CN109597431A - A kind of method and device of target following - Google Patents
A kind of method and device of target following Download PDFInfo
- Publication number
- CN109597431A CN109597431A CN201811308505.9A CN201811308505A CN109597431A CN 109597431 A CN109597431 A CN 109597431A CN 201811308505 A CN201811308505 A CN 201811308505A CN 109597431 A CN109597431 A CN 109597431A
- Authority
- CN
- China
- Prior art keywords
- tracking
- target
- tracking target
- parameter
- opentld
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 87
- 230000008569 process Effects 0.000 claims abstract description 53
- 230000033001 locomotion Effects 0.000 claims description 34
- 230000003068 static effect Effects 0.000 claims description 22
- 230000000386 athletic effect Effects 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 15
- 230000001133 acceleration Effects 0.000 claims description 13
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 230000009849 deactivation Effects 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims 1
- 230000037431 insertion Effects 0.000 claims 1
- 230000006855 networking Effects 0.000 description 31
- 230000036544 posture Effects 0.000 description 29
- 238000005516 engineering process Methods 0.000 description 20
- 210000003128 head Anatomy 0.000 description 15
- 230000005540 biological transmission Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- RTZKZFJDLAIYFH-UHFFFAOYSA-N Diethyl ether Chemical compound CCOCC RTZKZFJDLAIYFH-UHFFFAOYSA-N 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000005352 clarification Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000000571 coke Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 241000700605 Viruses Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002155 anti-virotic effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention provides a kind of method of target following and devices.The described method includes: the embedded platform developer terminal obtains the video flowing acquired by the picture pick-up device, it is sent to the client, the client receives the tracking target that user selectes, and the tracking target is sent to the embedded platform developer terminal, the embedded platform developer terminal calls openTLD process to determine the tracking parameter to the tracking target, target signature information, the embedded platform developer terminal is after determining that the tracking target is lost, identify that the characteristic information of the photographic subjects in the video flowing is matched with the tracking target signature information, continue the tracking parameter for calling the openTLD process to determine to tracking target, and the picture pick-up device zoom and/or the adjustment electric platform angle are controlled according to the tracking parameter, to the tracking target It is tracked.The present invention is realized after tracking target is lost and is reappeared, the identification and tracking to tracking target.
Description
Technical field
The present invention relates to target tracking domains, more particularly to the method and device of a kind of target following.
Background technique
Traditional Target Tracking System has a ultrasonic wave and microwave tracking, infrared track etc., ultrasonic wave and microwave tracking due to
Anti-interference is poor to be abandoned, infrared track, although being commonly used, tracked target needs to carry infrared positioning dress
It sets, it is also very inconvenient.
In recent years, artificial intelligence field rapidly develops, visual pursuit technology is important as one of artificial intelligence field
Direction, development speed is very swift and violent in fact, by the combination of Visual Tracking and electric platform and intelligence system etc.,
It may be implemented to automatically track target.
Existing automatically track target system, although can with automatically track target, after target loss, can not continue with
Track target can not also re-recognize target even if target reappears in the visual field of picture pick-up device, lead to not continue to track
Target.
Summary of the invention
In view of the above problems, the present invention provides the method and device of a kind of target following, solve it is existing automatically with
Track goal systems, even if target reappears in the visual field of picture pick-up device, can not re-recognize after tracking target is lost
Target cannot continue the problem of tracking target.
In order to solve the above-mentioned technical problem, the embodiment of the invention provides a kind of method of target following, the method is answered
For tracking system, the tracking system includes: picture pick-up device, embedded platform developer terminal, electric platform and client
End, the external picture pick-up device of the embedded platform developer terminal, electric platform and client, which comprises
The embedded platform developer terminal obtains the video flowing acquired by the picture pick-up device, and the video flowing includes
Multiple photographic subjects, and by the video stream to the client；
The client receives the tracking target that user selectes in multiple photographic subjects of the video flowing, and will be described
Required tracking target is sent to the embedded platform developer terminal；
The embedded platform developer terminal calls openTLD process to determine the tracking parameter to the tracking target,
And the picture pick-up device zoom and/or the adjustment electric platform angle are controlled according to the tracking parameter, to the target
Equipment carries out tracking and by video stream to client, and determines the target signature information of the tracking target；
The embedded platform developer terminal identifies the bat in the video flowing after determining that the tracking target is lost
Take the photograph whether clarification of objective information matches with the tracking target signature information, if it does, then continuing to call the openTLD
Process determines the tracking parameter to tracking target, and controls the picture pick-up device zoom and/or adjustment according to the tracking parameter
The electric platform angle, to carry out tracking and by video stream to client to the tracking target.
Optionally, the embedded platform developer terminal identifies the video after determining that the tracking target is lost
Whether the characteristic information for the photographic subjects for being in stream matches with the target signature information, comprising:
After the embedded platform developer terminal determines that the tracking target is lost, the embedded platform developer
Terminal gives the video stream after the tracking target loss to the client；
The client receives the region that user draws a circle to approve in the video flowing after the tracking target is lost, and by the circle
Fixed region is sent to the embedded platform developer terminal；
The embedded platform developer terminal controls the picture pick-up device and acquires the circle according to the region of the delineation
The video flowing in fixed region calls the video flowing in the region of delineation described in the openTLD progress recognizing；
After the tracking target reappears in the region of the delineation, tracked described in the openTLD progress recognizing
Target go out again after video flowing in the characteristic informations of photographic subjects whether matched with the tracking target signature information.
Optionally, the embedded platform developer terminal identifies the video after determining that the tracking target is lost
Whether the characteristic information of the photographic subjects in stream matches with the target signature information, the method also includes:
If the characteristic information of the photographic subjects in the video flowing and the tracking target signature information mismatch, described
OpenTLD process described in embedded platform developer's terminal disabling terminates the tracking to the tracking target.
Optionally, the embedded platform developer terminal call the openTLD process determine to tracking target with
Track parameter, comprising:
The tracking parameter includes the first tracking parameter and the second tracking parameter；
The openTLD process carries out kinematic parameter study to tracking target, obtains the first tracking parameter of tracking target,
The kinematic parameter includes: position, speed, acceleration and motion profile feature；
The openTLD process carries out athletic posture detection to tracking target, obtains the second tracking parameter of tracking target,
The athletic posture includes various movement appearance posture features.
Optionally, the embedded platform developer terminal calls the openTLD process to determine the tracking target
Target signature information, comprising:
The openTLD process obtains described required according to each frame image of the video flowing of the required tracking target
The static appearance feature of target is tracked, and according to the static appearance feature and the athletic posture feature described embedded
Tracking target signature information library is established in platform developer terminal.
Optionally, the electric platform includes: holder bracket, cradle head controllor and motor, the holder bracket and institute
State between picture pick-up device using hard link, the embedded platform developer terminal call the openTLD process determine to
The tracking parameter of track target, and the picture pick-up device zoom and/or the adjustment electric platform are controlled according to the tracking parameter
Angle, comprising:
The embedded platform developer terminal sends the tracking parameter to the cradle head controllor；
The cradle head controllor calculates holder rack mechanical angular adjustment parameter according to the tracking parameter；
The cradle head controllor controls motor rotation, adjusts the holder bracket according to the mechanical angle adjustment parameter
Mechanical angle, the holder bracket drives the picture pick-up device rotation, realizes the tracking to tracking target.
The embodiment of the invention also provides a kind of device of target following, described device is applied to tracking system, it is described with
Track system includes: picture pick-up device, the embedded platform developer terminal, electric platform and client, described embedded flat
The external picture pick-up device of platform developer's terminal, electric platform and client, the embedded platform developer terminal include
OpenTLD process, described device include:
Sending module is obtained, obtains the video acquired by the picture pick-up device for the embedded platform developer terminal
Stream, the video flowing includes the image of multiple photographic subjects and target peripheral region, and by the video stream to described
Client, the client receive the video flowing, select tracking target in the multiple photographic subjects, and by the tracking
Target is sent to calling control module；
Call control module, for the embedded platform developer terminal call the openTLD process determine to
The tracking parameter of track target, and the picture pick-up device zoom and/or the adjustment electric platform are controlled according to the tracking parameter
Angle to carry out tracking and by video stream to client to the tracking target, and determines the mesh of the tracking target
Mark characteristic information；
Sending module is identified, for knowing after the embedded platform developer terminal determines that the tracking target is lost
Whether the characteristic information of the photographic subjects in the not described video flowing matches with the tracking target signature information, if it does, then
Continue the tracking parameter for calling the openTLD process to determine tracking target, and the camera shooting is controlled according to the tracking parameter
Equipment zoom and/or the adjustment electric platform angle, to carry out tracking and by video stream to visitor to the tracking target
Family end.
