CN108257159A - A kind of audio-video monitoring server-side, system and method - Google Patents
A kind of audio-video monitoring server-side, system and method Download PDFInfo
- Publication number
- CN108257159A CN108257159A CN201711287455.6A CN201711287455A CN108257159A CN 108257159 A CN108257159 A CN 108257159A CN 201711287455 A CN201711287455 A CN 201711287455A CN 108257159 A CN108257159 A CN 108257159A
- Authority
- CN
- China
- Prior art keywords
- video
- audio
- moving target
- video frame
- data
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention relates to a kind of audio-video monitoring server-side, system and method, method includes:Obtain audio-video monitoring data;Video image is obtained from the audio-video monitoring data, and detaches the foreground and background of video image, moving target is determined from the prospect;Tracing detection is carried out to the moving target according to mean shift iterations algorithm, obtains tracking result.The present invention obtains video image from monitoring audio/video data, and detaches contexts, according to the operation of video frame in the foreground determine moving target, and can pursuit movement target, show tracking result, can replace manpower search abnormal conditions.
Description
Technical field
The invention mainly relates to technical field of video monitoring, and in particular to a kind of audio-video monitoring server-side, system and side
Method.
Background technology
At present, the application of video monitoring either all plays a crucial role in production or in living, security
Personnel can in real time, intuitively, truly watch the concrete condition of monitoring area by monitor video.When being abnormal situation,
It needs to recall all videos, carries out video playing and search abnormal conditions picture one by one, extremely expend the time.Therefore,
Need a kind of technology that manpower can be replaced to search abnormal conditions.
Invention content
The technical problem to be solved by the present invention is in view of the deficiencies of the prior art, provide a kind of audio-video monitoring server-side,
System and method.
The technical solution that the present invention solves above-mentioned technical problem is as follows:A kind of monitoring method, including:
Obtain audio-video monitoring data;
Video image is obtained from the audio-video monitoring data, and detaches the foreground and background of video image, from described
Moving target is determined in prospect;
Tracing detection is carried out to the moving target according to mean shift iterations algorithm, obtains tracking result.
The beneficial effects of the invention are as follows:Video image is obtained from monitoring audio/video data, and detaches contexts, according to
The operation of video frame in the foreground determine moving target, and can pursuit movement target, obtain tracking result, the standard of target following
True rate is high, manpower can be replaced to search abnormal conditions, quickly found the abnormal situation, improve monitoring efficiency.
Based on the above technical solution, the present invention can also be improved as follows.
Further, the foreground and background of the separation video image, determines moving target from the prospect, specific to wrap
It includes:
The foreground and background of video image is detached according to Cam-shift moving body tracks algorithm, then from the prospect
Moving object contours are extracted, and the moving object contours are subjected to back projection, obtain moving target.
Advantageous effect using above-mentioned further scheme is:The moving object contours in video can be extracted, and are carried out
Back projection, being capable of clearer determining moving target.
Further, it is described that tracing detection is carried out to the moving target according to mean shift iterations algorithm, obtain tracking knot
Fruit specifically includes:
The tracking of moving target that current video frame is calculated according to mean shift iterations algorithm and sequential video frame
Data calculate the initial value of motion target tracking data as next video frame, calculate the tracking data of next video frame, until
The tracking data of moving target in all video frame is calculated and is completed, obtains tracking result.
Advantageous effect using above-mentioned further scheme is:It is constantly calculated, is realized to fortune by mean shift iterations algorithm
The tracking and identification of moving-target.
Further, the tracking data of the moving target that current video frame is calculated is calculated as next video frame
The initial value of motion target tracking data calculates the tracking data of next video frame, until by moving target in all video frame
Tracking data calculate complete, specifically include:
The characteristic value probability density of moving target described in current video frame is calculated according to cuclear density algorithm;
The cluster centre data value of moving target in current video frame is calculated according to Mean-shift mean shift algorithms;
The profile of the moving target of current video frame is detected, and the external of moving target is determined according to the profile
Rectangle frame using the boundary rectangle frame as search window, and obtains search window numerical value according to search window;
Using the characteristic value probability density of current video frame, cluster centre data value and search window numerical value as next video
Frame calculates the initial value of the tracking data of moving target, calculates the tracking data of next video frame, until will be in all video frame
The tracking data of moving target, which calculates, to be completed.
