CN104881650A - Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform - Google Patents
Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform Download PDFInfo
- Publication number
- CN104881650A CN104881650A CN201510284911.6A CN201510284911A CN104881650A CN 104881650 A CN104881650 A CN 104881650A CN 201510284911 A CN201510284911 A CN 201510284911A CN 104881650 A CN104881650 A CN 104881650A
- Authority
- CN
- China
- Prior art keywords
- target vehicle
- video
- vehicle
- frame
- unmanned plane
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a vehicle tracking method based on an unmanned aerial vehicle (UAV) dynamic platform, and relates to the field of computer vision. The method is mainly technically characterized in that the method comprises the following steps: step one, receiving a video frame currently shot by a UAV, manually searching for whether the video frame comprises a target vehicle, if the video frame comprises the target vehicle, calculating position coordinates of the target vehicle in the current video frame, and if the video frame does not comprise the target vehicle, repeating the step one; step two, according to the position coordinates of the target vehicle in the current video frame, finding an optimum matching position of the target vehicle in a subsequent frame so as to realize target tracking; step three, according to the position of the target vehicle in a next video, controlling the motion direction of the UAV; and repeating the steps from the step one to the step three.
Description
Technical field
Invention belongs to computer vision field, the car tracing method under especially a kind of unmanned aerial vehicle platform, complex background.
Background technology
Unmanned spacecraft is called for short " unmanned plane ", and english abbreviation is " UAV ", is a kind of unmanned vehicle handled by radio robot or self presetting apparatus.
Current unmanned plane has been applied in the field that plurality of target traces and monitors.In pursue and capture an escaped prisoner, shoot etc. is applied, the vehicle tracking based on unmanned plane has great importance.But under unmanned plane moving platform, carry out vehicle tracking also come with some shortcomings and cause unmanned plane tracking technique temporarily also not widely applied in vehicle tracking field.Existing vehicle tracking is mainly based on license plate number, but in the optical imaging apparatus visual field of unmanned plane, be generally picture less, and resolution is not high, and Car license recognition almost can not use.
Summary of the invention
Technical matters to be solved by this invention, provides a kind of target vehicle tracking.
Vehicle detection based on unmanned plane moving platform provided by the invention and tracking, comprising:
Whether step 1: receive the frame of video that unmanned plane current shooting arrives, manually search containing target vehicle in frame of video, as containing then calculating the position coordinates of target vehicle in current video frame, then repeats step 1 if do not contained;
Step 2: according to the position coordinates tracking target vehicle position in next frame of video of target vehicle at current video frame;
Step 3: the target vehicle position control unmanned plane direction of motion in next video obtained according to step 2;
Repeat step 1 ~ 3.
Preferably, in step 2, use the position of optical flow method localizing objects vehicle in next frame of video.
Preferably, described step 3 comprises further: the target vehicle obtained according to step 2 position judgment target vehicle in next video, in the horizontal direction near left margin or the edge, the right of frame of video, then controls unmanned plane to close in the horizontal direction that Edge shifts of target vehicle; The target vehicle obtained according to step 2 position judgment target vehicle in the vertical direction in next video, near the upper edge of frame of video or lower edge, then controls unmanned plane to close that Edge shifts of target vehicle in the vertical direction.
Further comprise step 4: when target vehicle occurring in tracing process and losing, utilize Kalman filter may appear at the region in subsequent video frame according to the frame of video target of prediction vehicle photographed before lose objects vehicle and be marked in described region in the follow-up frame of video photographed of unmanned plane.
In sum, owing to have employed technique scheme, the invention has the beneficial effects as follows:
The present invention by the position prediction target vehicle ensuing movement locus of target vehicle in current video frame, and adjusts the direction of motion of unmanned plane, the tracking thus the unmanned plane achieving vehicle is taken photo by plane according to predicted position.When there is the situation of track rejection when tracking target vehicle, the region that the present invention also utilizes Kalman filter prediction target vehicle may occur in subsequent video frame, and in subsequent video, indicate this region so that operating personnel find target vehicle in the video frame fast, further increase the stability that target vehicle is followed the tracks of.
Accompanying drawing explanation
Examples of the present invention will be described by way of reference to the accompanying drawings, wherein:
Fig. 1 is the process flow diagram of the embodiment of the present invention.
Embodiment
All features disclosed in this instructions, or the step in disclosed all methods or process, except mutually exclusive feature and/or step, all can combine by any way.
Arbitrary feature disclosed in this instructions, unless specifically stated otherwise, all can be replaced by other equivalences or the alternative features with similar object.That is, unless specifically stated otherwise, each feature is an example in a series of equivalence or similar characteristics.
The inventive method mainly runs on the unmanned plane operating terminal on ground.