Optionally, the identification sending module includes:
Determine sending submodule, for after the embedded platform developer terminal determines that the tracking target is lost,
The embedded platform developer terminal gives the video stream after the tracking target loss to the client, the client
End receives the region that user draws a circle to approve in the video flowing after the tracking target is lost, and the region of the delineation is sent to institute
State embedded platform developer's terminal；
Submodule is called in control, for the embedded platform developer terminal according to the region of the delineation, controls institute
The video flowing that picture pick-up device acquires the region of the delineation is stated, the region of delineation described in the openTLD progress recognizing is called
Video flowing；
Identify submodule, for after the tracking target reappears in the region of the delineation, the openTLD into
Journey identifies whether the characteristic information for tracking the photographic subjects in the video flowing after target goes out again is special with the tracking target
Levy information matches.
Optionally, the calling control module includes:
Study submodule is called, kinematic parameter study is carried out to tracking target for the openTLD process, is tracked
First tracking parameter of target, the kinematic parameter include: position, speed, acceleration and motion profile feature；
Detection sub-module is called, athletic posture detection is carried out to tracking target for the openTLD process, is tracked
Second tracking parameter of target, the athletic posture include various movement appearance posture features；
Call establishment submodule, for the openTLD process according to each of the required video flowing for tracking target
Frame image obtains the static appearance feature of the required tracking target, and according to the static appearance feature and the movement
Posture establishes tracking target signature information library in the embedded platform developer terminal.
Optionally, described device further include:
Deactivation module is identified, for identifying the photographic subjects in the video flowing after determining that the tracking target is lost
Characteristic information whether matched with the tracking target signature information, if mismatch, deactivate the openTLD process, terminate
Tracking to the tracking target.
Compared with prior art, the method and device of a kind of target following provided by the invention, by tracking target
Characteristic information establish database, it is lasting to obtain the video flowing after tracking target is lost after target loss, when target goes out again
In the visual field of present picture pick-up device, target is re-recognized, according to tracking parameter, controls the rotation of electric platform, to adjust camera shooting
The tracking again to target is lost simply and effectively is realized in the position of equipment.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of networking schematic diagram of view networking of the invention；
Fig. 2 is a kind of hardware structural diagram of node server of the invention；
Fig. 3 is a kind of hardware structural diagram of access switch of the invention；
Fig. 4 is the hardware structural diagram that a kind of Ethernet association of the invention turns gateway；
Fig. 5 is a kind of flow chart of the method for target following of the embodiment of the present invention；
Fig. 6 is a kind of specific flow chart of a method wherein step for target following of the embodiment of the present invention；
Fig. 7 is a kind of another specific flow chart of a method wherein step for target following of the embodiment of the present invention；
Fig. 8 is the method flow diagram of the adjustment electric platform angle of the embodiment of the present invention；
Fig. 9 is a kind of schematic diagram of the system of target following of the embodiment of the present invention；
Figure 10 is a kind of block diagram of the device of target following of the embodiment of the present invention；
Figure 11 is a kind of specific block diagram of the device of target following of the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It is the important milestone of network Development depending on networking, is a real-time network, can be realized HD video real-time Transmission,
Push numerous Internet applications to HD video, high definition is face-to-face.
Real-time high-definition video switching technology is used depending on networking, it can be such as high in a network platform by required service
Clear video conference, Intellectualized monitoring analysis, emergency command, digital broadcast television, delay TV, the Web-based instruction, shows video monitoring
Field live streaming, VOD program request, TV Mail, individual character records (PVR), Intranet (manages) channel by oneself, intelligent video Broadcast Control, information publication
All be incorporated into a system platform etc. services such as tens of kinds of videos, voice, picture, text, communication, data, by TV or
Computer realizes that high-definition quality video plays.
Embodiment in order to enable those skilled in the art to better understand the present invention is introduced to depending on networking below:
Depending on networking, applied portion of techniques is as described below:
Network technology (Network Technology)
Traditional ethernet (Ethernet) is improved depending on the network technology innovation networked, with potential huge on network
Video flow.(Circuit is exchanged different from simple network packet packet switch (Packet Switching) or lattice network
Switching), Streaming demand is met using Packet Switching depending on networking technology.Has grouping depending on networking technology
Flexible, the simple and low price of exchange, is provided simultaneously with the quality and safety assurance of circuit switching, it is virtually electric to realize the whole network switch type
The seamless connection of road and data format.
Switching technology (Switching Technology)
Two advantages of asynchronous and packet switch that Ethernet is used depending on networking eliminate Ethernet under the premise of complete compatible and lack
It falls into, has the end-to-end seamless connection of the whole network, direct user terminal, directly carrying IP data packet.User data is in network-wide basis
It is not required to any format conversion.It is the more advanced form of Ethernet depending on networking, is a real-time exchange platform, can be realized at present mutually
The whole network large-scale high-definition realtime video transmission that networking cannot achieve pushes numerous network video applications to high Qinghua, unitizes.
Server technology (Server Technology)
It is different from traditional server, its Streaming Media depending on the server technology in networking and unified video platform
Transmission be built upon it is connection-oriented on the basis of, data-handling capacity is unrelated with flow, communication time, single network layer energy
Enough transmitted comprising signaling and data.For voice and video business, handled depending on networking and unified video platform Streaming Media
Complexity many simpler than data processing, efficiency substantially increase hundred times or more than traditional server.
Reservoir technology (Storage Technology)
The ultrahigh speed reservoir technology of unified video platform in order to adapt to the media content of vast capacity and super-flow and
Using state-of-the-art real time operating system, the programme information in server instruction is mapped to specific hard drive space, media
Content is no longer pass through server, and moment is directly delivered to user terminal, and user waits typical time less than 0.2 second.It optimizes
Sector distribution greatly reduces the mechanical movement of hard disc magnetic head tracking, and resource consumption only accounts for the 20% of the internet ad eundem IP, but
The concurrent flow greater than 3 times of traditional disk array is generated, overall efficiency promotes 10 times or more.
Network security technology (Network Security Technology)
Depending on the structural design networked by servicing independent licence system, equipment and the modes such as user data is completely isolated every time
The network security problem that puzzlement internet has thoroughly been eradicated from structure, does not need antivirus applet, firewall generally, has prevented black
The attack of visitor and virus, structural carefree secure network is provided for user.
It services innovative technology (Service Innovation Technology)
Business and transmission are fused together by unified video platform, whether single user, private user or a net
The sum total of network is all only primary automatic connection.User terminal, set-top box or PC are attached directly to unified video platform, obtain rich
The multimedia video service of rich colorful various forms.Unified video platform is traditional to substitute with table schema using " menu type "
Complicated applications programming, considerably less code, which can be used, can be realized complicated application, realize the new business innovation of " endless ".
Networking depending on networking is as described below:
It is a kind of central controlled network structure depending on networking, which can be Tree Network, Star network, ring network etc. class
Type, but centralized control node is needed to control whole network in network on this basis.
As shown in Figure 1, being divided into access net and Metropolitan Area Network (MAN) two parts depending on networking.
The equipment of access mesh portions can be mainly divided into 3 classes: node server, access switch, terminal (including various machines
Top box, encoding board, memory etc.).Node server is connected with access switch, and access switch can be with multiple terminal phases
Even, and it can connect Ethernet.
Wherein, node server is the node that centralized control functions are played in access net, can control access switch and terminal.
Node server can directly be connected with access switch, can also directly be connected with terminal.