Advantageous effect using above-mentioned further scheme is:Search window is moved along the increased direction in probability density direction
It is dynamic, obtain the movement locus of moving target;It is effective to solve the problems, such as target distortion and block, in the process of motion target tracking
The middle size that can adjust search target size, can be accurately positioned, achieve the purpose that pursuit movement target.
Further, step is further included:Obtain audio data from the audio-video monitoring data, by the audio data into
Row plays.
Another technical solution that the present invention solves above-mentioned technical problem is as follows:A kind of audio-video monitoring server-side, including:
Audio and video acquisition module, for obtaining audio-video monitoring data;
Audio and video processing module, for obtaining video image, and detach video image from the audio-video monitoring data
Foreground and background, from the prospect determine moving target, and according to mean shift iterations algorithm to the moving target into
Line trace detects, and obtains tracking result.
Based on the above technical solution, the present invention can also be improved as follows.
Further, the audio and video processing module is specifically used for:
The foreground and background of video image is detached according to Cam-shift moving body tracks algorithm, then from the prospect
Moving object contours are extracted, and the moving object contours are subjected to back projection, obtain moving target.
Further, the audio and video processing module also particularly useful for:
The tracking of moving target that current video frame is calculated according to mean shift iterations algorithm and sequential video frame
Data calculate the initial value of motion target tracking data as next video frame, calculate the tracking data of next video frame, until
The tracking data of moving target in all video frame is calculated and is completed, obtains tracking result.
Further, the audio and video processing module also particularly useful for:
The characteristic value probability density of moving target described in the current video frame is calculated according to cuclear density algorithm;
The cluster centre data value of moving target in current video frame is calculated according to Mean-shift mean shift algorithms;
The profile of the moving target of current video frame is detected, and the external of moving target is determined according to the profile
Rectangle frame using the boundary rectangle frame as search window, and obtains search window numerical value according to search window;
Using the characteristic value probability density of current video frame, cluster centre data value and search window numerical value as next video
Frame calculates the initial value of the tracking data of moving target, calculates the tracking data of next video frame, until will be in all video frame
The tracking data of moving target, which calculates, to be completed.
Another technical solution that the present invention solves above-mentioned technical problem is as follows:A kind of audio/video monitor and control system, regards including sound
Frequency acquisition front end and the video monitoring server-side;
The audio-video collection front end, for acquiring the audio-video monitoring data of monitoring area, and according to the audio and video
The audio-video monitoring data are sent in audio-video monitoring server-side by the acquisition signal at monitoring service end.
Description of the drawings
Fig. 1 is the method flow diagram of monitoring method that one embodiment of the invention provides;
Fig. 2 is the module frame chart of audio-video monitoring server-side that one embodiment of the invention provides;
Fig. 3 is the module frame chart of audio/video monitor and control system that one embodiment of the invention provides.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
Fig. 1 is the method flow diagram of monitoring method that one embodiment of the invention provides;
As shown in Figure 1, a kind of monitoring method, including:
Obtain audio-video monitoring data;
Video image is obtained from the audio-video monitoring data, and detaches the foreground and background of video image, from described
Moving target is determined in prospect;
Tracing detection is carried out to the moving target according to mean shift iterations algorithm, obtains tracking result.
In above-described embodiment, video image is obtained from monitoring audio/video data, and detach contexts, according to video frame
Operation in the foreground determine moving target, and can pursuit movement target, obtain tracking result, the accuracy rate of target following
Height can replace manpower to search abnormal conditions, quickly found the abnormal situation, improve monitoring efficiency.
