CN103024344A - Automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter - Google Patents

Automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter Download PDF

Info

Publication number
CN103024344A
CN103024344A CN2011102824962A CN201110282496A CN103024344A CN 103024344 A CN103024344 A CN 103024344A CN 2011102824962 A CN2011102824962 A CN 2011102824962A CN 201110282496 A CN201110282496 A CN 201110282496A CN 103024344 A CN103024344 A CN 103024344A
Authority
CN
China
Prior art keywords
target
ptz
particle filter
camera
automatic
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
Application number
CN2011102824962A
Other languages
Chinese (zh)
Inventor
赵刚
张少文
冯琰一
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
PCI Suntek Technology Co Ltd
Original Assignee
PCI Suntek Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by PCI Suntek Technology Co Ltd filed Critical PCI Suntek Technology Co Ltd
Priority to CN2011102824962A priority Critical patent/CN103024344A/en
Publication of CN103024344A publication Critical patent/CN103024344A/en
Pending legal-status Critical Current

Links

Images

Abstract

The invention discloses an automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter. The automatic PTZ target tracking method comprises the steps of detection of a moving target, target tracking and pan-and-tilt control. The method can allow a camera to lock the moving target automatically and implement automatic tracking of vision guidance, thereby overcoming the defect that a fixed camera has a narrow monitoring visual field. At first, the moving target is selected by a manual frame in a pre-set position or the moving target is automatically detected by a vision consistency algorithm; secondly, a target position is matched and tracked by the classic particle filter; and finally, a control order is sent according to the position and the size of the target, so that the position and the focal distance of the camera can be adjusted. When a tracking process fails, the camera automatically skips back to the pre-set position, and the detection of next turn can be carried out. The automatic PTZ target tracking method provided by the invention is reasonable in design, so that the automatic tracking function of the camera to the target can be realized, and the target is located in the middle of a lens all along. Therefore, the automatic PTZ target tracking method brings convenience to monitoring personnel.

Description

A kind of method of the PTZ automatically track target based on particle filter
Technical field
The present invention relates to computer vision field, particularly relate to a kind of method of the PTZ automatically track target based on particle filter.
Background technology
It is high that Pan/Tilt/Zoom camera has the fast precision of speed, and the advantage that monitoring range is large is one of monitoring frontend that the most generally uses in the monitoring field now.The automatic Tracking monitoring system of intelligence PTZ has the target analysis function, and is furnished with high-resolution camera, large multiplying power Zoom optic lens and high rotating speed The Cloud Terrace, and automatic capturing is to suspicious object fast and accurately.By presetting bit is set, the automatic Tracking monitoring system of intelligent PTZ can be realized the functions such as presetting bit scanning, automatic cruising.Therefore and unrealized real from motion tracking but this scanning is just blindly cruised, and fails the state of real-time target acquisition.Therefore need to propose the automatic tracking control technology of a kind of The Cloud Terrace, when The Cloud Terrace possesses the Automatic Target Tracking function, can control according to the actual motion information of target the motion of The Cloud Terrace, for the monitor staff provides more valuable monitor message.
Automatic tracking system based on PTZ mainly is divided into the two large divisions: the one, obtain target information according to video image, i.e. and target detection, another part mates target exactly, i.e. target following, and utilize trace information control video camera to rotate.At present, although many have the target detection of a lot of maturations and an algorithm of tracking, can be directly used in the ball machine of motion seldom.Because the rotation of camera, traditional background modeling method can not be used, and can not use based on the motion target tracking of testing result.Another major issue in the system is exactly the control of PTZ, there is difference in different servo-control systems to response speed and the accuracy of control command, in case reaching demand to the response of control command, control appliance just may not cause target in image, to be lost, image analysis algorithm so also must cause the failure of following the tracks of just with ineffective.Thereby closely link to each other with target detection, target following, PTZ control based on the performance of the automatic tracking system of PTZ.
Summary of the invention
Technical problem to be solved by this invention is the method that proposes a kind of PTZ automatically track target based on particle filter, automatically locks moving target and carries out visually oriented from motion tracking to realize video camera.
For achieving the above object, the present invention carries out manual frame in presetting bit first and selects moving target or utilize the vision consistency algorithm to carry out the automatic detection of moving target, the coupling of utilizing classical particle filtering to carry out the target location is followed the tracks of, according to position and the size transmission control command of target position and the focal length of video camera are adjusted at last, after following the tracks of unsuccessfully, automatically jump back to presetting bit, carry out the detection of next round.
Described particle filter is used for: seeks one group of random sample of propagating at state space probability density function is similar to, replace integral operation with sample average, thus the process of the state of acquisition minimum variance estimate.In the method, be used for the pursuit movement target.
The present invention also provides a kind of strategy of PTZ control, comprising: according to the tracing positional of target, calculate target from the distance of image center, if distance is then sent out the order that PTZ moves and is offset greater than the threshold value of setting; Account for the ratio of entire image when the size of target less than the threshold value of setting, then send the focus controlling order.All orders all are only to allow cam movement a bit of, and what namely realize is intermittent control.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, the below will do simple the introduction to the accompanying drawing of required use in embodiment or the description of the Prior Art, apparently, accompanying drawing in the following describes only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is PTZ automatically track target structural representation in the embodiment of the invention one;
Fig. 2 is based on the particle filter tracking schematic flow sheet in the embodiment of the invention one;
Fig. 3 is The Cloud Terrace control flow schematic diagram in the embodiment of the invention one.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, the present invention is further detailed explanation below in conjunction with the drawings and specific embodiments.Obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
Embodiment one, referring to Fig. 1, and Fig. 2, Fig. 3.
The course of work of said system specifically may further comprise the steps referring to Fig. 1:
Step 1, choose target to be tracked, can adopt manual mode, also can adopt automatic mode.
Step 2, utilization are followed the tracks of moving target based on the method for classical particle filtering, obtain the position of moving target.
The distance of step 3, judgement moving target and image center is controlled The Cloud Terrace.When target disappears or follows the tracks of unsuccessfully, jump to preset point, carry out detection next time.
Described tracking based on classical particle filtering specifically may further comprise the steps:
Step 1, initialization: get k=0, press p (x 0) N sample point of extraction
Figure BSA00000578498400031
I=1 ..., N
Step 5, resample: according to normalization weights separately
Figure BSA00000578498400033
Size copy/give up sample
Figure BSA00000578498400034
Obtain N approximate the obedience
Figure BSA00000578498400035
The sample that distributes Order
Step 6, Output rusults: the output of algorithm is the particle collection Can approximate representation with it
Figure BSA00000578498400039
Step 7, K=K+1 repeated for 2 steps to 6 steps.
The above only is the specific embodiment of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.

Claims (5)

1. the method based on the PTZ automatically track target of particle filter is characterized in that, may further comprise the steps:
The first step: according to the needs of monitoring occasion, choose suitable presetting bit, manually frame selects target to be tracked in presetting bit, or utilizes based on the conforming moving object detection algorithm of vision, automatically detects moving target;
Second step: the coupling of utilizing classical particle filter method to carry out moving target position is followed the tracks of;
The 3rd step: position and size to target are analyzed, if the position of target exceeds the zone of setting, then send the order of camera motion; If target sizes is less than the threshold value of setting, the order of then sending adjusting focal length;
The 4th step: if target exceeds the catching range of video camera or follows the tracks of unsuccessfully, then jump to presetting bit, and return the first step, carry out next time tracking otherwise return second step.
2. the method for a kind of PTZ automatically track target based on particle filter according to claim 1, it is characterized in that, the described manual frame of the first step selects moving target to belong to manual mode, utilization belongs to automatic mode based on the conforming moving object detection algorithm of vision, when detecting a plurality of moving target, select the conduct target to be tracked of area maximum.
3. the method for a kind of PTZ automatically track target based on particle filter according to claim 1, it is characterized in that, the described classical particle filtering of second step is a kind ofly to utilize a kind of method of rewards and punishments mechanism estimated state value based on the dynamical system forward model, can be used for non linear system.
4. the method for a kind of PTZ automatically track target based on particle filter according to claim 1, it is characterized in that, the 3rd described camera translation of step and deflection control command, be to be determined by the distance that put to the optical center position of target, the focus controlling order is that the ratio that the size by target accounts for entire image determines.
5. the method for a kind of PTZ automatically track target based on particle filter according to claim 1, it is characterized in that, the 4th step is described, if target exceeds the catching range of video camera or follows the tracks of unsuccessfully, then jumping to presetting bit, is to be in the state of cisco unity malfunction for the failure that prevents from following the tracks of causes video camera.
CN2011102824962A 2011-09-20 2011-09-20 Automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter Pending CN103024344A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2011102824962A CN103024344A (en) 2011-09-20 2011-09-20 Automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2011102824962A CN103024344A (en) 2011-09-20 2011-09-20 Automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter

Publications (1)

Publication Number Publication Date
CN103024344A true CN103024344A (en) 2013-04-03

Family

ID=47972424

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2011102824962A Pending CN103024344A (en) 2011-09-20 2011-09-20 Automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter

Country Status (1)

Country Link
CN (1) CN103024344A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104394324A (en) * 2014-12-09 2015-03-04 成都理想境界科技有限公司 Special-effect video generation method and device
CN104883506A (en) * 2015-06-26 2015-09-02 重庆智韬信息技术中心 Self-service shooting method based on face identification technology
CN105844673A (en) * 2016-05-20 2016-08-10 北京传翼四方科技发展有限公司 All-angle human tracking system and control method based on nature human-computer interaction technology
CN107105193A (en) * 2016-02-23 2017-08-29 芋头科技(杭州)有限公司 Robot monitoring system based on human body information
CN107135377A (en) * 2017-05-27 2017-09-05 深圳市景阳科技股份有限公司 Monitor automatic tracking method and device
CN108921001A (en) * 2018-04-18 2018-11-30 特斯联(北京)科技有限公司 A kind of video monitor holder and its method for tracing using artificial intelligence prediction tracking
CN109302562A (en) * 2018-10-12 2019-02-01 中国民用航空总局第二研究所 Target acquisition method for tracing, system, medium and equipment based on video

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101026759A (en) * 2007-04-09 2007-08-29 华为技术有限公司 Visual tracking method and system based on particle filtering
CN101072332A (en) * 2007-06-04 2007-11-14 深圳市融合视讯科技有限公司 Automatic mobile target tracking and shooting method
CN101572804A (en) * 2009-03-30 2009-11-04 浙江大学 Multi-camera intelligent control method and device
CN102006461A (en) * 2010-11-18 2011-04-06 无锡中星微电子有限公司 Joint tracking detection system for cameras

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101026759A (en) * 2007-04-09 2007-08-29 华为技术有限公司 Visual tracking method and system based on particle filtering
CN101072332A (en) * 2007-06-04 2007-11-14 深圳市融合视讯科技有限公司 Automatic mobile target tracking and shooting method
CN101572804A (en) * 2009-03-30 2009-11-04 浙江大学 Multi-camera intelligent control method and device
CN102006461A (en) * 2010-11-18 2011-04-06 无锡中星微电子有限公司 Joint tracking detection system for cameras

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104394324B (en) * 2014-12-09 2018-01-09 成都理想境界科技有限公司 Special efficacy video generation method and device
CN104394324A (en) * 2014-12-09 2015-03-04 成都理想境界科技有限公司 Special-effect video generation method and device
CN104883506A (en) * 2015-06-26 2015-09-02 重庆智韬信息技术中心 Self-service shooting method based on face identification technology
CN104883506B9 (en) * 2015-06-26 2021-09-03 重庆智韬信息技术中心 Self-service shooting method based on face recognition technology
CN104883506B (en) * 2015-06-26 2021-07-02 重庆智韬信息技术中心 Self-service shooting method based on face recognition technology
CN107105193B (en) * 2016-02-23 2020-03-20 芋头科技(杭州)有限公司 Robot monitoring system based on human body information
CN107105193A (en) * 2016-02-23 2017-08-29 芋头科技(杭州)有限公司 Robot monitoring system based on human body information
CN105844673B (en) * 2016-05-20 2020-03-24 北京传翼四方科技发展有限公司 Full-angle human tracking system based on natural human-computer interaction technology and control method
CN105844673A (en) * 2016-05-20 2016-08-10 北京传翼四方科技发展有限公司 All-angle human tracking system and control method based on nature human-computer interaction technology
CN107135377A (en) * 2017-05-27 2017-09-05 深圳市景阳科技股份有限公司 Monitor automatic tracking method and device
CN108921001A (en) * 2018-04-18 2018-11-30 特斯联(北京)科技有限公司 A kind of video monitor holder and its method for tracing using artificial intelligence prediction tracking
CN109302562A (en) * 2018-10-12 2019-02-01 中国民用航空总局第二研究所 Target acquisition method for tracing, system, medium and equipment based on video
CN109302562B (en) * 2018-10-12 2020-09-29 中国民用航空总局第二研究所 Video-based target detection tracking method, system, medium, and device

Similar Documents

Publication Publication Date Title
CN103024344A (en) Automatic PTZ (Pan/Tilt/Zoom) target tracking method based on particle filter
CN101860732B (en) Method of controlling holder camera to automatically track target
CN103716595B (en) Panoramic mosaic video camera and ball machine inter-linked controlling method and device
CN103927878B (en) A kind of automatic shooting device for parking offense and automatically grasp shoot method
CN102291569B (en) Double-camera automatic coordination multi-target eagle eye observation system and observation method thereof
CN105744163A (en) Video camera and video recording method performing tracking focusing based on depth information
CN103716594A (en) Panorama splicing linkage method and device based on moving target detecting
CN105407283A (en) Multi-target active recognition tracking and monitoring method
CN101572804A (en) Multi-camera intelligent control method and device
CN107509055A (en) A kind of rotary panorama focus identification optronic tracker and its implementation
CN205693769U (en) A kind of motion cameras positioning capturing quick to panorama target system
CN102307297A (en) Intelligent monitoring system for multi-azimuth tracking and detecting on video object
CN105208327A (en) Master/slave camera intelligent monitoring method and device
CN103247260B (en) LED display automatic brightness-regulating system and method
CN105430280A (en) Double-field thermal imager and automatic focusing method thereof
CN104010131A (en) Automatic follow-focus device and method of cameras
CN111586357A (en) Monitoring device and method for automatic focusing of multiple monitoring cameras
CN203722342U (en) Inspection system of transformer station
CN105096596A (en) Traffic violation detecting method and system
CN103546679B (en) Device and method for reducing separation of shot object from shooting window
CN202231803U (en) Intelligent monitoring system for multi-aspect video object tracking detection
CN105516661A (en) Master-slave target monitoring system and method in combination of fisheye camera and PTZ camera
CN103634509A (en) Automatic tracking recording method and system
CN201837775U (en) Remote laser night vision device
CN103677734A (en) Multi-target data association algorithm based on feature matching matrix

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20130403