CN112347892A - Target identification method and system based on double zoom holders - Google Patents
Target identification method and system based on double zoom holders Download PDFInfo
- Publication number
- CN112347892A CN112347892A CN202011192526.6A CN202011192526A CN112347892A CN 112347892 A CN112347892 A CN 112347892A CN 202011192526 A CN202011192526 A CN 202011192526A CN 112347892 A CN112347892 A CN 112347892A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- aerial vehicle
- unmanned aerial
- wide
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000003384 imaging method Methods 0.000 claims abstract description 20
- 239000012212 insulator Substances 0.000 claims description 8
- 238000007689 inspection Methods 0.000 abstract description 7
- 230000005540 biological transmission Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
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
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a target identification method and a system based on a double-zoom holder, which comprises the following steps: acquiring an image containing a first target through a first imaging device carried on the unmanned aerial vehicle, and identifying the first target from the image; and determining the position of the second target according to the relevance of the first target and the second target, zooming a second imaging device carried on the unmanned aerial vehicle to acquire an image of the second target, and identifying the second target. According to the invention, when the unmanned aerial vehicle is used for carrying out medium-distance and long-distance inspection, the large target and the small target power devices can be simultaneously and accurately and clearly identified.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a target recognition method and a target recognition system based on a double-zooming cradle head.
Background
The unmanned aerial vehicle technology is widely used in power inspection, if the details of a power transmission line need to be observed, the unmanned aerial vehicle needs to fly close to or be in a hovering state, and then target observation is carried out, but at the moment, the safety of the unmanned aerial vehicle and the power transmission line is reduced due to the fact that the distance between the unmanned aerial vehicle and the power transmission line is too close, and particularly when the ultra-high voltage line inspection is carried out; if the aircraft flies in a zoom view field, target identification can be performed only in one scene, and synchronous execution cannot be performed on targets with different size grades, for example, the size difference between an insulator and a pin is large, identification of the pin is limited under the condition that the insulator can be identified, and the insulator often exceeds the view field under the condition that the pin can be identified.
From this, the problem that remote little target and big target carry out multiscale, accurate detection simultaneously can not effectively be solved to present unmanned aerial vehicle electric power inspection scheme.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a target identification method and a target identification system based on a double zoom holder, which can simultaneously and accurately and clearly identify a large target and a small target power device when an unmanned aerial vehicle carries out medium-distance and long-distance inspection.
In order to achieve the purpose, the invention provides the following technical scheme:
the target identification method based on the double zoom holder is provided, and comprises the following steps:
acquiring an image containing a first target through a first imaging device carried on the unmanned aerial vehicle, and identifying the first target from the image;
and determining the position of the second target according to the relevance of the first target and the second target, zooming a second imaging device carried on the unmanned aerial vehicle to acquire an image of the second target, and identifying the second target.
Preferably, the first target is one or more of an insulator, a link fitting, a grading ring and a lightning arrester.
Preferably, the first and second targets are different sizes.
Preferably, the second target comprises a pin.
There is also provided a target recognition system capable of implementing the above target recognition method, comprising:
an unmanned aerial vehicle;
the first imaging device is carried on the unmanned aerial vehicle and used for acquiring a first target image and identifying a first target from the first target image;
a relevance calculating unit for determining the position of the second target according to the relevance of the first target and the second target;
and the second imaging equipment is carried on the unmanned aerial vehicle and used for zooming according to the orientation information of the second target so as to acquire an image of the second target and identify the second target.
Preferably, first imaging equipment is including carrying on the wide-angle cloud platform on unmanned aerial vehicle, connecting the wide-angle zoom lens and the edge calculation module of wide-angle cloud platform, the wide-angle cloud platform drives the wide-angle zoom lens and rotates, the wide-angle zoom lens acquires the image that includes first target, and sends it to the edge calculation module, the first target is discerned from the image to the edge calculation module.
Preferably, the second imaging device comprises a long-focus zooming holder carried on the unmanned aerial vehicle and a long-focus camera connected with the long-focus zooming holder, the long-focus zooming holder drives the long-focus camera to rotate to the position of the second target, and then the long-focus camera zooms to obtain the image of the second target.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, image information of a large-target power device (namely a first target) in a visual field is collected through the wide-angle zoom lens, the image information is accurately identified through the edge calculation module, the position of a second target is determined according to the relevance between the first target and the second target, and the high-precision detection of the second target is further realized through the zooming of the long-focus camera, so that the large-target power device and the small-target power device can be accurately and clearly identified in the same scene.
Drawings
FIG. 1 is a flow chart of steps of a target identification method based on a double zoom holder in the invention;
FIG. 2 is a diagram showing the recognition result of a first object in the present invention;
FIG. 3 is a diagram showing the recognition result of a second object in the present invention;
fig. 4 is a schematic structural diagram of the target recognition system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
as shown in fig. 1, the target identification method based on the dual zoom holders in this embodiment is applicable to power inspection based on the unmanned aerial vehicle, and the method specifically includes:
s1, flying the unmanned aerial vehicle to a preset height, if the unmanned aerial vehicle flies to a position basically consistent with the height of the power transmission line;
s2, as shown in fig. 2, acquiring an image containing a first target P1 by a first imaging device mounted on the drone, and identifying therefrom a first target P1; the first imaging device comprises a wide-angle holder carried on the unmanned aerial vehicle, a wide-angle zoom lens connected with the wide-angle holder and an edge calculation module, wherein the wide-angle holder drives the wide-angle zoom lens to rotate, the wide-angle zoom lens acquires an image containing a first target P1 and sends the image to the edge calculation module, and the edge calculation module identifies the first target P1 from the image;
the first target is one or more of main electric power devices on the transmission line, such as insulators, connecting hardware fittings, grading rings, lightning arresters and the like, and the main electric power devices directly play roles of line connection, fixation, conduction and the like in the transmission process and are generally large-component devices;
s3, as shown in fig. 3, determining the orientation of the second target P2 according to the relevance between the first target P1 and the second target P2, and zooming the second imaging device mounted on the drone so as to be able to stably acquire an image of the second target P2 (i.e. a refined shot image of the second target) and identify a plurality of second targets P2 from the image, wherein the number of the second targets P2 may be multiple; wherein, the size of the first target P1 and the second target P2 is different (the size is determined according to the common knowledge of the skilled person, and according to the conventional concept, the size of the first target P1 is larger than that of the second target P2), and the second target P2 is an auxiliary power device on the power transmission line, including a connection pin, etc., which is generally used for auxiliary connection and fixation of the above main power device, and is mostly a small component device; the second imaging device comprises a long zooming holder carried on the unmanned aerial vehicle and a long-focus camera connected with the long zooming holder, the long zooming holder drives the long-focus camera to rotate to the position of the second target P2, and then the long-focus camera zooms to obtain an image of the second target P2; the relevance comprises a relative position relation between a first target P1 and a second target P2, for example, two ends of a glass insulator are connected with a connecting fitting, and the edge position of the connecting fitting is provided with a pin and a pin missing target; since the grading ring and the link fitting are arranged at the bottom of the ceramic and composite insulator, and the pin, the pin-missing target and the like are arranged at the edge position of the link fitting, the position of the first target P2 is determined according to the acquired image of the first target P2, and the approximate orientation of the second target P2 is further calculated according to the position.
Therefore, the wide-angle zoom lens and the telephoto camera are arranged in the embodiment, when the unmanned aerial vehicle performs a medium-distance and long-distance power patrol task, the unmanned aerial vehicle collects image information of a large part of power devices (namely a first target) in a visual field through the wide-angle zoom lens firstly, accurately identifies the image information through the edge calculation module, determines the position of a second target according to the relevance between the first target and the second target, and further realizes high-precision detection of the second target through zooming of the telephoto camera, so that the unmanned aerial vehicle can accurately and clearly identify the large target and the small target power devices simultaneously in the same scene.
Example 2:
the present embodiment provides a target identification system capable of implementing the target identification method in embodiment 1, as shown in fig. 4, the target identification system includes:
an unmanned aerial vehicle 1;
a first imaging device 2 mounted on the unmanned aerial vehicle 1, for acquiring a first target P1 image and identifying therefrom a first target P1;
a relevance calculating unit 3 for determining the position of the second target P2 according to the relevance of the first target P1 and the second target P2;
and a second imaging device 4 mounted on the unmanned aerial vehicle 1 and used for zooming according to the orientation information of the second target P2 to acquire an image of the second target P2 and identify the second target P2 from the image.
Other related technical features, such as the definitions of the first target P1 and the second target P2, are the same as those of embodiment 1, and are not repeated herein.
In summary, the invention can meet the requirement of the unmanned aerial vehicle for performing power inspection at medium and long distances, and is provided with the wide-angle zoom lens and the telephoto camera, image information of a large part of power devices (namely a first target) in a field of view is collected through the wide-angle zoom lens, the image information is accurately identified through the edge calculation module, the position of a second target is determined according to the relevance between the first target and the second target, and high-precision detection of the second target is further realized through zooming of the telephoto camera, so that the large target and a small target power devices can be accurately and clearly identified simultaneously in the same scene.
It should be noted that the technical features of the above embodiments 1 to 3 can be arbitrarily combined, and the technical solutions obtained by combining the technical features belong to the scope of the present application. In this document, terms such as "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. A target identification method based on a double zoom holder is characterized by comprising the following steps:
acquiring an image containing a first target through a first imaging device carried on the unmanned aerial vehicle, and identifying the first target from the image;
and determining the position of the second target according to the relevance of the first target and the second target, zooming a second imaging device carried on the unmanned aerial vehicle to acquire an image of the second target, and identifying the second target.
2. The target identification method according to claim 1, wherein the first target is one or more of an insulator, a link fitting, a grading ring, and a lightning arrester.
3. The object recognition method of claim 1, wherein the first object and the second object are different sizes.
4. The object recognition method of claim 1, wherein the second object comprises a pin.
5. An object recognition system capable of implementing the object recognition method according to any one of claims 1 to 4, comprising:
an unmanned aerial vehicle;
the first imaging device is carried on the unmanned aerial vehicle and used for acquiring a first target image and identifying a first target from the first target image;
a relevance calculating unit for determining the position of the second target according to the relevance of the first target and the second target;
and the second imaging equipment is carried on the unmanned aerial vehicle and used for zooming according to the orientation information of the second target so as to acquire an image of the second target and identify the second target.
6. The object recognition system of claim 5, wherein the first imaging device includes a wide-angle pan/tilt mounted on the drone, a wide-angle zoom lens coupled to the wide-angle pan/tilt, the wide-angle pan/tilt driving the wide-angle zoom lens to rotate, the wide-angle zoom lens capturing an image containing the first object and sending it to the edge calculation module, the edge calculation module identifying the first object from the image.