Optionally, as one embodiment of the present of invention, the foreground and background of the separation video image, from the prospect
In determine moving target, specifically include:
The foreground and background of video image is detached according to Cam-shift moving body tracks algorithm, then from the prospect
Moving object contours are extracted, and the moving object contours are subjected to back projection, obtain moving target.
In above-described embodiment, the moving object contours in video can be extracted, and carry out back projection, can become apparent from
Determining moving target.
Optionally, as one embodiment of the present of invention, it is described according to mean shift iterations algorithm to the moving target
Tracing detection is carried out, tracking result is obtained, specifically includes:
The tracking of moving target that current video frame is calculated according to mean shift iterations algorithm and sequential video frame
Data calculate the initial value of motion target tracking data as next video frame, calculate the tracking data of next video frame, until
The tracking data of moving target in all video frame is calculated and is completed, obtains tracking result.
It in above-described embodiment, is constantly calculated by mean shift iterations algorithm, realizes tracking and identification to moving target.
Optionally, as one embodiment of the present of invention, the moving target that current video frame is calculated with
Track data calculate the input value of motion target tracking data as next video frame, and calculate next video frame according to input value
Tracking data specifically includes:
The characteristic value probability density of moving target described in current video frame is calculated according to cuclear density algorithm;Specifically, with
Pixel value (multidimensional or gray scale) is corresponding the one of histogram on a certain position of input picture (color characteristic histogram is first obtained)
Value on a bin replaces the pixel value, and the more big probability that just represent the appearance of this pixel value of value on bin is bigger;
The cluster centre data value of moving target in current video frame is calculated according to Mean-shift mean shift algorithms;
The profile of the moving target of current video frame is detected, and the external of moving target is determined according to the profile
Rectangle frame using the boundary rectangle frame as search window, and obtains search window numerical value according to search window;
Using the characteristic value probability density of current video frame, cluster centre data value and search window numerical value as next video
Frame calculates the initial value of the tracking data of moving target, calculates the tracking data of next video frame, until will be in all video frame
The tracking data of moving target, which calculates, to be completed.
Target current location can be obtained, tracking and identification to moving target are realized, when target sizes change
Target area is searched in adjustment that can be adaptive, continues to track.
It further includes, the moving target is carried out according to Mean-shift mean shift algorithms initial when obtaining search window
Change, and the profile of the moving target after initialization is detected, obtain the boundary rectangle frame of moving target profile.
In above-described embodiment, search window is moved along the increased direction in probability density direction, obtains the fortune of moving target
Dynamic rail mark;It is effective to solve the problems, such as target distortion and block, search target ruler can be adjusted during motion target tracking
Very little size can be accurately positioned, and achieve the purpose that pursuit movement target.
Optionally, as one embodiment of the present of invention, step is further included:Sound is obtained from the audio-video monitoring data
Frequency evidence plays out the audio data.
Fig. 2 is the module frame chart of audio-video monitoring server-side that one embodiment of the invention provides;
Optionally, as an alternative embodiment of the invention, as shown in Fig. 2, a kind of audio-video monitoring server-side, including:
Audio and video acquisition module, for obtaining audio-video monitoring data;
Audio and video processing module, for obtaining video image, and detach video image from the audio-video monitoring data
Foreground and background, from the prospect determine moving target, and according to mean shift iterations algorithm to the moving target into
Line trace detects, and obtains tracking result.
Optionally, as one embodiment of the present of invention, display module is further included, for showing the tracking result.
Optionally, as one embodiment of the present of invention, the audio and video processing module is specifically used for:
The foreground and background of video image is detached according to Cam-shift moving body tracks algorithm, then from the prospect
Moving object contours are extracted, and the moving object contours are subjected to back projection, obtain moving target.
Optionally, as one embodiment of the present of invention, the audio and video processing module also particularly useful for:
The tracking of moving target that current video frame is calculated according to mean shift iterations algorithm and sequential video frame
Data calculate the initial value of motion target tracking data as next video frame, calculate the tracking data of next video frame, until
The tracking data of moving target in all video frame is calculated and is completed, obtains tracking result.
Optionally, as one embodiment of the present of invention, the audio and video processing module also particularly useful for:
The characteristic value probability density of moving target described in the current video frame is calculated according to cuclear density algorithm;
The cluster centre data value of moving target in current video frame is calculated according to Mean-shift mean shift algorithms;
The profile of the moving target of current video frame is detected, and the external of moving target is determined according to the profile
Rectangle frame using the boundary rectangle frame as search window, and obtains search window numerical value according to search window;
Using the characteristic value probability density of current video frame, cluster centre data value and search window numerical value as next video
Frame calculates the initial value of the tracking data of moving target, calculates the tracking data of next video frame, until will be in all video frame
The tracking data of moving target, which calculates, to be completed.
Fig. 3 is the module frame chart of audio/video monitor and control system that one embodiment of the invention provides;
Optionally, as one embodiment of the present of invention, as shown in figure 3, a kind of audio/video monitor and control system, including audio and video
Acquire front end and the audio-video monitoring server-side;
The audio-video collection front end, for acquiring the audio, video data of monitoring area, and according to the audio-video monitoring
The audio, video data is sent in audio-video monitoring server-side by the acquisition signal of server-side.
Specifically, the video acquisition front end includes:
Audio collection module, for acquiring the audio data of monitoring area by sound collection equipment;Specifically, sound is adopted
Collection equipment is the refined YES-800G regarding prestige, the desk-top small speaker HIRALIY H7 of multimedia;
Video acquisition module, for passing through the video data for imaging collecting device acquisition monitoring area;Specifically, camera shooting is adopted
Collection equipment is 5,000,000 pixels, the wide-angle high-definition camera of focal length 3.6mm;
Core processing module for the audio data acquired and video data to be carried out coded treatment, obtains audio and video number
According to;
Memory module, for preserving the audio, video data after encoding;Specifically, memory module is single layer cell flash memory
SLC NAND;
First communication module, for establishing wireless connection with the audio-video monitoring server-side, and by the audio and video number
According to being sent in the audio-video monitoring server-side;Specifically, it includes WiFi module and 4G communication modules;
Power module, for each modules with power of audio-video collection front end;
Ethernet module, for module each in audio-video collection front end to be carried out networking connection;Ethernet module includes
Ethernet interface supports 10/100/1000Mbit/s operating modes, it can be achieved that network interface data sends and receivees;
First voice talk module connect for establishing voice with the audio-video monitoring server-side.
Specifically, core processing module includes H.265 compressing processing chip, and kernel is the processing chip of Cortex A7,
Model Hi3516A supports multichannel real-time coding, and video data is encoded using H.265 standard, is compiled according to H.265 video
Video flowing is carried out coding compression by code standard, obtains H.265 video data, video encoder VEDU can support H.265 video mark
Standard, CPU usage is low, and bus bandwidth occupancy is small, and image resolution ratio maximum is supported to can reach 2592*2592, supports CBR/
Tri- kinds of code check control models of VBR/FIXQP, bit rate output range is between 2kbps~40Mbps;Audio data is assisted using audio
View is encoded, and is encoded by audio protocols to obtain audio code stream according to obtained audio data, audio input output interface AIO connects
Mouth completes the recording and broadcasting of sound, audio frequency process can be used sea and think what chip interior integrated for being docked with Audio Codec
1 AIO (including 1 AIP and 1 AOP), wherein AIP supports MCVF multichannel voice frequency to receive, and audio-frequency signal processing module supports 8khz to adopt
Sample rate, supports G711, G726, and the audio coding decoding of ADPCM forms is supported to record and play the audio of LPCM forms;It can basis
Varying environment selects different standards, ensures the stabilization and continuity of video monitoring.
