CN108427933B - Identification system and identification method for laser obstacle clearance - Google Patents
Identification system and identification method for laser obstacle clearance Download PDFInfo
- Publication number
- CN108427933B CN108427933B CN201810243712.4A CN201810243712A CN108427933B CN 108427933 B CN108427933 B CN 108427933B CN 201810243712 A CN201810243712 A CN 201810243712A CN 108427933 B CN108427933 B CN 108427933B
- Authority
- CN
- China
- Prior art keywords
- contour
- obstacle
- laser
- line
- recognition
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000003384 imaging method Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 230000001066 destructive effect Effects 0.000 abstract 1
- 230000035772 mutation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 239000002985 plastic film Substances 0.000 description 1
- 229920006255 plastic film Polymers 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an identification system for laser obstacle clearance, which comprises an imaging system, an obstacle identification subsystem, a figure identification subsystem, an emergency braking system and a laser emission system. Because of the problem that the beam-shaped laser is difficult to accurately aim at the obstacle due to the remote laser obstacle clearance, the invention provides a method for automatically identifying the obstacle of the power transmission line through line profile extraction; because the laser has very high energy, if the laser is intentionally utilized, destructive striking can be caused, the invention provides a method for identifying and protecting the portrait, and after the portrait information is accurately identified by an algorithm, the cutting protection is automatically carried out, so that the laser obstacle clearing work is safer and more efficient; and automatically judging whether a natural person is in the laser influence range or not before laser emission through portrait contour extraction, if so, cutting off an external power supply through an emergency braking system, and if not, performing the next operation.
Description
Technical Field
The invention belongs to the field of recognition of transmission line obstacles, and particularly relates to a recognition system and a recognition method for laser obstacle clearance.
Background
Because strong wind weather easily occurs in spring and autumn in part of areas, obstacles (greenhouse roller blinds, color steel plates, plastic films, balloons, celebration color bars, kites, plastic bags, banners and the like) frequently occur on the distribution lines and are scraped onto the wires by wind, so that the obstacles hung on the wires and the ground wires of the transmission lines in urban areas and peripheral areas are increased, line faults and power failure frequently occur, and serious threats are caused to the safe operation of the transmission lines and the distribution lines. Currently, the following obstacle clearing modes exist in the power grid: 1. the device of the method is huge, cannot meet complex terrains, and the power grid needs to be subjected to power failure treatment; 2. the wheel type robot is provided with a foreign matter removing tool for removing, and the method is complex in operation and easy to damage a circuit due to mechanical stress; 3. the unmanned aerial vehicle is subjected to flaming cleaning, the positioning process is complex, the cost is high, the environment is polluted, and the line is easy to damage due to the fact that the unmanned aerial vehicle is close to the electrified line.
The remote laser obstacle clearance effectively solves the problems, has the advantages of low operation cost, small influence on the circuit and live working, but the following problems still exist at present: 1. measuring and calculating the distance between the laser emission point and the obstacle to determine the focal length of the laser; 2. manual operation makes it difficult to locate obstacles that are far away, and may lead to misuse of the laser, which may be dangerous to personal safety, for other purposes than clearing obstacles.
The invention provides an identification system and an identification method for laser obstacle clearing, which can effectively identify a target positioned by the system, judge whether the target is an obstacle or a natural person, and close a laser emission system switch only when the system identifies a line and identifies that the obstacle exists on the line and does not identify the person, or cut off an external circuit, thereby greatly eliminating hidden danger of using laser for other purposes and guaranteeing personal safety.
Disclosure of Invention
An identification system for laser obstacle clearance includes an imaging system, an identification system, an emergency braking system, and a laser firing system. The imaging system transmits the region aligned by the laser emission system to the recognition system in the form of an image through the natural light lens group, and the recognition system further comprises an obstacle recognition subsystem and a human image recognition subsystem.
A method for embedding in an identification system comprising the steps of:
s1, imaging a laser obstacle clearance range through an imaging system and then transmitting the imaged laser obstacle clearance range to an identification system;
s2, extracting contour features after carrying out contour recognition on the received image by the recognition system, judging whether a line, an obstacle and a natural person exist in the laser obstacle clearance range or not, and carrying out circling and tracking on the recognized obstacle;
s3, when the portrait identification subsystem judges that natural people exist in the laser influence range, the emergency braking system receives a power-off signal sent by the identification system and can rapidly cut off a power supply switch of the laser emission system;
s4, when the identification system identifies the line, detects that an obstacle exists on the line and does not detect a person, the laser emission system is started to emit laser.
The obstacle recognition subsystem utilizes a contour method to extract a line contour for recognition, a recognized contour line is suddenly changed if an obstacle exists in a power grid line formed by straight lines, a suddenly changed threshold value phi is set for recognition of the obstacle, the obstacle is recognized as the obstacle if the recognized actual suddenly changed value s is larger than the threshold value phi, the contour is defined, and the obstacle is skipped if the suddenly changed value s is smaller than the threshold value phi.
For the definition of the abrupt change value s, two points on the contour line are selected by a specific straight line distance delta l to carry out abrupt change judgment,
where Δl is the distance between two points, d max Is the maximum distance from a point on the contour line between two points to the line connecting the two points.
And determining the threshold value phi, wherein the threshold value phi is larger than the mutation value of the line and smaller than or equal to the mutation value of all the barrier contour lines calculated in the database, and selecting the range.
The portrait identification subsystem extracts image information by using a contour method, compares the acquired contour with the contour of people in a database, and identifies whether natural people exist in the laser influence range.
The contour method is characterized in that binarization processing is carried out on a shot picture, gray values of pixel points on the image are set to be 0 or 255, the whole image shows obvious black-white visual effect, then the binarized image is read, image scanning is sequentially carried out from a first row, contour extraction of the binarized image is achieved through image scanning, and if the image contains a plurality of black blocks, the contour of each color block is extracted from left to right and only one contour is extracted. The contour extraction only extracts the external contour information, ignores the internal information, reduces the data processing amount and improves the recognition efficiency and speed.
The contour extraction firstly defines contour points and starts to search a first contour point, and recursively searches from four adjacent points up, down, left and right until the points of the whole contour are searched.
The definition of the contour point is that if 8 adjacent points of a black point are respectively upper, lower, left, right, upper left, lower left, upper right and lower right, one of the points is a white point, namely the contour point is considered.
The recognition system utilizes the OpenCV to track the recognized portrait or obstacle, if the portrait disappears in the laser influence range, a power supply switch of the laser emission system is closed, and if the obstacle is in the laser influence range, the laser is emitted.
When the portrait identification subsystem judges that a natural person exists in the laser influence range, the emergency braking system receives a power-off signal sent by the identification system, and can rapidly cut off a power supply switch of the laser emission system.
The laser emission system is started to emit laser only when the identification system identifies a line and detects that an obstacle exists on the line and no person is detected.
The beneficial effects of the invention are as follows:
through full-automatic identification, the obstacles on the power transmission line are identified and then cleared, so that the obstacle clearing efficiency of the power grid is improved, the on-line operation of personnel is avoided, the personal safety is ensured, and the problem that the obstacles are difficult to locate in the remote laser obstacle clearing manual operation is further solved; meanwhile, the problem of misuse of the laser is considered, a figure identification security system is established, the system intelligently judges whether natural people exist in the image through figure outline identification, makes a decision of closing or opening a switch, and improves the security of remote laser obstacle clearance.
Drawings
FIG. 1 is a schematic diagram of the relationship between the systems of the present invention;
FIG. 2 is a schematic diagram of the image recognition subsystem of the present invention extracting a target profile;
FIG. 3 is a schematic diagram of an obstacle recognition subsystem of the present invention extracting a target profile;
Detailed Description
As shown in fig. 1, an identification and security system and method based on laser obstacle clearance comprises an imaging system, an identification system, an emergency braking system and a laser emission system. The imaging system transmits the region aligned by the laser emission system to the recognition system in a video form through the lens group, and the recognition system further comprises an obstacle recognition subsystem and a human image recognition subsystem.
Imaging the object on the light screen by an imaging system, namely imaging the convex lens;
performing binarization processing on each frame of image, scanning the processed image, and scanning sequentially from the first row; when the first black point is confirmed, recursively searching for the black point as a center to the left upper, the left lower, the right upper and the right lower respectively, and if one of eight adjacent black points is a white point, the one is a contour point; continuing to confirm a second black point, performing the above operation by taking the black point as the center, performing the circulating operation until the whole contour is found, and performing the following judgment on the extracted contour in the image;
1. as shown in fig. 2, judging whether a closed curve exists in the extracted contour, and if so, returning to the contour midpoint coordinates and the contour shape corresponding to the closed curve; judging whether the midpoint coordinate of the contour is in the influence area of laser emission, comparing the acquired contour shape with the contour of a person in a database, and if the contour is judged to be the person and the midpoint coordinate of the contour is in the influence area of laser emission, cutting off an external switch;
2. as shown in fig. 3, it is determined whether a straight line exists in the extracted contour and whether a mutation exists on the straight line, and if the value of the mutation exceeds a threshold value phi, the internal switch is closed if all three determinations are yes, and it is noted that the internal switch and the external switch are in a series connection relationship with each other, and the laser emission system can be started to emit laser only if both switches are closed.
Of course, the present invention is capable of other various embodiments and its several details are capable of modification and variation in light of the present invention, as will be apparent to those skilled in the art, without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (5)
1. An identification method for laser obstacle clearance is characterized by comprising the following steps:
s1, imaging a laser obstacle clearance range through an imaging system and then transmitting the imaged laser obstacle clearance range to an identification system;
s2, extracting contour features after carrying out contour recognition on the received image by the recognition system, judging whether a line, an obstacle and a natural person exist in the laser obstacle clearance range or not, and carrying out circling and tracking on the recognized obstacle;
s3, when the portrait identification subsystem judges that natural people exist in the laser influence range, the emergency braking system receives a power-off signal sent by the identification system, and can rapidly cut off a power supply switch of the laser emission system;
s4, when the identification system identifies a line, detects that an obstacle exists on the line and does not detect a person, the laser emission system starts the laser emission system to emit laser;
the obstacle recognition in the step S2 is to extract a line contour by using a contour method to recognize, wherein if an obstacle exists in a power grid line formed by straight lines, the recognized contour line is suddenly changed, a suddenly changed threshold value phi is set to recognize the obstacle, if the recognized actual suddenly changed value S is larger than the threshold value phi, the obstacle is recognized as the obstacle, the contour is defined, and if the suddenly changed value S is smaller than the threshold value phi, the obstacle is skipped; the contour method carries out binarization processing on the shot picture, and sets the gray value of the pixel point on the image to 0 or255, displaying a remarkable black-and-white visual effect on the whole image, reading the binarized image, sequentially scanning the image from the first row, extracting the contour of the binarized image by using the image scanning, extracting the contour of each color block from left to right and extracting only one contour if the image contains a plurality of black blocks, extracting only external contour information by extracting the contour, and ignoring internal information; and the definition of the abrupt change value s is that two points on the contour line are selected by a certain specific straight line distance Deltal to carry out abrupt change judgment,wherein Deltal is the distance between two points, dmax is the maximum distance from a point on the contour line between the two points to the connecting line of the two points; and is also provided with
The threshold value phi is larger than the abrupt change value of the power grid line, is smaller than or equal to the abrupt change value of all the obstacle contour lines calculated in the database, and is selected in the range.
2. The recognition method according to claim 1, wherein the portrait recognition in step S2 extracts image information by using a contour method, compares the acquired contour with the contour of a person in the database, and recognizes whether a natural person exists in the laser influence range.
3. The method of claim 1, wherein the contour extraction is performed by defining contour points first and starting to find a first contour point, and recursively finding from four adjacent points above, below, left and right until the entire contour point is found.
4. A method of identifying as claimed in claim 3, characterized in that the definition of the contour point is that if 8 adjacent points of a black point are respectively one of the upper, lower, left, right, upper left, lower left, upper right, lower right, white point, the contour point is considered.
5. The recognition method according to claim 1, wherein the recognition system performs recognition of the figure or the obstacle by using OpenCV, closes a power supply switch of the laser emission system if the figure disappears in the laser influence range, and emits laser light if the obstacle has reached the laser influence range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810243712.4A CN108427933B (en) | 2018-03-23 | 2018-03-23 | Identification system and identification method for laser obstacle clearance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810243712.4A CN108427933B (en) | 2018-03-23 | 2018-03-23 | Identification system and identification method for laser obstacle clearance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108427933A CN108427933A (en) | 2018-08-21 |
| CN108427933B true CN108427933B (en) | 2024-01-05 |
Family
ID=63158856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810243712.4A Active CN108427933B (en) | 2018-03-23 | 2018-03-23 | Identification system and identification method for laser obstacle clearance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108427933B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090232348A1 (en) * | 2008-03-17 | 2009-09-17 | Analogic Corporation | Image Object Separation |
| CN103921942A (en) * | 2014-04-24 | 2014-07-16 | 安徽瓦尔特机械贸易有限公司 | High-altitude unmanned aerial vehicle for removing obstacles |
| CN107103323A (en) * | 2017-03-09 | 2017-08-29 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of target identification method based on image outline feature |
| CN107407722A (en) * | 2015-03-23 | 2017-11-28 | 三菱重工业株式会社 | Laser radar apparatus and driving body |
| CN107666135A (en) * | 2017-11-27 | 2018-02-06 | 上海西邦电气有限公司 | A kind of long distance laser obstacle eliminating system and its application method |
-
2018
- 2018-03-23 CN CN201810243712.4A patent/CN108427933B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090232348A1 (en) * | 2008-03-17 | 2009-09-17 | Analogic Corporation | Image Object Separation |
| CN103921942A (en) * | 2014-04-24 | 2014-07-16 | 安徽瓦尔特机械贸易有限公司 | High-altitude unmanned aerial vehicle for removing obstacles |
| CN107407722A (en) * | 2015-03-23 | 2017-11-28 | 三菱重工业株式会社 | Laser radar apparatus and driving body |
| CN107103323A (en) * | 2017-03-09 | 2017-08-29 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of target identification method based on image outline feature |
| CN107666135A (en) * | 2017-11-27 | 2018-02-06 | 上海西邦电气有限公司 | A kind of long distance laser obstacle eliminating system and its application method |
Non-Patent Citations (2)
| Title |
|---|
| （苏）古勃金，С.И.著；高文馨等译.金属塑性变形 第1卷 塑性变形的物理-力学基础.《金属塑性变形 第1卷 塑性变形的物理-力学基础》.中国工业出版社,1963,第159页. * |
| 辛洪兵等.计算机数字图像处理.《计算机数字图像处理》.2015,第85-86页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108427933A (en) | 2018-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062349B (en) | Video monitoring method and system based on video structured data and deep learning | |
| CN103106766B (en) | Forest fire identification method and forest fire identification system | |
| CN102819735B (en) | Flame detection method based on video frame image | |
| CN110781844B (en) | Security patrol monitoring method and device | |
| CN114140503A (en) | Power distribution network dangerous area identification device and method based on deep learning | |
| CN113743256B (en) | Intelligent early warning method and device for site safety | |
| CN112464782B (en) | Pedestrian recognition method and system | |
| CN107666135A (en) | A kind of long distance laser obstacle eliminating system and its application method | |
| CN114913323B (en) | Charging pile area night open fire detection method | |
| CN112528979A (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN106250846A (en) | A kind of public security image method for detecting based on video monitoring | |
| CN113537007A (en) | Non-worker intrusion detection and alarm method and device applied to railway platform | |
| CN103456123A (en) | Video smoke detection method based on flowing and diffusion characters | |
| CN108427933B (en) | Identification system and identification method for laser obstacle clearance | |
| CN113392754A (en) | Method for reducing false detection rate of pedestrian based on yolov5 pedestrian detection algorithm | |
| KR101249374B1 (en) | Apparatus and method for detecting target shape from image | |
| CN113554682B (en) | Target tracking-based safety helmet detection method | |
| CN113724247B (en) | Intelligent substation inspection method based on image discrimination technology | |
| Gu et al. | Robust road lane detection using extremal-region enhancement | |
| CN112699745A (en) | Method for positioning trapped people on fire scene | |
| CN114914843A (en) | Automatic identification and aiming algorithm for floating foreign matters in power transmission line and laser remote removal system | |
| CN114037951B (en) | Power transmission line anti-collision early warning method based on multidimensional feature recognition | |
| CN112115794A (en) | Method for detecting wearing condition of safety helmet based on deep learning | |
| Aziz et al. | Real-time tracking using edge and color feature | |
| CN113158725B (en) | Comprehensive engineering vehicle construction action judgment method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |