abbreviation ASIC), field programmable gate array (Field-Programmable Gate Array,
Abbreviation FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.
In addition, in a specific embodiment, video interested region intelligently encoding will be realized under the dynamic scene
Technical solution is applied in video monitoring system, specifically, as shown in figure 3, the video monitoring system is adopted including at least video
Realize that video interested region intelligently encoding system and client modules, the video are adopted under collection module, the dynamic scene
Collect module (such as holder cruise camera or aerial camera) described source video information of acquisition, and the source video information is transmitted
Module is obtained to the picture realized in video interested region intelligently encoding system under the dynamic scene；The client modules
After receiving the decoding that the coding/decoding module realized in video interested region intelligently encoding system under the dynamic scene provides
Video information and display, the client modules also have parameter configuration function with video acquisition module described in feedback regulation,
Video interested region intelligently encoding system is realized under the dynamic scene.
Wherein, the video acquisition module is only responsible for the acquisition of the source video information, the analysis of video pictures, mark substantially
Note, comparison etc. calculate work and are placed under the dynamic scene in realization video interested region intelligently encoding system, thus effectively
The CPU and power consumption resource for saving the video acquisition module, reduce its design and manufacture cost.
In conclusion realizing the technical solution of video interested region intelligently encoding under dynamic scene provided by the present invention
By the corresponding foreground area model of real time contrast's analysis picture, automatic identification and video figure under dynamic scene can be marked
The foreground area of picture, instead of using the process for being manually operated manually label prospect, save in the prior art manually at
This；Automatic identification marks the foreground area of video image under dynamic scene and then passes through area-of-interest intelligent coding
It is encoded, so that the video camera of camera site or angle change can also obtain optimal picture quality under finite bandwidth；It will
Realize that the technical solution of video interested region intelligently encoding is applied to video monitoring system under dynamic scene provided by the present invention
When system, a large amount of calculating work of video pictures back-end system be can be placed on, the CPU and power consumption money of front-end camera saved
Source, reduces the design and manufacture cost of video camera, realizes that video interested region is intelligently compiled under the dynamic scene to improve
Practicability of the technical solution of code under more application scenarios.
Above-described embodiment is merely exemplary to illustrate technical solution of the present invention principle, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (12)
1. realizing video interested region intelligent coding method under a kind of dynamic scene, which is characterized in that comprising steps of
Source video information is sampled, the batch picture of video image is obtained；
The picture is spliced, the panoramic pictures under the dynamic scene are obtained；
Analysis identification is carried out multiple described panoramic pictures, and establishes the foreground area model of panorama sketch；
Real time contrast analyzes the picture and the foreground area model, determines the foreground area of the picture；
According to the dimension scale of the foreground area of the picture and the picture, and maximum bandwidth is combined, determined in the picture
The code rate of foreground area and background area；And
According to the code rate of foreground area and background area in the picture, area-of-interest intelligently encoding is carried out to the picture.
2. realizing video interested region intelligent coding method under dynamic scene according to claim 1, which is characterized in that
When sampling to the source video information, the sampling in the region is determined according to the regional change frequency of the video image
Frequency carries out continuous screenshotss operation to the video image to sample, obtains the batch picture of the video image.
3. realizing video interested region intelligent coding method under dynamic scene according to claim 1, which is characterized in that
According to the video acquisition period of the dynamic scene or video acquisition range, using image mosaic technology multiple described pictures into
Row splicing, obtains the panoramic pictures under the dynamic scene.
4. realizing video interested region intelligently encoding side under dynamic scene as claimed in any of claims 1 to 3
Method, which is characterized in that it is described that multiple described panoramic pictures are analyzed, and the step of establishing the foreground area model of panorama sketch
Include:
Auto-partition is carried out to the panoramic pictures, and extracts area pixel value, using Binarization methods, edge enhancement algorithm and
At least one algorithm in contour detecting algorithm automatically identifies dynamic area, as foreground area；
Video acquisition time and video acquisition position according to the profile and color difference of each region, and in conjunction with the dynamic scene,
Position and label of the foreground area in the panoramic pictures are obtained, using the panoramic pictures after label as before described
Scenic spot domain model, and the foreground area model carries out dynamic update according to the generation frequency of the panoramic pictures after label.
5. realizing video interested region intelligent coding method under dynamic scene according to claim 4, which is characterized in that
On the basis of automatically identifying the dynamic area, high priority foreground area delimited manually according to the demand of user.