First embodiment
As Fig. 1, the present embodiment comprises the following steps:
Step 1: the frame of video that the current shooting that the transmission of reception unmanned plane is returned arrives, unmanned plane operating personnel search target vehicle in the video frame, as then calculated the position coordinates of target vehicle in current video frame containing target vehicle, then repeat this step if do not contained.The present embodiment adopts the method for the position coordinates of the vehicle that really sets the goal to be, first carries out binaryzation to image, extracts the profile determination target vehicle position in the video frame of target vehicle, finally determines the position coordinates in this region.
Step 2: according to the position coordinates tracking target vehicle position in next frame of video of target vehicle at current video frame.What adopt in the present embodiment is that optical flow method is followed the tracks of.The method utilizes image sequence to carry out estimated position velocity field about time (t) and the grey scale change in space (x, y).The method advantage is to detect self-movement target, does not need the information knowing scene in advance, and can be used for the situation of camera motion.
Step 3: the target vehicle position control unmanned plane direction of motion in next video obtained according to step 2, with the middle position making target vehicle be positioned at the unmanned plane shooting visual field as much as possible, is convenient to track up.
Repeat step 1 ~ 3, the unmanned plane of realize target vehicle continues track up.
In other embodiments, described step 3 comprises further: the target vehicle obtained according to step 2 position judgment target vehicle in next video, in the horizontal direction near left margin or the edge, the right of frame of video, then controls unmanned plane to close in the horizontal direction that Edge shifts of target vehicle; The target vehicle obtained according to step 2 position judgment target vehicle in the vertical direction in next video, near the upper edge of frame of video or lower edge, then controls unmanned plane to close that Edge shifts of target vehicle in the vertical direction.
Such as predict the top right-hand side edge of target vehicle near frame of video, then send steering order to unmanned plane, control it and offset certain distance to the right and upwards offset certain distance.
Second embodiment
The present embodiment also add step 4 on the basis of the first embodiment, be specially when target vehicle occurring in tracing process and losing, utilize Kalman filter may appear at the region in subsequent video frame according to the frame of video target of prediction vehicle photographed before lose objects vehicle and be marked in described region in the follow-up frame of video photographed of unmanned plane, so that operating personnel preferably can carry out target vehicle identification in sign region, find target vehicle fast.
Utilize Kalman Filter Technology target of prediction movement locus to be prior art, be widely used in communication, navigation, Control and Guild etc. are multi-field.
The present invention is not limited to aforesaid embodiment.The present invention expands to any new feature of disclosing in this manual or any combination newly, and the step of the arbitrary new method disclosed or process or any combination newly.
Claims (4)
1. based on a wireless vehicle tracking for unmanned plane moving platform, it is characterized in that, comprising:
Whether step 1: receive the frame of video that unmanned plane current shooting arrives, manually search containing target vehicle in frame of video, as containing then calculating the position coordinates of target vehicle in current video frame, then re-executes step 1 if do not contained;
Step 2: according to the position coordinates tracking target vehicle position in next frame of video of target vehicle at current video frame;
Step 3: the target vehicle position control unmanned plane direction of motion in next frame of video obtained according to step 2;
Repeat step 1 ~ 3.
2. a kind of wireless vehicle tracking based on unmanned plane moving platform according to claim 1, is characterized in that, in step 2, uses the position of optical flow method localizing objects vehicle in next frame of video.
3. a kind of wireless vehicle tracking based on unmanned plane moving platform according to claim 1 and 2, it is characterized in that, described step 3 comprises further: the target vehicle obtained according to step 2 position judgment target vehicle in next video, in the horizontal direction near left margin or the edge, the right of frame of video, then controls unmanned plane to close in the horizontal direction that Edge shifts of target vehicle; The target vehicle obtained according to step 2 position judgment target vehicle in the vertical direction in next video, near the upper edge of frame of video or lower edge, then controls unmanned plane to close that Edge shifts of target vehicle in the vertical direction.