Similar, the equipment of metropolitan area mesh portions can also be divided into 3 classes: metropolitan area server, node switch, node serve
Device.Metropolitan area server is connected with node switch, and node switch can be connected with multiple node servers.
Wherein, node server is the node server for accessing mesh portions, i.e. node server had both belonged to access wet end
Point, and belong to metropolitan area mesh portions.
Metropolitan area server is the node that centralized control functions are played in Metropolitan Area Network (MAN), can control node switch and node serve
Device.Metropolitan area server can be directly connected to node switch, can also be directly connected to node server.
It can be seen that be entirely a kind of central controlled network structure of layering depending on networking network, and node server and metropolitan area
The network controlled under server can be the various structures such as tree-shaped, star-like, cyclic annular.
Visually claim, access mesh portions can form unified video platform (part in virtual coil), and multiple unified videos are flat
Platform can form view networking；Each unified video platform can be interconnected by metropolitan area and wide area depending on networking.
Classify depending on networked devices
1.1 embodiment of the present invention can be mainly divided into 3 classes: server depending on the equipment in networking, interchanger (including ether
Net gateway), terminal (including various set-top boxes, encoding board, memory etc.).Depending on networking can be divided on the whole Metropolitan Area Network (MAN) (or
National net, World Wide Web etc.) and access net.
1.2 equipment for wherein accessing mesh portions can be mainly divided into 3 classes: node server, access switch (including ether
Net gateway), terminal (including various set-top boxes, encoding board, memory etc.).
The specific hardware structure of each access network equipment are as follows:
Node server:
As shown in Fig. 2, mainly including Network Interface Module 201, switching engine module 202, CPU module 203, disk array
Module 204；
Wherein, Network Interface Module 201, the Bao Jun that CPU module 203, disk array module 204 are come in enter switching engine
Module 202；Switching engine module 202 look into the operation of address table 205 to the packet come in, to obtain the navigation information of packet；
And the packet is stored according to the navigation information of packet the queue of corresponding pack buffer 206；If the queue of pack buffer 206 is close
It is full, then it abandons；All pack buffer queues of 202 poll of switching engine mould, are forwarded: 1) port if meeting the following conditions
It is less than to send caching；2) the queue package counting facility is greater than zero.Disk array module 204 mainly realizes the control to hard disk, including
The operation such as initialization, read-write to hard disk；CPU module 203 is mainly responsible between access switch, terminal (not shown)
Protocol processes, to address table 205 (including descending protocol packet address table, uplink protocol package address table, data packet addressed table)
Configuration, and, the configuration to disk array module 204.
Access switch:
As shown in figure 3, mainly including Network Interface Module (downstream network interface module 301, uplink network interface module
302), switching engine module 303 and CPU module 304；
Wherein, the packet (upstream data) that downstream network interface module 301 is come in enters packet detection module 305；Packet detection mould
Whether mesh way address (DA), source address (SA), type of data packet and the packet length of the detection packet of block 305 meet the requirements, if met,
It then distributes corresponding flow identifier (stream-id), and enters switching engine module 303, otherwise abandon；Uplink network interface mould
The packet (downlink data) that block 302 is come in enters switching engine module 303；The data packet that CPU module 204 is come in enters switching engine
Module 303；Switching engine module 303 look into the operation of address table 306 to the packet come in, to obtain the navigation information of packet；
If the packet into switching engine module 303 is that downstream network interface is gone toward uplink network interface, in conjunction with flow identifier
(stream-id) packet is stored in the queue of corresponding pack buffer 307；If the queue of the pack buffer 307 is close full,
It abandons；If the packet into switching engine module 303 is not that downstream network interface is gone toward uplink network interface, according to packet
Navigation information is stored in the data packet queue of corresponding pack buffer 307；If the queue of the pack buffer 307 is close full,
Then abandon.
All pack buffer queues of 303 poll of switching engine module, are divided to two kinds of situations in embodiments of the present invention:
If the queue is that downstream network interface is gone toward uplink network interface, meets the following conditions and be forwarded: 1)
It is less than that the port sends caching；2) the queue package counting facility is greater than zero；3) token that rate control module generates is obtained；
If the queue is not that downstream network interface is gone toward uplink network interface, meets the following conditions and is forwarded:
1) it is less than to send caching for the port；2) the queue package counting facility is greater than zero.
Rate control module 208 is configured by CPU module 204, to all downlink networks in programmable interval
Interface generates token toward the pack buffer queue that uplink network interface is gone, to control the code rate of forwarded upstream.
CPU module 304 is mainly responsible for the protocol processes between node server, the configuration to address table 306, and,
Configuration to rate control module 308.
Ethernet association turns gateway:
As shown in figure 4, mainly including Network Interface Module (downstream network interface module 401, uplink network interface module
402), switching engine module 403, CPU module 404, packet detection module 405, rate control module 408, address table 406, Bao Huan
Storage 407 and MAC adding module 409, MAC removing module 410.
Wherein, the data packet that downstream network interface module 401 is come in enters packet detection module 405；Packet detection module 405 is examined
Ethernet mac DA, ethernet mac SA, Ethernet length or frame type, the view networking mesh way address of measured data packet
DA, whether meet the requirements depending on networking source address SA, depending on networking data Packet type and packet length, corresponding stream is distributed if meeting
Identifier (stream-id)；Then, MAC DA, MAC SA, length or frame type are subtracted by MAC removing module 410
(2byte), and enter corresponding receive and cache, otherwise abandon；
Downstream network interface module 401 detects the transmission caching of the port, according to the view of packet networking mesh if there is Bao Ze
Address D A knows the ethernet mac DA of corresponding terminal, adds the ethernet mac DA of terminal, Ethernet assists the MAC for turning gateway
SA, Ethernet length or frame type, and send.
The function that Ethernet association turns other modules in gateway is similar with access switch.
Terminal:
It mainly include Network Interface Module, Service Processing Module and CPU module；For example, set-top box mainly connects including network
Mouth mold block, video/audio encoding and decoding engine modules, CPU module；Encoding board mainly includes Network Interface Module, video encoding engine
Module, CPU module；Memory mainly includes Network Interface Module, CPU module and disk array module.
The equipment of 1.3 metropolitan area mesh portions can be mainly divided into 2 classes: node server, node switch, metropolitan area server.
Wherein, node switch mainly includes Network Interface Module, switching engine module and CPU module；Metropolitan area server mainly includes
Network Interface Module, switching engine module and CPU module are constituted.
2, networking data package definition is regarded
2.1 access network data package definitions
Access net data packet mainly include following sections: destination address (DA), source address (SA), reserve bytes,
payload(PDU)、CRC。
As shown in the table, the data packet for accessing net mainly includes following sections:
Wherein:
Destination address (DA) is made of 8 bytes (byte), and first character section indicates type (such as the various associations of data packet
Discuss packet, multicast packet, unicast packet etc.), be up to 256 kinds of possibility, the second byte to the 6th byte is metropolitan area net address,
Seven, the 8th bytes are access net address；
Source address (SA) is also to be made of 8 bytes (byte), is defined identical as destination address (DA)；
Reserve bytes are made of 2 bytes；
The part payload has different length according to the type of different datagrams, is if it is various protocol packages
64 bytes are 32+1024=1056 bytes if it is single group unicast packets words, are not restricted to above 2 kinds certainly；
CRC is made of 4 bytes, and calculation method follows the Ethernet CRC algorithm of standard.
Based on the above-mentioned characteristic of view networking, one of the core concepts of the embodiments of the present invention is proposed, it then follows regard the association of networking
View can regard embedded platform developer terminal, picture pick-up device, electric platform and client as the terminal in view networking, visitor
Family end sends signaling, passes through view networked server between terminal and carries out the transmission of data, and regards characteristic of the networking because of its own,
The transmission delay of audio/video flow can be made to have great shortening compared with internet, while also improving the quality of audio-video, more
Be conducive to the tracking to moving target, reaffirm identification after equally losing to tracking target, then carries out tracking and also provide more
High audio-video quality and faster speed.
