CN114299107A - Multi-photoelectric intelligent tracking method in water area detection system - Google Patents
Multi-photoelectric intelligent tracking method in water area detection system Download PDFInfo
- Publication number
- CN114299107A CN114299107A CN202111259859.0A CN202111259859A CN114299107A CN 114299107 A CN114299107 A CN 114299107A CN 202111259859 A CN202111259859 A CN 202111259859A CN 114299107 A CN114299107 A CN 114299107A
- Authority
- CN
- China
- Prior art keywords
- photoelectric
- target
- tracking
- intelligent
- ship
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 16
- 239000013598 vector Substances 0.000 claims abstract description 37
- 239000000284 extract Substances 0.000 claims abstract description 5
- 230000005693 optoelectronics Effects 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000000903 blocking effect Effects 0.000 abstract description 4
- 230000005622 photoelectricity Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a multi-photoelectric intelligent tracking method in a water area detection system, which divides the existing intelligent tracking scheme into two parts: the intelligent ship identification device identifies the ship through the central station, extracts the characteristic vector A and sends the characteristic vector A to the photoelectric tracking controller, and the intelligent identification computing power can support more photoelectric devices as far as possible through an intelligent identification computing power distribution algorithm; and the two photoelectric smooth tracking controllers receive the video signals, obtain the characteristic vector of the moving target through a ship intelligent recognition algorithm, match the characteristic vector with the A vector and trigger a KCF Tracker tracking algorithm to track the target. Through the cooperative work of the two parts, the blocking and the time delay generated when the photoelectric equipment continuously tracks the target for a long time are reduced, and the photoelectric equipment can accurately track the ship.
Description
Technical Field
The invention relates to the technical field related to radar detection, in particular to a multi-photoelectric intelligent tracking method in a water area detection system.
Background
The most important function in the radar-photoelectric detection system for water area is to find the ship by radar and guide the photoelectric equipment to track the ship for a long time. At present, the long-time smooth tracking of target ships is realized through an artificial intelligence algorithm and is generally applied to a water radar-photoelectric detection system. The common intelligent tracking scheme in the market is as follows: 1. guiding photoelectric aiming targets by a radar; 2. the image is sent to an artificial intelligence device by photoelectricity, a ship is identified intelligently, and a pixel displacement vector from the center of gravity of the ship to the center of the image is calculated; 3. and converting the pixel displacement vector into an optoelectronic PTZ control signal according to information such as radar coordinates of the ship, coordinates of current optoelectronic equipment, a rotation angle, a pitch angle and the like. And automatically controlling the photoelectric equipment to smoothly track the target, and keeping the target at the center of the picture and amplifying the target to a proper size.
However, the artificial intelligent identification software and hardware in the target water area detection system directly use mature algorithms and hardware devices in vehicle identification and pedestrian identification, and the unique characteristics of ship tracking identification in water area detection are not deeply researched, so that the existing intelligent identification software and hardware devices cannot be well used in water area detection.
In the existing water area detection system, one radar is often matched with 4-5 heavy-duty tripod head photoelectric equipment. The radar and the photoelectricity are both deployed in the field, the power supply and the network bandwidth are extremely limited, and the central station is deployed in an urban machine room and is far away from detection equipment such as the radar and the photoelectricity. If the artificial intelligent identification software and hardware are deployed in the central station, the network delay can cause the control signal sent by the intelligent identification software to have larger delay, and the photoelectric equipment cannot accurately track the ship. If the artificial intelligence software and hardware are arranged at the photoelectric equipment end, the artificial intelligence software and hardware consume much energy, the power which can be provided in the field is usually very short, and the artificial intelligence software and hardware can not support high-power equipment. And artificial intelligence software and hardware adds an expensive one, and the cost of each photoelectricity all being equipped with the artificial intelligence equipment can be greatly increased.
In addition, the ship usually navigates very slowly, the monitoring radius of the heavy cradle head photoelectric equipment is 10-20 kilometers, the photoelectric equipment can continuously track and monitor the same ship for more than 10 minutes, and an artificial intelligence recognition algorithm is used for continuously recognizing the same target for a long time, which wastes calculation power.