4. a kind of wireless vehicle tracking based on unmanned plane moving platform according to claim 1, it is characterized in that, also comprise step 4: when target vehicle occurring in tracing process and losing, utilize Kalman filter may appear at the region in subsequent video frame according to the frame of video target of prediction vehicle photographed before lose objects vehicle and be marked in described region in the follow-up frame of video photographed of unmanned plane.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510284911.6A CN104881650A (en) | 2015-05-29 | 2015-05-29 | Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510284911.6A CN104881650A (en) | 2015-05-29 | 2015-05-29 | Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104881650A true CN104881650A (en) | 2015-09-02 |
Family
ID=53949137
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510284911.6A Pending CN104881650A (en) | 2015-05-29 | 2015-05-29 | Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104881650A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105512643A (en) * | 2016-01-06 | 2016-04-20 | 北京二郎神科技有限公司 | Image acquisition method and device |
CN106874854A (en) * | 2017-01-19 | 2017-06-20 | 西安电子科技大学 | Unmanned plane wireless vehicle tracking based on embedded platform |
WO2017114496A1 (en) * | 2015-12-31 | 2017-07-06 | Wellen Sham | Facilitating location positioning service through a uav network |
WO2017147789A1 (en) * | 2016-03-01 | 2017-09-08 | SZ DJI Technology Co., Ltd. | System and method for identifying target objects |
CN107622273A (en) * | 2016-07-13 | 2018-01-23 | 深圳雷柏科技股份有限公司 | A kind of target detection and the method and apparatus of identification |
WO2018098824A1 (en) * | 2016-12-02 | 2018-06-07 | 深圳市大疆创新科技有限公司 | Photographing control method and apparatus, and control device |
CN108573259A (en) * | 2018-03-10 | 2018-09-25 | 王洁 | Unmanned plane during flying Orientation system and method |
CN108573498A (en) * | 2018-03-08 | 2018-09-25 | 李绪臣 | The instant tracking system of driving vehicle based on unmanned plane |
CN108734726A (en) * | 2017-12-04 | 2018-11-02 | 北京猎户星空科技有限公司 | A kind of method for tracking target, device, electronic equipment and storage medium |
CN109508036A (en) * | 2018-12-24 | 2019-03-22 | 深圳市道通智能航空技术有限公司 | A kind of relay point generation method, device and unmanned plane |
CN109583347A (en) * | 2018-11-22 | 2019-04-05 | 华南理工大学 | A method of it is tracked for a long time for mobile platform |
CN110209201A (en) * | 2019-06-24 | 2019-09-06 | 重庆化工职业学院 | A kind of UAV Intelligent tracing system |
CN110225366A (en) * | 2019-06-26 | 2019-09-10 | 腾讯科技(深圳)有限公司 | Video data processing and advertisement position determine method, apparatus, medium and electronic equipment |
CN110431506A (en) * | 2017-02-24 | 2019-11-08 | 福特全球技术公司 | Tracking based on unmanned plane |
CN110533692A (en) * | 2019-08-21 | 2019-12-03 | 深圳新视达视讯工程有限公司 | A kind of automatic tracking method towards target mobile in unmanned plane video |
CN112699854A (en) * | 2021-03-22 | 2021-04-23 | 亮风台(上海)信息科技有限公司 | Method and device for identifying stopped vehicle |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009029051A1 (en) * | 2007-08-24 | 2009-03-05 | Stratech Systems Limited | Runway surveillance system and method |
CN102156481A (en) * | 2011-01-24 | 2011-08-17 | 广州嘉崎智能科技有限公司 | Intelligent tracking control method and system for unmanned aircraft |
CN103149939A (en) * | 2013-02-26 | 2013-06-12 | 北京航空航天大学 | Dynamic target tracking and positioning method of unmanned plane based on vision |
-
2015
- 2015-05-29 CN CN201510284911.6A patent/CN104881650A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009029051A1 (en) * | 2007-08-24 | 2009-03-05 | Stratech Systems Limited | Runway surveillance system and method |
CN102156481A (en) * | 2011-01-24 | 2011-08-17 | 广州嘉崎智能科技有限公司 | Intelligent tracking control method and system for unmanned aircraft |
CN103149939A (en) * | 2013-02-26 | 2013-06-12 | 北京航空航天大学 | Dynamic target tracking and positioning method of unmanned plane based on vision |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017114496A1 (en) * | 2015-12-31 | 2017-07-06 | Wellen Sham | Facilitating location positioning service through a uav network |
CN107046710A (en) * | 2015-12-31 | 2017-08-15 | 沈玮 | Position location services are promoted by UAV networks |
CN105512643A (en) * | 2016-01-06 | 2016-04-20 | 北京二郎神科技有限公司 | Image acquisition method and device |
US10922542B2 (en) | 2016-03-01 | 2021-02-16 | SZ DJI Technology Co., Ltd. | System and method for identifying target objects |
WO2017147789A1 (en) * | 2016-03-01 | 2017-09-08 | SZ DJI Technology Co., Ltd. | System and method for identifying target objects |
CN107622273A (en) * | 2016-07-13 | 2018-01-23 | 深圳雷柏科技股份有限公司 | A kind of target detection and the method and apparatus of identification |