6. realizing video interested region intelligent coding method under dynamic scene according to claim 4, which is characterized in that
On the basis of automatically identifying the dynamic area, the foreground zone delimited with road, building or place based on map level
Domain.
7. realizing video interested region intelligent coding method under dynamic scene according to claim 4, which is characterized in that
On the basis of automatically identifying the dynamic area, using binarization method identify contour of object, and according to demand, scene or
Cost delimit certain objects for the foreground area.
8. realizing video interested region intelligent coding method under dynamic scene according to claim 4, which is characterized in that
The foreground area model carries out the model formation of dynamic update according to the generation frequency of the panoramic pictures after label are as follows: a
=1+N*b, wherein a indicates that the number of the marked panoramic pictures generated, N indicate update times, and b is indicated every time more
The number of the marked panoramic pictures newly received.
9. realizing video interested region intelligent coding method under dynamic scene according to claim 1, which is characterized in that
The step of real time contrast analyzes the picture and the foreground area model, determines the foreground area of the picture include:
If have not been obtained with the picture in real time the corresponding foreground area model, processing mark is not carried out to the picture
Note；
If getting with the picture corresponding foreground area model in real time, picture and the prospect described in comparative analysis
Regional model, and video acquisition time and video acquisition position in conjunction with the dynamic scene, obtain the picture and it is described before
The consistent foreground area of scenic spot domain model, and marked in the picture.
10. realizing video interested region intelligently encoding system under a kind of dynamic scene characterized by comprising
Picture obtains module, samples to source video information, obtains the batch picture of video image；
Panoramic mosaic module splices the picture, obtains the panoramic pictures under the dynamic scene；
Foreground area identification module carries out analysis identification multiple described panoramic pictures, and establishes the foreground area mould of panorama sketch
Type；
Model application module carries out real time contrast's analysis to the picture and the foreground area model, determines and marks described
The foreground area of picture；
Data Rate Distribution module obtains the picture that foreground area is marked, according to the foreground area of the picture and the figure
The dimension scale of piece, and maximum bandwidth is combined, determine the code rate of foreground area and background area in the picture；
Coding/decoding module encodes the picture according to the code rate that the Data Rate Distribution module determines, and decodes.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Any one of claims 1 to 9 the method is realized when execution.
12. a kind of electric terminal characterized by comprising processor and memory；
The memory is used to execute the computer journey of the memory storage for storing computer program, the processor
Sequence, so that the terminal executes such as any one of claims 1 to 9 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910287411.6A CN110022463A (en) | 2019-04-11 | 2019-04-11 | Video interested region intelligent coding method and system are realized under dynamic scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910287411.6A CN110022463A (en) | 2019-04-11 | 2019-04-11 | Video interested region intelligent coding method and system are realized under dynamic scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110022463A true CN110022463A (en) | 2019-07-16 |
Family
ID=67191104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910287411.6A Pending CN110022463A (en) | 2019-04-11 | 2019-04-11 | Video interested region intelligent coding method and system are realized under dynamic scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110022463A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110708570A (en) * | 2019-10-21 | 2020-01-17 | 腾讯科技（深圳）有限公司 | Video coding rate determining method, device, equipment and storage medium |
| CN110784745A (en) * | 2019-11-26 | 2020-02-11 | 科大讯飞股份有限公司 | Video transmission method, device, system, equipment and storage medium |
| CN111191654A (en) * | 2019-12-30 | 2020-05-22 | 重庆紫光华山智安科技有限公司 | Road data generation method and device, electronic equipment and storage medium |