Disclosure of Invention
In order to solve the above problems, the present invention provides an intelligent identification method for multiple photoelectric devices in a water area detection system, which splits the existing intelligent tracking scheme into two parts: the intelligent ship identification device identifies the ship through the central station, extracts the characteristic vector A and sends the characteristic vector A to the photoelectric tracking controller, and the intelligent identification computing power can support more photoelectric devices as far as possible through an intelligent identification computing power distribution algorithm; and the two photoelectric smooth tracking controllers receive the video signals, obtain the characteristic vector of the moving target through a ship intelligent recognition algorithm, match the characteristic vector with the A vector and trigger a KCF Tracker tracking algorithm to track the target. Through the cooperative work of the two parts, the blocking and the time delay generated when the photoelectric equipment continuously tracks the target for a long time are reduced, and the photoelectric equipment can accurately track the ship.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a multi-photoelectric intelligent tracking method in a water area detection system comprises the following specific steps:
s1, aiming the target ship by the radar guide photoelectric equipment: if the target enters the warning area, triggering the radar to continuously send target coordinates, and if the target deviates from the flight path, triggering the radar to continuously send the target coordinates;
s2, the intelligent ship recognition equipment of the central station receives the video stream sent by the photoelectric equipment, the intelligent recognition algorithm recognizes a video stream target, the recognized ship extracts feature points and forms a feature vector A, and the feature vector A of the target is sent;
through an intelligent identification computing power distribution algorithm, the intelligent identification computing power simultaneously supports a plurality of photoelectric devices;
s3, receiving the target characteristic vector A by the photoelectric tracking controller, tracking the target ship by a KCF Tracker tracking algorithm, and calculating the pixel distance between the target center and the video center;
s4, calculating a control signal of the photoelectric equipment by the photoelectric pan-tilt control algorithm according to the radar coordinates of the target ship and the current PTZ information of the photoelectric equipment through the photoelectric tracking controller, and sending the control signal to the photoelectric equipment;
and S5, the photoelectric device adjusts the rotation angle, the pitch angle and the focal length by means of the control signal, automatically controls the photoelectric device to smoothly track the target, keeps the target at the center of the picture and amplifies the target to a proper size.
Further, in step S3, the optoelectronic tracking controller receives a video signal of the optoelectronic device, and obtains a moving object by a sparse optical flow method; and calculating the characteristic vector of the moving target, performing characteristic matching with the characteristic vector A, and tracking the target by using a KCF Tracker tracking algorithm on the successfully matched target.
Further, in step S4, the pixel displacement vector is converted into the photoelectric PTZ control signal according to the radar coordinates of the ship, the coordinates of the current photoelectric device, the rotation angle, the pitch angle, and the like.
Further, the intelligent ship identification equipment of the central station sequentially identifies the video stream sent by each photoelectric equipment; identifying ships in the video, marking the target ships in the video by combining PTZ information of the photoelectric equipment and radar coordinates of the targets, and sending the extracted characteristic vectors A of the ships to the corresponding photoelectric tracking controller to help the photoelectric tracking controller to manually select the targets.
Furthermore, the photoelectric tracking controller can successfully trigger a KCF Tracker algorithm to realize target tracking by means of a feature vector obtained by a ship intelligent identification algorithm; and when the tracking of the photoelectric tracking controller fails, sending a signal to the central station, and triggering the intelligent ship identification algorithm to manually select the target again.
Compared with the prior art, the invention has the following advantages:
1. according to the invention, the intelligent identification computational power distribution algorithm is installed on the intelligent ship identification equipment of the central station, so that the intelligent identification of the video streams sent by a plurality of photoelectric equipment can be realized with lower cost.
2. A target tracking algorithm and a photoelectric pan-tilt control algorithm are installed in the photoelectric tracking controller, the control facticity and smoothness of the photoelectric pan-tilt can be greatly guaranteed, and the blocking and time delay caused by continuous tracking of the target by the photoelectricity for a long time can be reduced. And the smooth tracking control of a plurality of pan-tilt cameras is realized under the condition of low cost.
3. The central station directly controls the camera usually has 2-3 seconds of delay, and the camera control of the invention has no delay under the condition of automatic identification and tracking.
Drawings
FIG. 1 is a diagram of a multi-photoelectric intelligent tracking method according to the present invention;
FIG. 2 is a flow chart of an intelligent recognition computing power allocation algorithm;
FIG. 3 is a flow chart of a target tracking algorithm;
FIG. 4 is a flow chart of a ship intelligent identification algorithm;
fig. 5 is a flow chart of a photoelectric pan-tilt control algorithm.
Detailed Description
The following describes in detail specific embodiments of the present invention. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
As shown in fig. 1-5, a multi-photoelectric intelligent tracking method in a water area detection system includes the following steps:
s1, aiming the target ship by the radar guide photoelectric equipment: if the target enters the warning area, triggering the radar to continuously send target coordinates, and if the target deviates from the flight path, triggering the radar to continuously send the target coordinates;
s2, the intelligent ship recognition equipment of the central station receives the video stream sent by the photoelectric equipment, the intelligent recognition algorithm recognizes a video stream target, the recognized ship extracts feature points and forms a feature vector A, and the feature vector A of the target is sent;
through an intelligent identification computing power distribution algorithm, the intelligent identification computing power simultaneously supports a plurality of photoelectric devices;
s3, receiving the target characteristic vector A by the photoelectric tracking controller, tracking the target ship by a KCF Tracker tracking algorithm, and calculating the pixel distance between the target center and the video center;
s4, calculating a control signal of the photoelectric equipment by the photoelectric pan-tilt control algorithm according to the radar coordinates of the target ship and the current PTZ information of the photoelectric equipment through the photoelectric tracking controller, and sending the control signal to the photoelectric equipment;
and S5, the photoelectric device adjusts the rotation angle, the pitch angle and the focal length by means of the control signal, automatically controls the photoelectric device to smoothly track the target, keeps the target at the center of the picture and amplifies the target to a proper size.
The specific embodiment is as follows:
the invention splits the existing intelligent tracking scheme into two parts: the intelligent ship identification device of the central station and the photoelectric smooth tracking controller.
As shown in fig. 2, the intelligent ship identification device at the central station is responsible for identifying ships, extracting feature points from the identified ships and forming feature vectors, and transmitting the feature vectors a of the ships to the photoelectric smooth tracking controller through the internet. By means of an intelligent recognition computing power distribution algorithm, the intelligent recognition computing power can support more photoelectric devices as far as possible.
As shown in fig. 3, the photoelectric tracking controller receives the photoelectric video signal and obtains the moving object by the sparse optical flow method. And calculating a feature vector of the moving target and performing feature matching with the A vector. And tracking the target by using a KCF Tracker tracking algorithm for the target successfully matched.
And converting the pixel displacement vector into an optoelectronic PTZ control signal according to information such as radar coordinates of the ship, coordinates of current optoelectronic equipment, a rotation angle, a pitch angle and the like. As shown in fig. 5, the photoelectric device is automatically controlled by the photoelectric pan-tilt control algorithm to smoothly track the target, and the target is kept at the center of the picture and enlarged to a proper size.
According to the invention, a target tracking algorithm and a photoelectric pan-tilt control algorithm are both installed in a photoelectric smooth tracking controller. The scheme has the advantages that the control facticity and smoothness of the photoelectric holder can be greatly guaranteed, and the blocking and time delay generated when the photoelectric holder continuously tracks the target for a long time are reduced. However, in order to control the cost, reduce the power and adapt to a high-humidity field installation environment, a fully-closed small industrial personal computer is required to be selected as the photoelectric tracking controller.
Due to the limitation of hardware, the target tracking algorithm needs to select a KCF Tracker tracking algorithm with small computational complexity and high speed. The KCF Tracker tracking algorithm has the following defects as other non-intelligent tracking algorithms: 1) the target needs to be manually selected; 2) the shooting angle changes along with the movement of the target, and the tracking success rate of the partially or completely shielded target is rapidly reduced.
In order to solve the two problems, the central station of the urban command center sequentially identifies the video stream sent by each photoelectric device through an intelligent identification algorithm. Identifying ships in the video, marking the target ships in the video by combining photoelectric PTZ information and radar coordinates of the targets, and sending the extracted characteristic vectors A of the ships to the corresponding photoelectric tracking controller to help the photoelectric tracking controller to manually select the targets.