US10897569B2 (en) | 2016-12-02 | 2021-01-19 | SZ DJI Technology Co., Ltd. | Photographing control method, apparatus, and control device |
US11863857B2 (en) | 2016-12-02 | 2024-01-02 | SZ DJI Technology Co., Ltd. | Photographing control method, apparatus, and control device |
US11575824B2 (en) | 2016-12-02 | 2023-02-07 | SZ DJI Technology Co., Ltd. | Photographing control method, apparatus, and control device |
WO2018098824A1 (en) * | 2016-12-02 | 2018-06-07 | 深圳市大疆创新科技有限公司 | Photographing control method and apparatus, and control device |
CN106874854B (en) * | 2017-01-19 | 2019-12-31 | 西安电子科技大学 | Unmanned aerial vehicle tracking method based on embedded platform |
CN106874854A (en) * | 2017-01-19 | 2017-06-20 | 西安电子科技大学 | Unmanned plane wireless vehicle tracking based on embedded platform |
CN110431506A (en) * | 2017-02-24 | 2019-11-08 | 福特全球技术公司 | Tracking based on unmanned plane |
CN108734726A (en) * | 2017-12-04 | 2018-11-02 | 北京猎户星空科技有限公司 | A kind of method for tracking target, device, electronic equipment and storage medium |
CN108573498A (en) * | 2018-03-08 | 2018-09-25 | 李绪臣 | The instant tracking system of driving vehicle based on unmanned plane |
CN108573259A (en) * | 2018-03-10 | 2018-09-25 | 王洁 | Unmanned plane during flying Orientation system and method |
CN108573259B (en) * | 2018-03-10 | 2019-06-25 | 东营市远信电器与技术有限责任公司 | Unmanned plane during flying Orientation system and method |
CN109583347A (en) * | 2018-11-22 | 2019-04-05 | 华南理工大学 | A method of it is tracked for a long time for mobile platform |
CN109508036A (en) * | 2018-12-24 | 2019-03-22 | 深圳市道通智能航空技术有限公司 | A kind of relay point generation method, device and unmanned plane |
CN110209201A (en) * | 2019-06-24 | 2019-09-06 | 重庆化工职业学院 | A kind of UAV Intelligent tracing system |
CN110225366A (en) * | 2019-06-26 | 2019-09-10 | 腾讯科技(深圳)有限公司 | Video data processing and advertisement position determine method, apparatus, medium and electronic equipment |
CN110533692A (en) * | 2019-08-21 | 2019-12-03 | 深圳新视达视讯工程有限公司 | A kind of automatic tracking method towards target mobile in unmanned plane video |
CN110533692B (en) * | 2019-08-21 | 2022-11-11 | 深圳新视达视讯工程有限公司 | Automatic tracking method for moving target in aerial video of unmanned aerial vehicle |
CN112699854A (en) * | 2021-03-22 | 2021-04-23 | 亮风台(上海)信息科技有限公司 | Method and device for identifying stopped vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104881650A (en) | Vehicle tracking method based on unmanned aerial vehicle (UAV) dynamic platform | |
CN104820998A (en) | Human body detection and tracking method and device based on unmanned aerial vehicle mobile platform | |
US10339387B2 (en) | Automated multiple target detection and tracking system | |
CN109931939B (en) | Vehicle positioning method, device, equipment and computer readable storage medium | |
CN108108697B (en) | Real-time unmanned aerial vehicle video target detection and tracking method | |
US10571934B2 (en) | Target tracking method for air vehicle | |
US8554462B2 (en) | Unmanned aerial vehicle and method for controlling the unmanned aerial vehicle | |
CN109407697A (en) | A kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement | |
CN104794468A (en) | Human face detection and tracking method based on unmanned aerial vehicle mobile platform | |
US9838595B2 (en) | Video generating method and apparatus of video generating system | |
KR101569919B1 (en) | Apparatus and method for estimating the location of the vehicle | |
CN112050810B (en) | Indoor positioning navigation method and system based on computer vision | |
CN112699839B (en) | Automatic video target locking and tracking method under dynamic background | |
CN102436738A (en) | Traffic monitoring device based on unmanned aerial vehicle (UAV) | |
CN108520559B (en) | Unmanned aerial vehicle positioning and navigation method based on binocular vision | |
CN107610157B (en) | Unmanned aerial vehicle target tracking method and system | |
CN109483507B (en) | Indoor visual positioning method for walking of multiple wheeled robots | |
CN103824070A (en) | Rapid pedestrian detection method based on computer vision | |
CN105374049B (en) | Multi-corner point tracking method and device based on sparse optical flow method | |
CN104681986A (en) | Satellite finding method of satellite antenna in inclined state | |
CN103903282A (en) | Target tracking method based on LabVIEW | |
CN104700088A (en) | Gesture track recognition method based on monocular vision motion shooting | |
CN109584264B (en) | Unmanned aerial vehicle vision guiding aerial refueling method based on deep learning | |
US10642272B1 (en) | Vehicle navigation with image-aided global positioning system | |
CN110889353B (en) | Space target identification method based on primary focus large-visual-field photoelectric telescope |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150902 |