Specifically, on the basis of Fig. 2 embodiments, the audio-video monitoring server-side includes:
Audio and video acquisition module is additionally operable to send acquisition signal to audio-video collection front end;
Second communication module, for establishing wireless connection with the audio-video monitoring server-side according to the acquisition signal,
And the acquisition signal is sent to the audio-video monitoring server-side, and receive the sound that the audio-video monitoring server-side is sent
The audio, video data is transmitted in decoder module by video data;Specifically, it includes WiFi module and 4G communication modules;
Decoder module for the audio, video data to be decoded processing, and will decode obtained audio, video data hair
It send to the audio and video acquisition module;
Video storage modules, for preserving the decoded audio, video data;
Second voice talk module connect for establishing voice with the audio-video collection front end.
The audio-video monitoring server-side further includes audio and video playback module, for the audio, video data to be returned
It puts.
By wireless network connection, audio-video monitoring server-side can be with for audio-video collection front end and audio-video monitoring server-side
It is mobile terminal, monitoring is convenient, convenient for handling emergency.
Specifically, the audio and video processing module of the audio-video monitoring server-side, which includes processing chip sea, thinks Hi3516A.
Audio-video monitoring server-side of the present invention can be any mobile terminal, interior this monitoring programme of installation, with audio and video
When acquisition front end passes through wireless network connection, monitor video and speech talkback can be watched in real time, facilitates monitoring work personnel and sound
Video acquisition front-end person who is talked with, and can be widely used in the fields such as security protection, railway traffic, campus;
Video image can be obtained from monitoring audio/video data automatically, and detaches contexts, according to the operation of video frame
Determine moving target in the foreground, and can pursuit movement target, obtain tracking result, the accuracy rate of target following is high, can
Abnormal conditions are searched instead of manpower, quickly found the abnormal situation, improve monitoring efficiency.
Reader should be understood that in the description of this specification reference term " one embodiment ", " is shown " some embodiments "
The description of example ", " specific example " or " some examples " etc. mean to combine the specific features of the embodiment or example description, structure,
Material or feature are contained at least one embodiment of the present invention or example.In the present specification, above-mentioned term is shown
The statement of meaning property need not be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the different embodiments or examples described in this specification and the spy of different embodiments or examples
Sign is combined.
It is apparent to those skilled in the art that for convenience of description and succinctly, the dress of foregoing description
The specific work process with unit is put, the corresponding process in preceding method embodiment can be referred to, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit, only
A kind of division of logic function, can there is an other dividing mode in actual implementation, for example, multiple units or component can combine or
Person is desirably integrated into another system or some features can be ignored or does not perform.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
Component may or may not be physical unit, you can be located at a place or can also be distributed to multiple networks
On unit.Some or all of unit therein can be selected according to the actual needs to realize the mesh of the embodiment of the present invention
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit is individually physically present or two or more units integrate in a unit.It is above-mentioned integrated
The form that hardware had both may be used in unit is realized, can also be realized in the form of SFU software functional unit.
If integrated unit realized in the form of SFU software functional unit and be independent product sale or in use, can
To be stored in a computer read/write memory medium.Based on such understanding, technical scheme of the present invention substantially or
Saying all or part of the part contribute to the prior art or the technical solution can be embodied in the form of software product
Out, which is stored in a storage medium, is used including some instructions so that a computer equipment
(can be personal computer, server or the network equipment etc.) performs all or part of each embodiment method of the present invention
Step.And aforementioned storage medium includes:It is USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random
Access various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic disc or CD
Matter.
More than, only specific embodiment of the invention, but protection scope of the present invention is not limited thereto is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be wanted with right
Subject to the protection domain asked.
Claims (10)
1. a kind of monitoring method, which is characterized in that including:
Obtain audio-video monitoring data;
Video image is obtained from the audio-video monitoring data, and detaches the foreground and background of video image, from the prospect
In determine moving target;
Tracing detection is carried out to the moving target according to mean shift iterations algorithm, obtains tracking result.
2. monitoring method according to claim 1, which is characterized in that the foreground and background of the separation video image, from
Moving target is determined in the prospect, is specifically included:
The foreground and background of video image is detached according to Cam-shift moving body tracks algorithm, then is extracted from the prospect
Moving object contours, and the moving object contours are subjected to back projection, obtain moving target.
3. monitoring method according to claim 1 or 2, which is characterized in that it is described according to mean shift iterations algorithm to institute
It states moving target and carries out tracing detection, obtain tracking result, specifically include:
The tracking data of moving target that current video frame is calculated according to mean shift iterations algorithm and sequential video frame
The initial value of motion target tracking data is calculated as next video frame, calculates the tracking data of next video frame, until by institute
The tracking data for having moving target in video frame, which calculates, to be completed, and obtains tracking result.
4. monitoring method according to claim 3, which is characterized in that the movement mesh that current video frame is calculated
Target tracking data calculates the initial value of motion target tracking data as next video frame, calculates the tracking number of next video frame
According to, until by all video frame moving target tracking data calculate complete, specifically include:
The characteristic value probability density of moving target described in current video frame is calculated according to cuclear density algorithm;
The cluster centre data value of moving target in current video frame is calculated according to Mean-shift mean shift algorithms;
The profile of the moving target of current video frame is detected, and the boundary rectangle of moving target is determined according to the profile
Frame using the boundary rectangle frame as search window, and obtains search window numerical value according to search window;
Using the characteristic value probability density of current video frame, cluster centre data value and search window numerical value as next video frame meter
The initial value of the tracking data of moving target is calculated, calculates the tracking data of next video frame, until will be moved in all video frame
The tracking data of target, which calculates, to be completed.
5. according to claim 1-4 any one of them monitoring methods, which is characterized in that further include step:From the audio and video
Audio data is obtained in monitoring data, the audio data is played out.
6. a kind of audio-video monitoring server-side, which is characterized in that including:
Audio and video acquisition module, for obtaining audio-video monitoring data;
Audio and video processing module, for obtaining video image from the audio-video monitoring data, and before detaching video image
Scape and background determine moving target from the prospect, and according to mean shift iterations algorithm the moving target is carried out with
Track detects, and obtains tracking result.
7. audio-video monitoring server-side according to claim 6, which is characterized in that the audio and video processing module is specifically used
In:
The foreground and background of video image is detached according to Cam-shift moving body tracks algorithm, then is extracted from the prospect
Moving object contours, and the moving object contours are subjected to back projection, obtain moving target.
8. the audio-video monitoring server-side described according to claim 6 or 7, which is characterized in that the audio and video processing module is also
It is specifically used for:
The tracking data of moving target that current video frame is calculated according to mean shift iterations algorithm and sequential video frame
The initial value of motion target tracking data is calculated as next video frame, calculates the tracking data of next video frame, until by institute
The tracking data for having moving target in video frame, which calculates, to be completed, and obtains tracking result.
9. audio-video monitoring server-side according to claim 8, which is characterized in that the audio and video processing module is also specific
For:
The characteristic value probability density of moving target described in the current video frame is calculated according to cuclear density algorithm;
The cluster centre data value of moving target in current video frame is calculated according to Mean-shift mean shift algorithms;
The profile of the moving target of current video frame is detected, and the boundary rectangle of moving target is determined according to the profile
Frame using the boundary rectangle frame as search window, and obtains search window numerical value according to search window;
Using the characteristic value probability density of current video frame, cluster centre data value and search window numerical value as next video frame meter
The initial value of the tracking data of moving target is calculated, calculates the tracking data of next video frame, until will be moved in all video frame
The tracking data of target, which calculates, to be completed.
10. a kind of audio/video monitor and control system, which is characterized in that including any one of audio-video collection front end and claim 6-9 institute
The video monitoring server-side stated;
The audio-video collection front end, for acquiring the audio-video monitoring data of monitoring area, and according to the audio-video monitoring
The audio-video monitoring data are sent in audio-video monitoring server-side by the acquisition signal of server-side.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711287455.6A CN108257159A (en) | 2017-12-07 | 2017-12-07 | A kind of audio-video monitoring server-side, system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711287455.6A CN108257159A (en) | 2017-12-07 | 2017-12-07 | A kind of audio-video monitoring server-side, system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108257159A true CN108257159A (en) | 2018-07-06 |
Family
ID=62721487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711287455.6A Pending CN108257159A (en) | 2017-12-07 | 2017-12-07 | A kind of audio-video monitoring server-side, system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108257159A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140082126A (en) * | 2012-12-23 | 2014-07-02 | 전남대학교산학협력단 | System and method for image classification using color histogram |
CN104134222A (en) * | 2014-07-09 | 2014-11-05 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
CN104268902A (en) * | 2014-09-30 | 2015-01-07 | 东南大学 | Multi-target video tracking method for industrial site |
CN107318000A (en) * | 2017-06-22 | 2017-11-03 | 重庆邮电大学 | A kind of wireless video monitoring system based on cloud platform |
CN107403439A (en) * | 2017-06-06 | 2017-11-28 | 沈阳工业大学 | Predicting tracing method based on Cam shift |
-
2017
- 2017-12-07 CN CN201711287455.6A patent/CN108257159A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140082126A (en) * | 2012-12-23 | 2014-07-02 | 전남대학교산학협력단 | System and method for image classification using color histogram |
CN104134222A (en) * | 2014-07-09 | 2014-11-05 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
CN104268902A (en) * | 2014-09-30 | 2015-01-07 | 东南大学 | Multi-target video tracking method for industrial site |
CN107403439A (en) * | 2017-06-06 | 2017-11-28 | 沈阳工业大学 | Predicting tracing method based on Cam shift |
CN107318000A (en) * | 2017-06-22 | 2017-11-03 | 重庆邮电大学 | A kind of wireless video monitoring system based on cloud platform |
Non-Patent Citations (1)
Title |
---|
雷帮军等: "《视频目标跟踪系统分步详解》", 31 December 2015 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104410807B (en) | A kind of multi-channel video synchronized playback method and device | |
CN105359544B (en) | Special play-back in digital video frequency flow transmission | |
CN102724492B (en) | Method and system for transmitting and playing video images | |
CN106664417A (en) | Content adaptive background-foreground segmentation for video coding | |
WO2015031548A1 (en) | Audio video playback synchronization for encoded media | |
CN103428483B (en) | A kind of media data processing method and equipment | |
Abdullah et al. | Traffic monitoring using video analytics in clouds | |
CN104427291A (en) | Image processing method and device | |
CN104363403A (en) | Method and device for storing video data in video monitoring system | |
US9805267B2 (en) | Video processing system with photo generation and methods for use therewith | |
US9020033B2 (en) | System and method for enhancing compression using skip macro block on a compressed video | |
CN102196268B (en) | Method, device and system for processing multimedia data | |
CN108234940A (en) | A kind of video monitoring server-side, system and method | |
CN110379130A (en) | A kind of Medical nursing shatter-resistant adjustable voltage system based on multi-path high-definition SDI video | |
CN108257159A (en) | A kind of audio-video monitoring server-side, system and method | |
CN109151574A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
CN105898320A (en) | Panorama video decoding method and device and terminal equipment based on Android platform | |
CN113645448A (en) | Video decoding method and device suitable for command scheduling | |
US11095901B2 (en) | Object manipulation video conference compression | |
CN109151387B (en) | webRTC-based low-delay solution for face recognition of mobile camera | |
CN105100663A (en) | Recording system based on hardware encoders, audio and video processing apparatus, and recording method | |
JPWO2019135270A1 (en) | Video analysis device, video analysis system, video analysis method, and program | |
CN115831132A (en) | Audio encoding and decoding method, device, medium and electronic equipment | |
TWI552573B (en) | Coding of video and audio with initialization fragments | |
KR20170081356A (en) | System for rapid management of large scale moving pictures and method thereof |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180706 |