The central station and the opto-electronic tracking controller typically have a 2, 3 second delay (too far distance, limited network bandwidth) and the vessel characteristics do not change as the vessel is typically slow for 3 seconds. As shown in fig. 4, the photoelectric tracking controller can successfully trigger the KCF Tracker algorithm to realize target tracking by means of the eigenvector obtained by the ship intelligent identification algorithm. And when the tracking of the photoelectric tracking controller fails, sending a signal to the central station, and triggering the intelligent ship identification algorithm to manually select the target again.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are merely illustrative of the principles of the invention, but that various changes and modifications may be made without departing from the spirit and scope of the invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. A multi-photoelectric intelligent tracking method in a water area detection system is characterized by comprising the following specific steps: s1, aiming the target ship by the photoelectric equipment guided by the radar;
s2, the intelligent ship recognition equipment of the central station receives the video stream sent by the photoelectric equipment, the intelligent recognition algorithm recognizes a video stream target, the recognized ship extracts feature points and forms a feature vector A, and the feature vector A of the target is sent;
through an intelligent identification computing power distribution algorithm, the intelligent identification computing power simultaneously supports a plurality of photoelectric devices;
s3, receiving the target characteristic vector A by the photoelectric tracking controller, tracking the target ship by a KCF Tracker tracking algorithm, and calculating the pixel distance between the target center and the video center;
s4, calculating a control signal of the photoelectric equipment by the photoelectric pan-tilt control algorithm according to the radar coordinates of the target ship and the current PTZ information of the photoelectric equipment through the photoelectric tracking controller, and sending the control signal to the photoelectric equipment;
and S5, the photoelectric device adjusts the rotation angle, the pitch angle and the focal length by means of the control signal, automatically controls the photoelectric device to smoothly track the target, keeps the target at the center of the picture and amplifies the target to a proper size.
2. The method as claimed in claim 1, wherein the step S3 comprises receiving video signals of optoelectronic devices in the optoelectronic tracking controller, and obtaining the moving object by sparse optical flow method; and calculating the characteristic vector of the moving target, performing characteristic matching with the characteristic vector A, and tracking the target by using a KCF Tracker tracking algorithm on the successfully matched target.
3. The method for multi-photoelectric intelligent tracking in a water area detecting system of claim 1, wherein in step S4, the pixel displacement vector is converted into the photoelectric PTZ control signal according to the radar coordinates of the ship, the coordinates of the current photoelectric device, the rotation angle, the pitch angle, etc.
4. The method of claim 1, wherein the central station intelligent vessel identifying device sequentially identifies the video stream transmitted by each optoelectronic device; identifying ships in the video, marking the target ships in the video by combining PTZ information of the photoelectric equipment and radar coordinates of the targets, and sending the extracted characteristic vectors A of the ships to the corresponding photoelectric tracking controller to help the photoelectric tracking controller to manually select the targets.
5. The multi-photoelectric intelligent tracking method in the water area detection system according to claim 4, wherein the photoelectric tracking controller can successfully trigger a KCF Tracker algorithm to realize target tracking by means of a feature vector obtained by a ship intelligent identification algorithm; and when the tracking of the photoelectric tracking controller fails, sending a signal to the central station, and triggering the intelligent ship identification algorithm to manually select the target again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111259859.0A CN114299107A (en) | 2021-10-28 | 2021-10-28 | Multi-photoelectric intelligent tracking method in water area detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111259859.0A CN114299107A (en) | 2021-10-28 | 2021-10-28 | Multi-photoelectric intelligent tracking method in water area detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114299107A true CN114299107A (en) | 2022-04-08 |
Family