| CN111210487A (en) * | 2020-02-28 | 2020-05-29 | 深圳壹账通智能科技有限公司 | Pattern generation method and system |
| CN111277827A (en) * | 2020-02-24 | 2020-06-12 | 腾讯科技（深圳）有限公司 | Video data processing method, device, equipment and readable storage medium |
| CN111553842A (en) * | 2020-04-24 | 2020-08-18 | 京东方科技集团股份有限公司 | Spliced picture display method and device, electronic equipment and storage medium |
| CN111726640A (en) * | 2020-07-03 | 2020-09-29 | 中图云创智能科技(北京)有限公司 | Live broadcast method with 0-360 degree dynamic viewing angle |
| CN112367521A (en) * | 2020-10-27 | 2021-02-12 | 广州华多网络科技有限公司 | Display screen content sharing method and device, computer equipment and storage medium |
| CN112468845A (en) * | 2020-11-16 | 2021-03-09 | 维沃移动通信有限公司 | Processing method and processing device for screen projection picture |
| WO2021056766A1 (en) * | 2019-09-29 | 2021-04-01 | 深圳传音控股股份有限公司 | Video screen capture method, terminal, and computer-readable storage medium |
| CN112995488A (en) * | 2019-12-12 | 2021-06-18 | 深圳富泰宏精密工业有限公司 | High-resolution video image processing method and device and electronic equipment |
| CN117915117A (en) * | 2024-01-25 | 2024-04-19 | 太一云境技术有限公司 | Accompanying communication care method, system, computer equipment and storage medium thereof |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005096508A1 (en) * | 2004-04-01 | 2005-10-13 | Beijing Media Works Co., Ltd | Enhanced audio encoding and decoding equipment, method thereof |
| CN101252687A (en) * | 2008-03-20 | 2008-08-27 | 上海交通大学 | Method for Realizing Multi-channel Combined Region of Interest Video Coding and Transmission |
| CN101494785A (en) * | 2008-12-19 | 2009-07-29 | 无锡亿普得科技有限公司 | Method for encoding H.264 interesting region |
| CN102006472A (en) * | 2010-11-18 | 2011-04-06 | 无锡中星微电子有限公司 | Video bitrate control system and method thereof |
| CN102905200A (en) * | 2012-08-07 | 2013-01-30 | 上海交通大学 | Method and system for dual-stream encoding and transmission of video region of interest |
| CN103903269A (en) * | 2014-04-10 | 2014-07-02 | 公安部第三研究所 | Structural description method and system of dome camera monitor video |
| CN106331711A (en) * | 2016-08-26 | 2017-01-11 | 北京工业大学 | A Dynamic Bit Rate Control Method Based on Network Features and Video Features |
| CN108334831A (en) * | 2018-01-26 | 2018-07-27 | 中南大学 | A kind of monitoring image processing method, monitoring terminal and system |
| CN108737826A (en) * | 2017-04-18 | 2018-11-02 | 中兴通讯股份有限公司 | A kind of method and apparatus of Video coding |
| CN109584272A (en) * | 2018-11-16 | 2019-04-05 | 北京中竞鸽体育文化发展有限公司 | A kind of method and device for establishing moving object flight model |
-
2019
- 2019-04-11 CN CN201910287411.6A patent/CN110022463A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005096508A1 (en) * | 2004-04-01 | 2005-10-13 | Beijing Media Works Co., Ltd | Enhanced audio encoding and decoding equipment, method thereof |
| CN101252687A (en) * | 2008-03-20 | 2008-08-27 | 上海交通大学 | Method for Realizing Multi-channel Combined Region of Interest Video Coding and Transmission |
| CN101494785A (en) * | 2008-12-19 | 2009-07-29 | 无锡亿普得科技有限公司 | Method for encoding H.264 interesting region |
| CN102006472A (en) * | 2010-11-18 | 2011-04-06 | 无锡中星微电子有限公司 | Video bitrate control system and method thereof |
| CN102905200A (en) * | 2012-08-07 | 2013-01-30 | 上海交通大学 | Method and system for dual-stream encoding and transmission of video region of interest |
| CN102905200B (en) * | 2012-08-07 | 2015-01-14 | 上海交通大学 | Video interesting region double-stream encoding and transmitting method and system |
| CN103903269A (en) * | 2014-04-10 | 2014-07-02 | 公安部第三研究所 | Structural description method and system of dome camera monitor video |
| CN106331711A (en) * | 2016-08-26 | 2017-01-11 | 北京工业大学 | A Dynamic Bit Rate Control Method Based on Network Features and Video Features |
| CN108737826A (en) * | 2017-04-18 | 2018-11-02 | 中兴通讯股份有限公司 | A kind of method and apparatus of Video coding |
| CN108334831A (en) * | 2018-01-26 | 2018-07-27 | 中南大学 | A kind of monitoring image processing method, monitoring terminal and system |
| CN109584272A (en) * | 2018-11-16 | 2019-04-05 | 北京中竞鸽体育文化发展有限公司 | A kind of method and device for establishing moving object flight model |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021056766A1 (en) * | 2019-09-29 | 2021-04-01 | 深圳传音控股股份有限公司 | Video screen capture method, terminal, and computer-readable storage medium |
| CN110708570A (en) * | 2019-10-21 | 2020-01-17 | 腾讯科技（深圳）有限公司 | Video coding rate determining method, device, equipment and storage medium |
| CN110784745A (en) * | 2019-11-26 | 2020-02-11 | 科大讯飞股份有限公司 | Video transmission method, device, system, equipment and storage medium |
| CN110784745B (en) * | 2019-11-26 | 2021-12-07 | 科大讯飞股份有限公司 | Video transmission method, device, system, equipment and storage medium |
| CN112995488A (en) * | 2019-12-12 | 2021-06-18 | 深圳富泰宏精密工业有限公司 | High-resolution video image processing method and device and electronic equipment |
| CN111191654A (en) * | 2019-12-30 | 2020-05-22 | 重庆紫光华山智安科技有限公司 | Road data generation method and device, electronic equipment and storage medium |
| CN111277827B (en) * | 2020-02-24 | 2022-12-20 | 腾讯科技（深圳）有限公司 | Video data processing method, device, equipment and readable storage medium |
| CN111277827A (en) * | 2020-02-24 | 2020-06-12 | 腾讯科技（深圳）有限公司 | Video data processing method, device, equipment and readable storage medium |
| US11871017B2 (en) | 2020-02-24 | 2024-01-09 | Tencent Technology (Shenzhen) Company Limited | Video data processing |
| CN111210487A (en) * | 2020-02-28 | 2020-05-29 | 深圳壹账通智能科技有限公司 | Pattern generation method and system |
| CN111553842A (en) * | 2020-04-24 | 2020-08-18 | 京东方科技集团股份有限公司 | Spliced picture display method and device, electronic equipment and storage medium |
| CN111553842B (en) * | 2020-04-24 | 2024-03-12 | 京东方科技集团股份有限公司 | Spliced picture display method and device, electronic equipment and storage medium |
| CN111726640A (en) * | 2020-07-03 | 2020-09-29 | 中图云创智能科技(北京)有限公司 | Live broadcast method with 0-360 degree dynamic viewing angle |
| CN112367521A (en) * | 2020-10-27 | 2021-02-12 | 广州华多网络科技有限公司 | Display screen content sharing method and device, computer equipment and storage medium |
| CN112468845A (en) * | 2020-11-16 | 2021-03-09 | 维沃移动通信有限公司 | Processing method and processing device for screen projection picture |
| CN117915117A (en) * | 2024-01-25 | 2024-04-19 | 太一云境技术有限公司 | Accompanying communication care method, system, computer equipment and storage medium thereof |
| CN117915117B (en) * | 2024-01-25 | 2024-08-06 | 太一云境技术有限公司 | Accompanying communication care method, system, computer equipment and storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110022463A (en) | Video interested region intelligent coding method and system are realized under dynamic scene | |
| EP4261778A1 (en) | Posture estimation method related apparatus | |
| WO2020151172A1 (en) | Moving object detection method and apparatus, computer device, and storage medium | |
| CN111739027B (en) | Image processing method, device, equipment and readable storage medium | |
| CN110379020B (en) | Laser point cloud coloring method and device based on generation countermeasure network | |
| US20220319168A1 (en) | Method for estimating and presenting passenger flow, system, and computer readable storage medium | |
| CN110853032A (en) | Unmanned aerial vehicle video aesthetic quality evaluation method based on multi-mode deep learning | |
| CN106971155B (en) | Unmanned vehicle lane scene segmentation method based on height information | |
| CN110706269B (en) | Binocular vision SLAM-based dynamic scene dense modeling method | |
| CN105678216A (en) | Spatio-temporal data stream video behavior recognition method based on deep learning | |
| CN111080746B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN105574848A (en) | A method and an apparatus for automatic segmentation of an object | |
| CN111382647B (en) | Picture processing method, device, equipment and storage medium | |
| US20140233802A1 (en) | Increased Quality of Image Objects Based on Depth in Scene | |
| CN113610720B (en) | Video denoising method and device, computer readable medium and electronic device | |
| CN112307853A (en) | Detection method of aerial image, storage medium and electronic device | |
| CN111383204A (en) | Video image fusion method, fusion device, panoramic monitoring system and storage medium | |
| US20240320971A1 (en) | Pre-processing image frames based on camera statistics | |
| CN102306307A (en) | Positioning method of fixed point noise in color microscopic image sequence | |
| CN113010736A (en) | Video classification method and device, electronic equipment and storage medium | |
| CN112802027A (en) | Target object analysis method, storage medium and electronic device | |
| CN113253890B (en) | Video image matting method, system and medium | |
| CN115249221A (en) | Image processing method and device and cloud equipment | |
| CN112581495A (en) | Image processing method, device, equipment and storage medium | |
| CN117395424B (en) | Video optimization method for video wireless transmission monitoring system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |
|
| RJ01 | Rejection of invention patent application after publication |