7. The target recognition system of claim 5, wherein the second imaging device comprises a long zooming platform mounted on the unmanned aerial vehicle and a long focusing camera connected to the long zooming platform, the long zooming platform drives the long focusing camera to rotate to the position of the second target, and then the long focusing camera zooms to obtain the image of the second target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011192526.6A CN112347892A (en) | 2020-10-30 | 2020-10-30 | Target identification method and system based on double zoom holders |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011192526.6A CN112347892A (en) | 2020-10-30 | 2020-10-30 | Target identification method and system based on double zoom holders |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112347892A true CN112347892A (en) | 2021-02-09 |
Family
ID=74356766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011192526.6A Pending CN112347892A (en) | 2020-10-30 | 2020-10-30 | Target identification method and system based on double zoom holders |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112347892A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034850A (en) * | 2012-12-21 | 2013-04-10 | 湖北工业大学 | Trouble of moving freight car detection system (TFDS) block key loss fault automatic identification method |
| US9609288B1 (en) * | 2015-12-31 | 2017-03-28 | Unmanned Innovation, Inc. | Unmanned aerial vehicle rooftop inspection system |
| US20180247145A1 (en) * | 2017-02-24 | 2018-08-30 | Konica Minolta Inc. | Object approach detection device and object approach detection method |
| CN111683204A (en) * | 2020-06-18 | 2020-09-18 | 南方电网数字电网研究院有限公司 | Unmanned aerial vehicle shooting method and device, computer equipment and storage medium |
-
2020
- 2020-10-30 CN CN202011192526.6A patent/CN112347892A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034850A (en) * | 2012-12-21 | 2013-04-10 | 湖北工业大学 | Trouble of moving freight car detection system (TFDS) block key loss fault automatic identification method |
| US9609288B1 (en) * | 2015-12-31 | 2017-03-28 | Unmanned Innovation, Inc. | Unmanned aerial vehicle rooftop inspection system |
| US20180247145A1 (en) * | 2017-02-24 | 2018-08-30 | Konica Minolta Inc. | Object approach detection device and object approach detection method |
| CN111683204A (en) * | 2020-06-18 | 2020-09-18 | 南方电网数字电网研究院有限公司 | Unmanned aerial vehicle shooting method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| RICARDO OSPINA 等: "target detection vehicle wide angle telephoto size", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》, vol. 162, pages 602 - 612 * |
| 岳子涵: "无人机管制系统中的视觉识别技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 3, pages 031 - 237 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Whitworth et al. | Aerial video inspection of overhead power lines | |
| CN111311967A (en) | Unmanned aerial vehicle-based power line inspection system and method | |
| WO2018056498A1 (en) | Transmission line electromagnetic field and instantaneous inspection image acquisition device and method | |
| CN102590882A (en) | Foreign body monitoring system for airport road surface | |
| CN101330595A (en) | Gang control system for ultra long range radar and video | |
| CN102480615A (en) | Image target area tracking system and method and computer program product | |
| CN104616003A (en) | System for identifying type of foreign matters on power line | |
| CN104101332A (en) | Automatic matching method for inspection photos of transmission lines | |
| CN115311346A (en) | Power inspection robot positioning image construction method and device, electronic equipment and storage medium | |
| CN104539905A (en) | Visible light accurate detection system for electric unmanned helicopter | |
| Schumann et al. | An image processing pipeline for long range UAV detection | |
| CN108281005A (en) | A kind of license board information harvester and method | |
| CN110658193B (en) | Composite insulator umbrella skirt image acquisition device and method and pulverization grade detection method | |
| CN113759961A (en) | Power transmission line panoramic inspection method and system based on unmanned aerial vehicle AI inspection control | |
| CN115580708A (en) | Unmanned aerial vehicle inspection method for optical cable line | |
| CN112351173A (en) | Double-zoom-lens-based stability augmentation holder, unmanned aerial vehicle and target identification method | |
| CN112991246B (en) | Visible light and infrared video image fusion method and device | |
| CN112173149A (en) | Stability augmentation cradle head with edge computing capability, unmanned aerial vehicle and target identification method | |
| CN112347892A (en) | Target identification method and system based on double zoom holders | |
| CN109241947A (en) | Information processing unit and method for the monitoring of stream of people's momentum | |
| CN207491089U (en) | A kind of unmanned machine head device for intelligently switching | |
| CN113873201B (en) | System and method for reverse observation of beyond-visual-distance high point | |
| CN115755946A (en) | Power inspection method, device and system based on digital twinning | |
| CN116301029A (en) | Unmanned aerial vehicle autonomous inspection snapshot method | |
| US20200059606A1 (en) | Multi-Camera System for Tracking One or More Objects Through a Scene |
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 |