ID=80964480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111259859.0A Pending CN114299107A (en) | 2021-10-28 | 2021-10-28 | Multi-photoelectric intelligent tracking method in water area detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299107A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB849499A (en) * | 1955-11-19 | 1960-09-28 | Atlas Werke Ag | Apparatus for recording the true courses of ship targets in conjunction with a radarset |
| CN104297739A (en) * | 2014-10-17 | 2015-01-21 | 西安天和防务技术股份有限公司 | Method for guiding photoelectric tracking equipment in navigation monitoring |
| CN109709589A (en) * | 2019-01-09 | 2019-05-03 | 深圳市芯鹏智能信息有限公司 | A kind of air-sea region solid perceives prevention and control system |
| CN110517284A (en) * | 2019-08-13 | 2019-11-29 | 中山大学 | A kind of target tracking method based on laser radar and Pan/Tilt/Zoom camera |
| CN110632589A (en) * | 2019-10-17 | 2019-12-31 | 安徽大学 | Radar photoelectric information fusion technology |
| CN112904328A (en) * | 2021-01-18 | 2021-06-04 | 安徽瞭望科技有限公司 | Radar photoelectric tracking early warning system and early warning method for offshore wind farm |
-
2021
- 2021-10-28 CN CN202111259859.0A patent/CN114299107A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB849499A (en) * | 1955-11-19 | 1960-09-28 | Atlas Werke Ag | Apparatus for recording the true courses of ship targets in conjunction with a radarset |
| CN104297739A (en) * | 2014-10-17 | 2015-01-21 | 西安天和防务技术股份有限公司 | Method for guiding photoelectric tracking equipment in navigation monitoring |
| CN109709589A (en) * | 2019-01-09 | 2019-05-03 | 深圳市芯鹏智能信息有限公司 | A kind of air-sea region solid perceives prevention and control system |
| CN110517284A (en) * | 2019-08-13 | 2019-11-29 | 中山大学 | A kind of target tracking method based on laser radar and Pan/Tilt/Zoom camera |
| CN110632589A (en) * | 2019-10-17 | 2019-12-31 | 安徽大学 | Radar photoelectric information fusion technology |
| CN112904328A (en) * | 2021-01-18 | 2021-06-04 | 安徽瞭望科技有限公司 | Radar photoelectric tracking early warning system and early warning method for offshore wind farm |
Non-Patent Citations (1)
| Title |
|---|
| 任维: ""运动平台下光电跟踪系统的抗扰控制技术研究"", 《知网》, 15 February 2021 (2021-02-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105407283B (en) | A kind of multiple target initiative recognition tracing and monitoring method | |
| CN108733073B (en) | System and method for controlling unmanned aerial vehicle in region and readable medium | |
| KR101120131B1 (en) | Intelligent Panorama Camera, Circuit and Method for Controlling thereof, and Video Monitoring System | |
| CN107452021A (en) | Camera to automatically track system and method based on single-lens image Dynamic Recognition | |
| CN112312068B (en) | Target detection method, device, equipment and storage medium | |
| CN104524731A (en) | Multi-information fusion intelligent water monitor extinguishing system based on electric-optic turret | |
| KR102473142B1 (en) | Fast zoom and focusing apparatus predicting for high-speed tracking and predicting moving object for camera for providing a high-quality image seamlessly and method for high-speed tracking and predicting moving object for camera using the same | |
| CN110377066B (en) | Control method, device and equipment for inspection equipment | |
| JPH0737100A (en) | Moving object detection and judgement device | |
| CN109917364A (en) | A kind of warning system of integrated radar guiding and photoelectric tracking function | |
| CN112485781B (en) | Anti-unmanned aerial vehicle unmanned system and method based on deep learning | |
| US9165364B1 (en) | Automatic tracking image pickup system | |
| CN112804454A (en) | Wide area warning system and warning method thereof | |
| CN113034828A (en) | System for realizing target detection and identification based on embedded computing terminal and layout method | |
| CN112945015B (en) | Unmanned aerial vehicle monitoring system, unmanned aerial vehicle monitoring method, unmanned aerial vehicle monitoring device and storage medium | |
| CN112489338B (en) | Alarm method, system, device, equipment and storage medium | |
| CN112346078B (en) | Ship ultrahigh detection method and device, electronic equipment and storage medium | |
| KR101836882B1 (en) | All directional Camera and Pan Tilt Zoom Camera Linkage Possible Photographing Apparatus and Method Thereof | |
| CN113095261B (en) | Monitoring method, system, equipment and storage medium based on gun-ball linkage | |
| CN208188331U (en) | Unmanned plane surveillance radar | |
| CN114299107A (en) | Multi-photoelectric intelligent tracking method in water area detection system | |
| CN209608780U (en) | A kind of overhead system automatic detecting safety monitoring system | |
| KR20050056092A (en) | Intelligent surveillance and sentry robot system | |
| CN216916282U (en) | Infrared and visible light cross-modal data fusion search robot | |
| US20120075467A1 (en) | Image capture device and method for tracking moving object using the same |
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 |