Fig. 5 shows a kind of flow chart of the method for target following of the embodiment of the present invention.This method is applied to tracking system
System, the system include: picture pick-up device, embedded platform developer terminal, electric platform and client, embedded platform exploitation
The external picture pick-up device of person's terminal, electric platform and client, the specific method of target following include the following steps:
Step 101: embedded platform developer's terminal obtains the video flowing acquired by picture pick-up device, which includes more
A photographic subjects, and by the video stream to client.
Referring to Fig. 9, in the embodiment of the present invention, embedded platform developer's terminal s30 be it is application-centered, with computer
Based on technology, and software and hardware can be cut, and be had strictly suitable for application system to function, reliability, cost, volume, power consumption
It is required that dedicated computer system, it generally comprise embedded microprocessor, peripheral hardware devices, embedded OS and
Four parts such as application program are connected to image for realizing functions, the terminals such as control, monitoring or management to other equipment
Equipment s20, electric platform s10 and pc client s50, pc client s50 be checked for user, selecting video stream picture and
Control instruction is sent, when needing to track some moving target, it is necessary first to which picture pick-up device s20 claps tracking target
It takes the photograph, obtains the image video flowing of tracking target, include the image of tracking target and tracking target ambient enviroment in the video flowing,
Since the range of picture pick-up device s20 shooting is bigger, it is possible to include many moving targets in the image of shooting, it is embedded flat
Platform developer's terminal s30 can actively obtain the view of multiple moving targets including tracking target of picture pick-up device s20 shooting
Frequency flows, and gives video stream to pc client s50, it is to be understood that all equipment that above-mentioned function may be implemented all are fallen
Enter in protection scope of the present invention, the concrete mode and user that obtain tracking target video stream are looked into the embodiment of the present invention
See, selecting video stream picture and send control instruction concrete mode be not specifically limited.
Step 102: client receives the tracking target that user selectes in multiple photographic subjects of video flowing, and will be required
Tracking target is sent to embedded platform developer's terminal.
Referring to Fig. 9, in the embodiment of the present invention, user is checked multiple including tracking target by pc client s50
The video flowing of moving target, the target tracked needed for choosing in multiple moving targets, the required quantity for tracking target can be
One or more, then the required tracking target of selection is sent to embedded platform developer terminal s30, the embodiment of the present invention
The concrete mode for choosing tracking target and the quantity for tracking target are not specifically limited.
Step 103: embedded platform developer's terminal calls openTLD process to determine the tracking parameter to tracking target,
And according to tracking parameter control picture pick-up device zoom and/or adjustment electric platform angle, with to tracking target tracked and incite somebody to action
Video stream is to client, and determines the target signature information of tracking target.
Referring to Fig. 9, embedded platform developer's terminal s30 is provided with openTLD program, openTLD be a kind of vision with
Track algorithm can constantly learn the target of locking, to obtain the newest external appearance characteristic of target, while in image sequence
Moving target detected, extracted, identified and tracked, obtain the kinematic parameter of moving target, as position, speed, acceleration,
Motion profile etc., to carry out the processing and analysis of next step, embedded platform developer's terminal s30 calls openTLD process,
It is available tracking target tracking parameter and target signature information, embedded platform developer's terminal s30 can according to
The tracking parameter of track target controls picture pick-up device s20 zoom, to realize the best influence of the tracking target in obtained video flowing
Effect, while tracking parameter is sent to electric platform s10, by electric platform s10 control picture pick-up device s20 to tracking target into
Line trace.
Optionally, referring to Fig. 6, step 103 can also specifically include the following steps:
Step 103a:openTLD process carries out kinematic parameter study to tracking target, obtains the first tracking of tracking target
Parameter, kinematic parameter include: position, speed, acceleration and motion profile feature.
In the embodiment of the present invention, while being tracked to tracking target, openTLD according to tracking the walking of target, run,
The movement such as jump and the relative positional relationship with ambient enviroment, obtain the kinematic parameter of tracking target, and kinematic parameter includes tracking
The features such as position, speed, acceleration, the motion profile of target, kinematic parameter include in the tracking parameter of tracking target.
Step 103b:openTLD process carries out athletic posture detection to tracking target, obtains the second tracking of tracking target
Parameter, athletic posture include various movement appearance posture features.
In the embodiment of the present invention, while tracking to tracking target, openTLD detecting and tracking target is during exercise
The movement appearance posture such as walk, run, jumping, squatting, rolling about, obtain the movement appearance posture feature of tracking target, appearance posture includes
In the tracking parameter of tracking target.
Step 103c:openTLD process obtains required tracking according to each frame image of the video flowing of required tracking target
The static appearance feature of target, and according to static appearance feature and athletic posture feature in embedded platform developer's terminal
Establish tracking target signature information library.
In the embodiment of the present invention, the static appearance feature of tracking target, static appearance needed for openTLD also needs to obtain are special
Sign can clearly be different from other similar to required tracking target including hair, eyes, nose, the figure profile etc. of tracking target
Clarification of objective type, openTLD according to it is required tracking target video flowing each frame image, carry out visual analysis, obtain
To the static appearance feature of required tracking target, and Integrated Static external appearance characteristic and athletic posture feature, in embedded platform
Tracking target signature information library is established in developer's terminal s30.
Step 104: embedded platform developer terminal identifies the shooting mesh in video flowing after determining that tracking target is lost
Target characteristic information whether with tracking target signature information match, if it does, then continue call openTLD process determination to
The tracking parameter of track target, and picture pick-up device zoom and/or adjustment electric platform angle are controlled according to the tracking parameter, with right
Tracking target carries out tracking and by video stream to client.
Referring to Fig. 9, in the embodiment of the present invention, when required tracking target is blocked by obstructions or other reasons cause to track
When target is not in the coverage of picture pick-up device, embedded platform developer's terminal s30 determines that tracking target is lost, and takes the photograph at this time
Position last before target is lost is tracked as equipment s20 can be rested on, continues the image video flowing for acquiring the position, openTLD
Video flowing after still losing to tracking target identifies, determines whether and goes out with the moving target of target signature information storehouse matching
Now in video streaming, when tracking target reappears in the coverage of picture pick-up device s20, openTLD is recognized in video
Have in stream and occurs with the moving target of target signature information storehouse matching.Certainly, embedded platform developer terminal s30 can also root
Motion profile before losing according to tracking target is analyzed, and determines that tracking target may continue to the region occurred, then control is taken the photograph
As equipment s20 scans the region, to monitor whether its tracking target continues to occur.
It should be noted that openTLD recognizes the moving target having in video streaming with target signature information storehouse matching
Occurring can be with are as follows: first determine whether the moving target occurred in video streaming static appearance feature whether with the static state in feature database
External appearance characteristic is consistent, such as shape, the color of moving target hair, and head accounts for the ratio of entire body, the size of eyes, appearance
Shape, whether posture profile suitable, and such as former tracking target has tail, and the moving target of appearance does not have tail, original tracking target
Four limbs are sound, and the feature that the various static appearance features such as moving target unsoundness of feet of appearance are stored with feature database matches,
The movement appearance posture of moving target is matched with the movement appearance posture in feature database again later, the movement of moving target
Appearance posture refers to moving target in the posture for carrying out dynamic movement process, such as the appearance of moving target four limbs when walking
State, the amplitude of fluctuation of four limbs, the various movement appearance postures such as frequency match with what feature database stored when race, both above-mentioned
It all matches, judges the moving target occurred in video flowing for the tracking target lost, openTLD is further according to tracking mesh later
The relative positional relationship of mark and ambient enviroment, the location information for obtaining tracking target are walked, are run according to a large amount of video flowing image
Deng movement, speed, acceleration and motion profile of tracking target etc. are calculated, above-mentioned tracking parameter is fed back to embedded flat
Platform developer terminal s30, embedded platform developer's terminal s30 control picture pick-up device s20 zoom and/or tune according to tracking parameter
Whole electric platform s10 angle is realized and is tracked again to tracking target, when tracking to tracking target, with tracking target
Tracking parameter is constantly sent to electric platform s10, electric platform s10 by the variation of position, embedded platform developer's terminal s30
Holder angle is adjusted according to tracking parameter, so that picture pick-up device s20 follows the movement of tracking target and rotates, guarantees tracking target
Always in the suitable coverage of picture pick-up device s20, while being tracked to tracking target, embedded platform developer
Terminal s10 gives video stream to pc client s50, so that user checks, controls, when user is seeing the tracking mesh in video
When marking not clear enough, user can control picture pick-up device s20 zoom, so that the image of tracking target is apparent from.
Optionally, referring to Fig. 7, step 104 can also specifically include the following steps:
Step 104a: after embedded platform developer's terminal determines that tracking target is lost, embedded platform developer is whole
End will track the video stream after target is lost to client.
Step 104b: client receives the region that user draws a circle to approve in the video flowing after tracking target is lost, and will delineation
Region be sent to embedded platform developer's terminal.
Step 104c: region of the embedded platform developer terminal according to delineation, the area of control picture pick-up device acquisition delineation
The video flowing in domain calls the video flowing in the region of openTLD progress recognizing delineation.
Step 104d: after tracking target reappears in the region of delineation, openTLD progress recognizing tracks target again
Whether the characteristic information of the photographic subjects in video flowing after out matches with tracking target signature information.
Referring to Fig. 9, in the embodiment of the present invention, when required tracking target is blocked by obstructions or other reasons cause to track
When target is not in the coverage of picture pick-up device s20, embedded platform developer's terminal s30 determines that tracking target is lost, this
When picture pick-up device s20 can rest on position last before tracking target is lost, continue the image video flowing for acquiring the position, be embedded in
Video stream after formula platform developer terminal s30 loses the tracking target of acquisition gives pc client s50, user call with
Video pictures before track target loss and the video pictures after loss choose some users and think to track mesh according to above-mentioned picture
The region that rotating savings occurs, the range in the region include tracking the region that activity is crossed before target is lost, and may live after losing
Above-mentioned zone is sent to embedded platform developer terminal s30, the region that terminal s30 is selected according to user, control by dynamic region
Picture pick-up device s20 processed carries out image collection in above-mentioned zone, and the video flowing after openTLD still loses tracking target carries out
Identification determines whether and occurs in video streaming with the moving target of target signature information storehouse matching, when tracking target reappears
In the coverage of picture pick-up device s20, openTLD recognizes the activity having in video streaming with target signature information storehouse matching
Target occurs, and openTLD determines that s30 is according to tracking parameter for embedded platform developer's terminal to the tracking parameter of tracking target
Picture pick-up device s20 zoom and/or adjustment electric platform s10 angle are controlled, realizes and tracking target is tracked again, and by video flowing
It is sent to pc client s50, so that user checks, controls, it is to be understood that after tracking target is lost, user can also be with
It is artificial to find tracking target, it is artificial to adjust picture pick-up device s20 alignment tracking target after finding tracking target, carry out image view
Frequency stream acquisition, the concrete mode that the embodiment of the present invention reappears judgement tracking target are not specifically limited.
Optionally, Fig. 8 shows the method flow diagram that electric platform angle is adjusted in the embodiment of the present invention.Electric platform packet
Include: holder bracket, cradle head controllor and motor use hard link between holder bracket and picture pick-up device, embedded platform is opened
Originator terminal is as follows according to the method and step that tracking parameter adjusts electric platform angle:
Step 201: embedded platform developer terminal sends the tracking parameter of tracking target to cradle head controllor.
Step 202: cradle head controllor calculates holder rack mechanical angular adjustment parameter according to tracking parameter.
Step 203: cradle head controllor controls motor rotation, adjusts the machine of holder bracket according to mechanical angle adjustment parameter
Tool angle, holder bracket drive picture pick-up device rotation, realize the tracking to tracking target.
Referring to Fig. 9, during the present invention is implemented, electric platform s10 include: holder bracket s101, cradle head controllor s102 and
Motor s104, electric platform s10 need external power supply s103, and hard link is used between holder bracket s101 and picture pick-up device s20, protect
It demonstrate,proves picture pick-up device s20 stabilization when being shot not shake, cradle head controllor s102 and embedded platform developer terminal s30 can
It to be carried out data transmission by wireless mode, can also be carried out data transmission using connection, both there is connecing for communication
Mouthful, cradle head controllor s102 receives tracking parameter, according to numbers such as position, the speed, accelerations for tracking target in tracking parameter
Accordingly and the features such as motion profile, holder bracket s101 mechanical angle adjustment parameter is calculated, further according to mechanical angle adjustment parameter,
Motor s104 rotation is controlled, motor s104 drives holder bracket s101 rotation by the drive apparatus such as gear or belt, can be with
Understand be holder bracket s101 rotation can be left and right directions rotation, be also possible to up and down direction rotation, due to holder branch
Hard link is used between frame s101 and picture pick-up device s20, so holder bracket s101 can drive picture pick-up device s20 to rotate, it is real
Now to the tracking of tracking target, the embodiment of the present invention controls picture pick-up device to electric platform, realizes the tracking to tracking target
Concrete mode is not specifically limited.
For example, referring to Fig. 9, a set of can include: embedded in the system to the system that moving target is tracked
Platform developer terminal s30, picture pick-up device s20, electric platform s10, network server s40 and pc client s50, it is embedded
Platform developer terminal s30 is equipped with openTLD program for realizing control, monitoring or the management to other equipment, inside,
OpenTLD is a kind of Vision Tracking, can constantly be learnt to the target of locking, special to obtain the newest appearance of target
Sign, while the moving target in image sequence is detected, extracted, identified and tracked, the kinematic parameter of moving target is obtained,
Such as position, speed, acceleration, motion profile, so that the processing and analysis of next step are carried out, embedded platform developer's terminal
S30 connects picture pick-up device s20, electric platform s10 and pc client s50 by connection, if above equipment all has nothing
Line communication function can then be carried out data transmission using wireless mode, by wireless communication in base station or network server s40
Wireless communication module, communicated with pc client s50.Picture pick-up device s20 is the equipment with shooting function, general to use
Imaging effect is good, and the lesser picture pick-up device s20 of external form volume facilitates control of the electric platform s10 to picture pick-up device s20, electronic
Holder s10 under the drive of motor s104, can do horizontal and vertical rotation, make picture pick-up device for installing picture pick-up device s20
S20 tracks target required for capable of being aligned and absorb in a wide range of, pc client s50 can allow user to check, selecting video
It flows picture and sends control instruction.
When needing to track some moving target, it is necessary first to which picture pick-up device s20 shoots tracking target, obtains
It include tracking target and the image for tracking target ambient enviroment to the image video flowing of tracking target, in the video flowing, due to
The range of picture pick-up device s20 shooting is bigger, is possible to include many moving targets in the image of shooting, embedded platform is opened
Originator terminal s30 can actively obtain the video flowing of multiple moving targets including tracking target of picture pick-up device s20 shooting,
And give video stream to pc client s50.User checks multiple activities including tracking target by pc client s50
The video flowing of target, if it find that the tracking target image in video flowing is not clear enough, it need to be to embedded platform developer's terminal
S30 sends the instruction of control picture pick-up device s20 focusing, and embedded platform developer's terminal s30 control picture pick-up device s20 is adjusted
Coke, to obtain the image video flowing for clearly tracking target.
The video of clearly multiple moving targets including tracking target is viewed by pc client s50 in user
After stream, user chooses the target of tracking in multiple moving targets, and the quantity for tracking target can be one or more, then will
The tracking target of selection is sent to embedded platform developer terminal s30, and embedded platform developer's terminal s30 receives selection
Tracking target, call openTLD process, openTLD according to tracking target walk, run, jump etc. to move and and ambient enviroment
Relative positional relationship, obtain the kinematic parameter of tracking target, kinematic parameter include track the position of target, speed, acceleration,
The features such as motion profile, detecting and tracking target during exercise the movement appearance posture such as walk, run, jumping, squatting, rolling about, tracked
The movement appearance posture feature of target, according to above- mentioned information, embedded platform developer's terminal s30 controls picture pick-up device s20 and becomes
Above- mentioned information so that the imaging effect of the tracking target in video flowing reaches most preferably, while being sent to electric platform s10 by coke,
Electric platform s10 includes: holder bracket s101, cradle head controllor s102 and motor s104, and electric platform s10 needs external power supply
S103 uses hard link between holder bracket s101 and picture pick-up device s20, guarantee that picture pick-up device s20 stablizes when being shot
It not shaking, cradle head controllor s102 can be carried out data transmission with embedded platform developer's terminal s30 by wireless mode,
It can be carried out data transmission using connection, both there is the interface for communication, the cradle head controllor s102 of electric platform s10
Above- mentioned information are received, according to the features such as data and motion profile such as position, speed, acceleration for tracking target in information,
Holder bracket s101 mechanical angle adjustment parameter is calculated, further according to mechanical angle adjustment parameter, controls motor s104 rotation, motor
S104 drives holder bracket s101 rotation by drive apparatus such as gear or belts, controls picture pick-up device by electric platform s10
S20 tracks tracking target.While tracking to tracking target, openTLD is according to the video flowing for tracking target
Each frame image, carry out visual analysis, obtain tracking target static appearance feature, static appearance feature include tracking target
Hair, eyes, nose, figure profile etc. can clearly be different from other clarification of objective classes similar with required tracking target
Type establishes tracking target in Integrated Static external appearance characteristic and athletic posture feature in embedded platform developer's terminal s30
Characteristic information library.
It is blocked by obstructions in tracking target or other reasons leads to track target not in the shooting model of picture pick-up device s20
Enclose it is interior after, embedded platform developer's terminal s30 determine tracking target lose, picture pick-up device s20 can rest on tracking mesh at this time
Last position before mark is lost, continues the image video flowing for acquiring the position, and embedded platform developer's terminal s10 is by acquisition
Video stream after tracking target is lost gives pc client s50, and user, which calls, to be tracked the video pictures before target is lost and lose
Video pictures after mistake choose some users and think to track the region that target will appear, the range in the region according to above-mentioned picture
Including tracking target lose before activity cross region, and lose after may movable region, above-mentioned zone is sent to embedding
Enter formula platform developer terminal s10, the region that terminal s10 is selected according to user, control picture pick-up device s20 in above-mentioned zone into
Row image collection, the video flowing after openTLD still loses tracking target identifies, determines whether and target signature information
In video streaming, reappearing in the coverage of picture pick-up device s20 when tracking target occurs in the moving target of storehouse matching,
OpenTLD recognizes to have in video streaming to be occurred with the moving target of target signature information storehouse matching, and openTLD is determined to tracking
The tracking parameter of target, embedded platform developer's terminal s30 adjust electric platform s10 angle, realization pair according to tracking parameter
Tracking target tracks again, and gives video stream to pc client s50, so that user checks, controls, it is to be understood that
After tracking target is lost, user can also manually find tracking target, after finding tracking target, artificially adjust picture pick-up device
S20 alignment tracking target, carry out the acquisition of image video flowing, embedded platform developer's terminal s10 also remain with unmanned vehicle or
The control unit interface of the unmanned machines such as unmanned plane can satisfy the tracking of the moving target in bigger farther range.
Optionally, a kind of block diagram of target tracker shown in 0, the device are applied to tracking system, tracking referring to Fig.1
System includes: picture pick-up device, embedded platform developer terminal, electric platform and client, and embedded platform developer is whole
External picture pick-up device, electric platform and client are held, described device includes:
Sending module 310 is obtained, obtains the video flowing acquired by picture pick-up device for embedded platform developer's terminal, depending on
Frequency stream includes the image of multiple photographic subjects and target peripheral region, and by video stream to client, client is received
Video flowing selectes tracking target in multiple photographic subjects, and tracking target is sent to calling control module；
Control module 320 is called, calls openTLD process to determine to tracking target for embedded platform developer terminal
Tracking parameter, and according to tracking parameter control picture pick-up device zoom and/or adjustment electric platform angle, with to tracking target into
Video stream is simultaneously tracked the target signature information of target to client, and determination by line trace；
Sending module 330 is identified, for identifying video after embedded platform developer's terminal determines that tracking target is lost
Whether the characteristic information of the photographic subjects in stream matches with tracking target signature information, if it does, then continuing to call openTLD
Process determines the tracking parameter of tracking target, and controls picture pick-up device zoom and/or adjustment electric platform angle according to tracking parameter
Degree, to carry out tracking and by video stream to client to tracking target.
Optionally, referring to Fig.1 1, on the basis of Figure 10, above-mentioned apparatus can also include:
Call control module 320 include:
Study submodule 3201 is called, kinematic parameter study is carried out to tracking target for openTLD process, is tracked
First tracking parameter of target, kinematic parameter include: position, speed, acceleration and motion profile feature；
Detection sub-module 3202 is called, athletic posture detection is carried out to tracking target for openTLD process, is tracked
Second tracking parameter of target, athletic posture include various movement appearance posture features；
Call establishment submodule 3203, for openTLD process according to each frame figure of the video flowing of required tracking target
Picture, the static appearance feature of tracking target needed for obtaining, and according to static appearance feature and athletic posture in embedded platform
Tracking target signature information library is established in developer's terminal.
Identify that sending module 330 includes:
Sending submodule 3301 is determined, for being embedded in after embedded platform developer's terminal determines that tracking target is lost
Formula platform developer terminal will track the video stream after target is lost to client, and client receives user in tracking target
The region drawn a circle to approve in video flowing after loss, and the region of delineation is sent to embedded platform developer's terminal.
Submodule 3302 is called in control, and for embedded platform developer terminal according to the region of delineation, control camera shooting is set
The video flowing in the region of standby acquisition delineation, calls the video flowing in the region of openTLD progress recognizing delineation.
Identify submodule 3303, for when tracking target reappear in the region of delineation after, openTLD progress recognizing with
Track target again go out after video flowing in photographic subjects characteristic information whether with tracking target signature information match.
Deactivation module 340 is identified, for identifying the feature of the photographic subjects in video flowing after determining that tracking target is lost
Information whether with tracking target signature information match, if mismatch, deactivate openTLD process, terminate to track target with
Track.
Through the foregoing embodiment, after being lost the invention enables tracking target, when reappearing, to the automatic identification of target with
And automatically track, solve the prior art tracking target lose again occur after, can not automatic identification and tracking the problem of.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Above to a kind of method and device of target following provided by the present invention, it is described in detail, herein
Apply that a specific example illustrates the principle and implementation of the invention, the explanation of above example is only intended to help
Understand method and its core concept of the invention；At the same time, for those skilled in the art, according to the thought of the present invention,
There will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as to this
The limitation of invention.
Claims (10)
1. a kind of method of target following, which is characterized in that the method is applied to tracking system, and the tracking system includes:
Picture pick-up device, embedded platform developer terminal, electric platform and client, the embedded platform developer terminal are external
Picture pick-up device, electric platform and client, which comprises
The embedded platform developer terminal obtains the video flowing acquired by the picture pick-up device, and the video flowing includes multiple
Photographic subjects, and by the video stream to the client；
The client receives the tracking target that user selectes in multiple photographic subjects of the video flowing, and will be described required
Tracking target is sent to the embedded platform developer terminal；
The embedded platform developer terminal calls openTLD process to determine the tracking parameter to the tracking target, and root
The picture pick-up device zoom and/or the adjustment electric platform angle are controlled according to the tracking parameter, to the tracking target
It carries out tracking and by video stream to client, and determines the target signature information of the tracking target；
The embedded platform developer terminal identifies the shooting mesh in the video flowing after determining that the tracking target is lost
Whether target characteristic information matches with the tracking target signature information, if it does, then continuing to call the openTLD process
Determine the tracking parameter to tracking target, and according to the tracking parameter controls the picture pick-up device zoom and/or adjusts
Electric platform angle, to carry out tracking and by video stream to client to the tracking target.
2. the method according to claim 1, wherein the embedded platform developer terminal determine it is described with
Track target lose after, identify the photographic subjects for being in the video flowing characteristic information whether with the target signature information
Match, comprising:
After the embedded platform developer terminal determines that the tracking target is lost, the embedded platform developer terminal
Video stream after the tracking target is lost is to the client；
The client receives the region that user draws a circle to approve in the video flowing after the tracking target is lost, and by the delineation
Region is sent to the embedded platform developer terminal；
The embedded platform developer terminal controls the picture pick-up device and acquires the delineation according to the region of the delineation
The video flowing in region calls the video flowing in the region of delineation described in the openTLD progress recognizing；
After the tracking target reappears in the region of the delineation, target is tracked described in the openTLD progress recognizing
Whether the characteristic information of the photographic subjects in video flowing after going out again matches with the tracking target signature information.
3. the method according to claim 1, wherein the embedded platform developer terminal determine it is described with
After track target is lost, identify whether the characteristic information of the photographic subjects in the video flowing matches with the target signature information,
The method also includes:
If the characteristic information of the photographic subjects in the video flowing and the tracking target signature information mismatch, the insertion
OpenTLD process described in formula platform developer terminal disabling terminates the tracking to the tracking target.
4. the method according to claim 1, wherein described in embedded platform developer terminal calling
OpenTLD process determines the tracking parameter to tracking target, comprising:
The tracking parameter includes the first tracking parameter and the second tracking parameter；
The openTLD process carries out kinematic parameter study to tracking target, obtains the first tracking parameter of tracking target, described
Kinematic parameter includes: position, speed, acceleration and motion profile feature；
The openTLD process carries out athletic posture detection to tracking target, obtains the second tracking parameter of tracking target, described
Athletic posture includes various movement appearance posture features.
5. the method according to claim 1, wherein described in embedded platform developer terminal calling
OpenTLD process determines the target signature information of the tracking target, comprising:
The openTLD process obtains the required tracking according to each frame image of the video flowing of the required tracking target
The static appearance feature of target, and according to the static appearance feature and the athletic posture feature in the embedded platform
Tracking target signature information library is established in developer's terminal.
6. the method according to claim 1, wherein the electric platform includes: holder bracket, cradle head controllor
And motor, hard link, the embedded platform developer terminal tune are used between the holder bracket and the picture pick-up device
The tracking parameter to tracking target is determined with the openTLD process, and the picture pick-up device is controlled according to the tracking parameter
Zoom and/or the adjustment electric platform angle, comprising:
The embedded platform developer terminal sends the tracking parameter to the cradle head controllor；
The cradle head controllor calculates holder rack mechanical angular adjustment parameter according to the tracking parameter；
The cradle head controllor controls motor rotation, adjusts the machine of the holder bracket according to the mechanical angle adjustment parameter
Tool angle, the holder bracket drive the picture pick-up device rotation, realize the tracking to tracking target.
7. a kind of device of target following, which is characterized in that described device is applied to tracking system, and the tracking system includes:
Picture pick-up device, the embedded platform developer terminal, electric platform and client, the embedded platform developer terminal
External picture pick-up device, electric platform and client, described device include:
Sending module is obtained, obtains the video flowing acquired by the picture pick-up device for the embedded platform developer terminal,
The video flowing includes the image of multiple photographic subjects and target peripheral region, and by the video stream to the client
End, the client receive the video flowing, select tracking target in the multiple photographic subjects, and by the tracking target
It is sent to calling control module；
Control module is called, calls the openTLD process to determine to tracking mesh for the embedded platform developer terminal
Target tracking parameter, and the picture pick-up device zoom and/or the adjustment electric platform angle are controlled according to the tracking parameter,
To carry out tracking and by video stream to client to the tracking target, and determine the target signature of the tracking target
Information；
Sending module is identified, for identifying institute after the embedded platform developer terminal determines that the tracking target is lost
Whether the characteristic information for stating the photographic subjects in video flowing matches with the tracking target signature information, if it does, then continuing
It calls the openTLD process to determine the tracking parameter of tracking target, and the picture pick-up device is controlled according to the tracking parameter
Zoom and/or the adjustment electric platform angle, to carry out tracking and by video stream to client to the tracking target.
8. device according to claim 7, which is characterized in that the identification sending module includes:
Determine sending submodule, it is described for after the embedded platform developer terminal determines that the tracking target is lost
Embedded platform developer terminal gives the video stream after the tracking target loss to the client, client's termination
User region for drawing a circle to approve in the video flowing after the tracking target is lost is received, and the region of the delineation is sent to described embedding
Enter formula platform developer terminal；
Submodule is called in control, for the embedded platform developer terminal according to the region of the delineation, takes the photograph described in control
As equipment acquires the video flowing in the region of the delineation, the video in the region of delineation described in the openTLD progress recognizing is called
Stream；
Submodule is identified, for after the tracking target reappears in the region of the delineation, the openTLD process to be known
Whether the not described characteristic information for tracking the photographic subjects in the video flowing after target goes out again is believed with the tracking target signature
Breath matching.
9. device according to claim 7, which is characterized in that the calling control module includes:
Study submodule is called, kinematic parameter study is carried out to tracking target for the openTLD process, obtains tracking target
The first tracking parameter, the kinematic parameter includes: position, speed, acceleration and motion profile feature；
Detection sub-module is called, athletic posture detection is carried out to tracking target for the openTLD process, obtains tracking target
The second tracking parameter, the athletic posture includes various movement appearance posture features；
Call establishment submodule, for the openTLD process according to each frame figure of the video flowing of the required tracking target
Picture obtains the static appearance feature of the required tracking target, and according to the static appearance feature and the athletic posture
Tracking target signature information library is established in the embedded platform developer terminal.
10. device according to claim 7, which is characterized in that described device further include:
Deactivation module is identified, for identifying the spy of the photographic subjects in the video flowing after determining that the tracking target is lost
Whether reference breath matches with the tracking target signature information, if mismatched, deactivates the openTLD process, terminates to institute
State the tracking of tracking target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811308505.9A CN109597431B (en) | 2018-11-05 | 2018-11-05 | Target tracking method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811308505.9A CN109597431B (en) | 2018-11-05 | 2018-11-05 | Target tracking method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109597431A true CN109597431A (en) | 2019-04-09 |
| CN109597431B CN109597431B (en) | 2020-08-04 |
Family
ID=65957573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811308505.9A Active CN109597431B (en) | 2018-11-05 | 2018-11-05 | Target tracking method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109597431B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111198561A (en) * | 2019-12-05 | 2020-05-26 | 浙江大华技术股份有限公司 | Motion control method and device for target tracking, computer equipment and storage medium |
| CN111932579A (en) * | 2020-08-12 | 2020-11-13 | 广东技术师范大学 | Method and device for adjusting equipment angle based on motion trail of tracked target |
| CN112119627A (en) * | 2019-08-14 | 2020-12-22 | 深圳市大疆创新科技有限公司 | Target following method and device based on holder, holder and computer storage medium |
| CN112204943A (en) * | 2019-07-16 | 2021-01-08 | 深圳市大疆创新科技有限公司 | Photographing method, apparatus, system, and computer-readable storage medium |
| CN112291480A (en) * | 2020-12-03 | 2021-01-29 | 维沃移动通信有限公司 | Tracking focusing method, tracking focusing device, electronic device and readable storage medium |
| CN112714253A (en) * | 2020-12-28 | 2021-04-27 | 维沃移动通信有限公司 | Video recording method and device, electronic equipment and readable storage medium |
| CN113606456A (en) * | 2021-07-02 | 2021-11-05 | 国网江苏省电力有限公司电力科学研究院 | High-precision numerical control holder capable of automatically tracking and aiming |
| CN113763416A (en) * | 2020-06-02 | 2021-12-07 | 璞洛泰珂(上海)智能科技有限公司 | Automatic labeling and tracking method, device, equipment and medium based on target detection |
| CN114356077A (en) * | 2021-12-15 | 2022-04-15 | 歌尔光学科技有限公司 | Data processing method and device, handle and head-mounted display system |
| CN114900672A (en) * | 2022-07-14 | 2022-08-12 | 杭州舜立光电科技有限公司 | Zooming tracking method |
| CN114979611A (en) * | 2022-05-19 | 2022-08-30 | 国网智能科技股份有限公司 | Binocular sensing system and method |
| CN115225815A (en) * | 2022-06-20 | 2022-10-21 | 南方科技大学 | Target intelligent tracking shooting method, server, shooting system, equipment and medium |
| WO2023284591A1 (en) * | 2021-07-12 | 2023-01-19 | 华为技术有限公司 | Video capture method and apparatus, electronic device, and storage medium |
| CN115690924A (en) * | 2022-12-30 | 2023-02-03 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Potential user identification method and device for unmanned vehicle |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102638675A (en) * | 2012-04-01 | 2012-08-15 | 安科智慧城市技术（中国）有限公司 | Method and system for target tracking by using multi-view videos |
| US20130293758A1 (en) * | 2010-10-12 | 2013-11-07 | Ability Enterprise Co., Ltd. | Method of producing an image |
| CN105654512A (en) * | 2015-12-29 | 2016-06-08 | 深圳羚羊微服机器人科技有限公司 | Target tracking method and device |
| CN105989367A (en) * | 2015-02-04 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Target acquisition method and equipment |
| CN107197199A (en) * | 2017-05-22 | 2017-09-22 | 哈尔滨工程大学 | A kind of intelligent monitoring and controlling device and method for tracking target |
| CN107832683A (en) * | 2017-10-24 | 2018-03-23 | 亮风台（上海）信息科技有限公司 | A kind of method for tracking target and system |
| CN108062115A (en) * | 2018-02-07 | 2018-05-22 | 成都新舟锐视科技有限公司 | A kind of continuous tracking system of multiple target based on cradle head control technology and method |
-
2018
- 2018-11-05 CN CN201811308505.9A patent/CN109597431B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130293758A1 (en) * | 2010-10-12 | 2013-11-07 | Ability Enterprise Co., Ltd. | Method of producing an image |
| CN102638675A (en) * | 2012-04-01 | 2012-08-15 | 安科智慧城市技术（中国）有限公司 | Method and system for target tracking by using multi-view videos |
| CN105989367A (en) * | 2015-02-04 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Target acquisition method and equipment |
| CN105654512A (en) * | 2015-12-29 | 2016-06-08 | 深圳羚羊微服机器人科技有限公司 | Target tracking method and device |
| CN107197199A (en) * | 2017-05-22 | 2017-09-22 | 哈尔滨工程大学 | A kind of intelligent monitoring and controlling device and method for tracking target |
| CN107832683A (en) * | 2017-10-24 | 2018-03-23 | 亮风台（上海）信息科技有限公司 | A kind of method for tracking target and system |
| CN108062115A (en) * | 2018-02-07 | 2018-05-22 | 成都新舟锐视科技有限公司 | A kind of continuous tracking system of multiple target based on cradle head control technology and method |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112204943A (en) * | 2019-07-16 | 2021-01-08 | 深圳市大疆创新科技有限公司 | Photographing method, apparatus, system, and computer-readable storage medium |
| CN112204943B (en) * | 2019-07-16 | 2022-05-20 | 深圳市大疆创新科技有限公司 | Photographing method, apparatus, system, and computer-readable storage medium |
| CN112119627A (en) * | 2019-08-14 | 2020-12-22 | 深圳市大疆创新科技有限公司 | Target following method and device based on holder, holder and computer storage medium |
| CN111198561A (en) * | 2019-12-05 | 2020-05-26 | 浙江大华技术股份有限公司 | Motion control method and device for target tracking, computer equipment and storage medium |
| CN111198561B (en) * | 2019-12-05 | 2021-10-22 | 浙江大华技术股份有限公司 | Motion control method and device for target tracking, computer equipment and storage medium |
| CN113763416A (en) * | 2020-06-02 | 2021-12-07 | 璞洛泰珂(上海)智能科技有限公司 | Automatic labeling and tracking method, device, equipment and medium based on target detection |
| CN111932579A (en) * | 2020-08-12 | 2020-11-13 | 广东技术师范大学 | Method and device for adjusting equipment angle based on motion trail of tracked target |
| CN112291480A (en) * | 2020-12-03 | 2021-01-29 | 维沃移动通信有限公司 | Tracking focusing method, tracking focusing device, electronic device and readable storage medium |
| CN112291480B (en) * | 2020-12-03 | 2022-06-21 | 维沃移动通信有限公司 | Tracking focusing method, tracking focusing device, electronic device and readable storage medium |
| CN112714253A (en) * | 2020-12-28 | 2021-04-27 | 维沃移动通信有限公司 | Video recording method and device, electronic equipment and readable storage medium |
| CN113606456A (en) * | 2021-07-02 | 2021-11-05 | 国网江苏省电力有限公司电力科学研究院 | High-precision numerical control holder capable of automatically tracking and aiming |
| WO2023284591A1 (en) * | 2021-07-12 | 2023-01-19 | 华为技术有限公司 | Video capture method and apparatus, electronic device, and storage medium |
| CN114356077A (en) * | 2021-12-15 | 2022-04-15 | 歌尔光学科技有限公司 | Data processing method and device, handle and head-mounted display system |
| CN114979611A (en) * | 2022-05-19 | 2022-08-30 | 国网智能科技股份有限公司 | Binocular sensing system and method |
| CN115225815A (en) * | 2022-06-20 | 2022-10-21 | 南方科技大学 | Target intelligent tracking shooting method, server, shooting system, equipment and medium |
| CN115225815B (en) * | 2022-06-20 | 2023-07-25 | 南方科技大学 | Intelligent target tracking shooting method, server, shooting system, equipment and medium |
| CN114900672A (en) * | 2022-07-14 | 2022-08-12 | 杭州舜立光电科技有限公司 | Zooming tracking method |
| CN115690924A (en) * | 2022-12-30 | 2023-02-03 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Potential user identification method and device for unmanned vehicle |
| CN115690924B (en) * | 2022-12-30 | 2023-04-18 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Potential user identification method and device for unmanned vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109597431B (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597431A (en) | A kind of method and device of target following | |
| CN108574597A (en) | A kind of newer method, apparatus of state and interactive system | |
| CN108063743B (en) | A kind of method and apparatus that web camera is communicated with depending on networked terminals | |
| CN110636257B (en) | Monitoring video processing method and device, electronic equipment and storage medium | |
| CN109788232A (en) | A kind of summary of meeting recording method of video conference, device and system | |
| CN108989837A (en) | A kind of method and apparatus of picture interception | |
| CN109996127A (en) | Data transmission method and device based on view networking | |
| CN108989273A (en) | A kind of method and apparatus obtaining video flowing | |
| CN110719425A (en) | Video data playing method and device | |
| CN108881948A (en) | A kind of method and system of view networking taking turn monitor video | |
| CN110337098A (en) | A kind of method for building up and device of communication connection | |
| CN110072126A (en) | Data request method, association turn server and computer readable storage medium | |
| CN110324644A (en) | UAV Video live broadcasting method, system, electronic equipment and readable storage medium storing program for executing | |
| CN109905616A (en) | A kind of method and apparatus of Switch Video picture | |
| CN108965783A (en) | A kind of video data handling procedure and view networking recording/playing terminal | |
| CN111447396A (en) | Audio and video transmission method and device, electronic equipment and storage medium | |
| CN110049069B (en) | Data acquisition method and device | |
| CN109788222A (en) | A kind of processing method and processing device regarding networked video | |
| CN110392224A (en) | A kind of data processing method and device | |
| CN108881793A (en) | A kind of data processing method and device of view networking | |
| CN108632635A (en) | A kind of data processing method and device based on regarding networking | |
| CN108880924A (en) | A kind of video broadcasting method and device | |
| CN108882049B (en) | Data display method and video networking terminal | |
| CN108156411A (en) | A kind of method and device asked regarding networked terminals with outside audio-video terminal I frames | |
| CN110139074A (en) | A kind of apparatus control method and system based on view networking |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201230 Address after: 570105 room 1201, Central International Plaza, 77 Binhai street, Longhua District, Haikou City, Hainan Province Patentee after: Hainan Qiantang Shilian Information Technology Co.,Ltd. Address before: 100000 Beijing Dongcheng District Qinglong Hutong 1 Song Hua Building A1103-1113 Patentee before: VISIONVERA INFORMATION TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |