CN115995043A - Transmission line hidden danger target identification method and computer readable storage medium - Google Patents
Transmission line hidden danger target identification method and computer readable storage medium Download PDFInfo
- Publication number
- CN115995043A CN115995043A CN202310152840.9A CN202310152840A CN115995043A CN 115995043 A CN115995043 A CN 115995043A CN 202310152840 A CN202310152840 A CN 202310152840A CN 115995043 A CN115995043 A CN 115995043A
- Authority
- CN
- China
- Prior art keywords
- candidate target
- power transmission
- detection frame
- scaling
- target
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 174
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 109
- 238000003384 imaging method Methods 0.000 claims abstract description 73
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000013135 deep learning Methods 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims description 23
- 239000000779 smoke Substances 0.000 claims description 12
- 238000003708 edge detection Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 7
- 239000004568 cement Substances 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 239000004020 conductor Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 241000282887 Suidae Species 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method for identifying hidden danger targets of a power transmission line and a computer readable storage medium, wherein the method comprises the following steps: detecting a transmission tower and a detection frame of a candidate target in a transmission image through a target detection technology based on deep learning; detecting and obtaining a transmission wire in a transmission image, and determining a wire area; determining a distance threshold corresponding to the candidate target according to the type of the candidate target; calculating the physical distance between the candidate target and the wire area according to the actual height of the transmission tower, the height of the detection frame of the transmission tower, the positions of the detection frame of the transmission tower and the detection frame of the candidate target in the transmission image and the imaging distance between the detection frame of the candidate target and the wire area; if the physical distance is smaller than or equal to the distance threshold value corresponding to the candidate target, judging that the candidate target is a hidden danger target. The invention can improve the identification accuracy of hidden danger targets.
Description
Technical Field
The invention relates to the technical field of target detection, in particular to a method for identifying hidden danger targets of a power transmission line and a computer readable storage medium.
Background
In a power transmission scene, construction equipment or other targets often appear near a power transmission wire, and certain hidden danger is generated for the safety of a power transmission line. Therefore, the method has great significance in identifying hidden danger targets in the transmission scene, and can greatly improve the safety guarantee of the transmission line.
In the chinese patent document with publication number CN107609556a, a method for detecting an aerial working machine in a power transmission line environment is proposed, which comprises performing a related preprocessing on an image, obtaining an edge image by edge detection, and dividing a sky area in the image according to the edge image; during detection, the edge images are used for differentiating to obtain candidate detection areas, false hidden danger areas in the candidate areas are removed by using a background model, targets which do not accord with specified characteristics are removed by using color information and edge curvature information, and finally the targets in the remaining candidate areas are regarded as aerial working machines to give an alarm.
The method mainly identifies the operation machinery above the astronomical line through edge detection, but the edge detection effect is lower, and meanwhile, the method cannot detect the target below the astronomical line, which can threaten the transmission line; moreover, detection of high risk targets such as forest fires, smoke, etc. is not supported; in addition, whether the analysis target is threat to the safety of the transmission line is not combined with the transmission line, and high false recognition rate exists.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: provided are a method for identifying potential targets of a power transmission line and a computer-readable storage medium, which can improve the identification accuracy of potential targets.
In order to solve the technical problems, the invention adopts the following technical scheme: a potential risk target identification method for a power transmission line comprises the following steps:
detecting a detection frame of a transmission tower and a detection frame of a candidate target in a transmission image through a target detection technology based on deep learning;
detecting in the power transmission image to obtain a power transmission wire through an edge detection technology, and determining a wire area;
determining a distance threshold corresponding to the candidate target according to the type of the candidate target;
calculating a physical distance between the candidate target and the wire area according to the actual height of the transmission tower, the height of the detection frame of the transmission tower, the positions of the detection frames of the transmission tower and the candidate target in the transmission image and the imaging distance between the detection frame of the candidate target and the wire area;
and if the physical distance is smaller than or equal to the distance threshold value corresponding to the candidate target, judging that the candidate target is a hidden danger target.
The invention also proposes a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements a method as described above.
The invention has the beneficial effects that: by using a target detection algorithm based on deep learning, candidate targets in a power transmission line scene can be identified with high integrity and high accuracy; by determining the wire area and judging whether the candidate target is a hidden danger target according to the actual physical distance between the candidate target and the wire area, whether the candidate target forms threat to the transmission wire can be accurately distinguished, the conditions of missing report and false report are reduced, and the identification accuracy of the hidden danger target can be effectively improved.
Drawings
FIG. 1 is a flow chart of a method for identifying potential targets of a transmission line according to the present invention;
FIG. 2 is a flow chart of a method according to a first embodiment of the invention;
fig. 3 is a schematic diagram of a transmission image according to a first embodiment of the present invention;
fig. 4 is a schematic diagram of a camera imaging principle according to a first embodiment of the present invention.
Detailed Description
In order to describe the technical contents, the achieved objects and effects of the present invention in detail, the following description will be made with reference to the embodiments in conjunction with the accompanying drawings.
Referring to fig. 1, a method for identifying potential targets of a power transmission line includes:
detecting a detection frame of a transmission tower and a detection frame of a candidate target in a transmission image through a target detection technology based on deep learning;
detecting in the power transmission image to obtain a power transmission wire through an edge detection technology, and determining a wire area;
determining a distance threshold corresponding to the candidate target according to the type of the candidate target;
calculating a physical distance between the candidate target and the wire area according to the actual height of the transmission tower, the height of the detection frame of the transmission tower, the positions of the detection frames of the transmission tower and the candidate target in the transmission image and the imaging distance between the detection frame of the candidate target and the wire area;
and if the physical distance is smaller than or equal to the distance threshold value corresponding to the candidate target, judging that the candidate target is a hidden danger target.
From the above description, the beneficial effects of the invention are as follows: the identification accuracy of hidden danger targets can be improved.
Further, the detecting, by the edge detecting technology, of the power transmission wire in the power transmission image, and determining the wire area, specifically includes:
detecting a marginal wire in the power transmission wire in a power transmission image through a rapid straight line detection algorithm, wherein the marginal wire comprises a left marginal wire and a right marginal wire;
mapping the left side marginal wire and the right side marginal wire to the horizontal ground to obtain a left side mapping ray and a right side mapping ray;
and determining a wire area according to the left mapping line, the right mapping line, the bottom line segment of the detection frame of the transmission tower and the bottom line segment of the transmission image.
From the above description, it can be known that by determining the wire area, whether the candidate target poses a threat to the transmission wire can be effectively and accurately identified.
Further, the determining, according to the type of the candidate target, a distance threshold corresponding to the candidate target specifically includes:
determining the risk level of the candidate target according to the type of the candidate target;
and determining a distance threshold corresponding to the candidate target according to the risk level of the candidate target.
As is apparent from the above description, by classifying the risk levels of the targets and setting the distance threshold according to the risk levels, the recognition sensitivity of the high-risk targets can be improved.
Further, the calculating the physical distance between the candidate target and the wire area according to the actual height of the transmission tower, the height of the detection frame of the transmission tower, the positions of the detection frames of the transmission tower and the candidate target in the transmission image, and the imaging distance between the detection frame of the candidate target and the wire area, specifically is:
determining the imaging height of the transmission tower according to the height of the detection frame of the transmission tower;
acquiring the actual height of the transmission tower, and calculating a scaling ratio corresponding to a bottom line segment of a detection frame of the transmission tower according to the imaging height and the actual height of the transmission tower to serve as a first scaling ratio;
calculating an imaging distance between the center height of the power transmission image and the bottom line segment of the detection frame of the power transmission tower as a first imaging distance according to the height of the power transmission image and the position of the bottom line segment of the detection frame of the power transmission tower in the power transmission image;
calculating an imaging distance between the center height of the power transmission image and the bottom line segment of the detection frame of the candidate target as a second imaging distance according to the height of the power transmission image and the position of the bottom line segment of the detection frame of the candidate target in the power transmission image;
calculating a scaling corresponding to a bottom line segment of a detection frame of the candidate target according to the first scaling, the first imaging distance and the second imaging distance, and taking the scaling as a second scaling;
calculating the imaging distance between the bottom line segment of the detection frame of the candidate target and the wire region in the horizontal direction according to the position of the bottom line segment of the detection frame of the candidate target in the power transmission image and the position of the wire region in the power transmission image, and taking the imaging distance as a third imaging distance;
and calculating the physical distance between the candidate target and the wire area according to the third imaging distance and the second scaling.
From the above description, according to the imaging principle of the camera, the actual physical distance between the candidate target and the wire area is obtained through analysis and calculation.
Further, the obtaining the actual height of the transmission tower, and calculating a scaling corresponding to a bottom line segment of a detection frame of the transmission tower according to the imaging height and the actual height of the transmission tower, where the scaling is used as a first scaling, specifically:
dividing the actual height of the transmission tower by the imaging height of the transmission tower to obtain a scaling corresponding to the bottom line segment of the detection frame of the transmission tower, and taking the scaling as a first scaling.
Further, according to the first scaling, the first imaging distance and the second imaging distance, a scaling corresponding to a bottom line segment of the detection frame of the candidate target is calculated, and the scaling is taken as a second scaling, specifically:
and multiplying the first scaling by the first imaging distance and dividing the first scaling by the second imaging distance to obtain scaling corresponding to the bottom line segment of the detection frame of the candidate target, wherein the scaling is used as the second scaling.
Further, the calculating the physical distance between the candidate target and the wire region according to the third imaging distance and the second scaling is specifically:
multiplying the third imaging distance by the second scaling to obtain a physical distance between the candidate object and the wire region.
Further, after the candidate target is determined to be a hidden danger target, the method further includes:
and alarming according to the alarming strategy corresponding to the candidate target.
From the above description, it can be seen that the safety of the transmission line is improved.
Further, the candidate targets include, but are not limited to, construction equipment, mountain fires and smoke, including, but not limited to, tower cranes, forklift trucks, bulldozers, excavators, dump trucks, cranes, cement pump trucks, boat cranes, pile machines, and long arm diggers.
The above description shows that the method can support detection of various construction instruments, detection of mountain fires and smoke, expansion of target types and improvement of the comprehensiveness of target identification.
The invention also proposes a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements a method as described above.
Example 1
Referring to fig. 2-4, a first embodiment of the present invention is as follows: a potential risk target identification method for a power transmission line can be applied to a power transmission scene. As shown in fig. 2, the method comprises the following steps:
s1: and detecting and obtaining a detection frame of a transmission tower and a detection frame of a candidate target in a transmission scene in the transmission image by a target detection technology based on deep learning.
As shown in fig. 3, T0 in fig. 3 is a detection frame of the transmission tower, and T1 is a detection frame of the candidate target.
In this embodiment, the target detection technique includes, but is not limited to, a target detection algorithm such as Yolo, RCNN, SSD. Candidate targets include, but are not limited to, construction equipment, including, but not limited to, tower cranes, forklift trucks, bulldozers, excavators, dump trucks, cranes, cement pump trucks, ship cranes, pile machines, and long arm hogs.
S2: and detecting and obtaining a power transmission wire in the power transmission image by an edge detection technology, and determining a wire area.
Specifically, detecting and obtaining a marginal wire in a transmission image by a fast straight line detection algorithm (FastLineDetector) of Opencv, wherein the marginal wire comprises a left marginal wire and a right marginal wire; then mapping the left side marginal wire and the right side marginal wire to the horizontal ground to obtain a left side mapping line and a right side mapping line; and finally, determining a wire area according to the left side mapping line, the right side mapping line, the bottom line segment of the detection frame of the transmission tower and the bottom line segment of the transmission image.
As shown in fig. 3, L1 in fig. 3 is a left side border wire, and extends to intersect with a detection frame T0 of the transmission tower; l2 is a right side marginal wire and extends to intersect with a detection frame T0 of the transmission tower; l1' is a mapping line segment of the left marginal wire on the horizontal ground, namely a left mapping line, the mapping basis is that the upper left starting point of L1 is mapped to the bottom of a power transmission image, and the lower right end point of L1 is mapped to the bottom of a detection frame T0 of a power transmission tower; l2' is a mapping line segment of the right side marginal wire on the horizontal ground, namely a right side mapping line, the mapping basis is that the upper right starting point of L2 is mapped to the bottom of a power transmission image, and the lower left end point of L2 is mapped to the bottom of a detection frame T0 of a power transmission tower; o is the intersection of the extension of L1 'and the extension of L2'.
In fig. 3, a is a lower left corner of the transmission tower detection frame T0, b is a lower right corner of the transmission tower detection frame T0, and a line segment ab is a bottom line segment of the transmission tower detection frame T0.
The wire area is the area enclosed by the L1', line segments ab, L2' and the bottom of the transmission image.
S3: and determining a distance threshold corresponding to the candidate target according to the type of the candidate target.
In this embodiment, the risk level of the candidate target is determined according to the type of the candidate target, and then the distance threshold corresponding to the candidate target is determined according to the risk level of the candidate target.
The risk level of the candidate target is classified according to the risk level, and may be classified into low risk and high risk, which are specifically classified as follows:
low risk targets: tower cranes, forklift trucks, bulldozers, excavators, dump trucks;
high risk targets: crane, cement pump truck, ship crane, pile machine, long arm digger, mountain fire and smoke.
In this embodiment, the distance threshold of the high risk target is 60 meters, and the distance threshold of the low risk target is 30 meters.
S4: a physical distance between the candidate object and the wire region is calculated.
As shown in fig. 4, assume that the target is located at position P 0 ，A 0 Vertex as target, B 0 For the bottom point of the target, O 0 The intersection point of the imaging horizontal line of the camera and the target is formed, and the imaging corresponding point of the target in the camera is A 0 ’、B 0 ’、O 0 'A'; the actual height of the target is H 0 The horizontal distance between the target and the camera is S 0 The optical center of the camera is R, and the focal length is f, so that A in the image can be calculated according to the imaging principle of the camera 0 Scale k of' position 0 I.e. k 0 ＝A 0 O 0 /A 0 ’O 0 ' wherein A 0 O 0 For point A 0 And point O 0 Distance between (physical distance), A 0 ’O 0 ' Point A 0 ' and Point O 0 ' distance between (imaging distance).
Similarly, when the target is located at any position P, the scaling k=ao/a 'O of the a' position in the image 0 ’。
Due to A 0 O 0 Equal to AO, therefore, k 0 /k＝A’O 0 ’/A 0 ’O 0 ’。
If the actual height of the target is known and the imaging height of the target can be obtained by the image, then P can be calculated 0 Scaling k of position 0 And A' O 0 ' and A 0 ’O 0 The ratio of' canBy image calculation, the scaling k of any position P can be calculated.
Referring to fig. 3-4, c in fig. 3 is a lower right corner of the detection frame of the candidate target, e and f are points of intersection of the extension line of the bottom line segment of the detection frame of the candidate target with the left mapping line L1 'and the right mapping line L2', and d is a point of intersection of the oc connection line and the extension line of the bottom line segment of the detection frame T0 of the transmission tower. Thus, the line segment ce represents the imaging distance between the bottom line segment of the detection frame of the candidate object and the wire region in the horizontal direction.
Assume that the actual height of the tower is H 0 An imaging height h 0 The scaling k at the bottom line ab of the shaft can be obtained 0 ＝H 0 /h 0 。
Assuming that the height of the imaged image (i.e., the power transmission image) is h, the ordinate of the line segment ab in the image is y 0 The ordinate of the line segment ce in the image is Y (the origin of the image coordinate system is at the upper left corner of the image, and the positive Y-axis direction is in the downward direction), and it is obtained that:
A 0 ’O 0 ’＝|y 0 -0.5h|，
A’O 0 ’＝|y-0.5h|，
thus, the scaling k=k at line segment ce 0 *A 0 ’O 0 ’/A’O 0 ’＝k 0 *(|y 0 -0.5h|)/(|y-0.5h|)。
The length L of the line segment ce in the image can be calculated from the imaged image, so that the actual distance s=l×k=l×k of the line segment ce 0 *(|y 0 -0.5h|)/(|y-0.5h|)。
Thus, the present step specifically comprises the steps of:
s401: and determining the imaging height of the transmission tower according to the height of the detection frame of the transmission tower.
S402: and acquiring the actual height of the transmission tower, and calculating the scaling corresponding to the bottom line segment of the detection frame of the transmission tower according to the imaging height and the actual height of the transmission tower to serve as a first scaling.
For example, assume the imaging height of a transmission towerAt 374pix (pixels), the actual height of the transmission tower is 50m (meters), then the first scaling k 0 ＝50/374＝0.134m/pix。
S403: and calculating an imaging distance between the center height of the power transmission image and the bottom line segment of the detection frame of the power transmission tower as a first imaging distance according to the height of the power transmission image and the position of the bottom line segment of the detection frame of the power transmission tower in the power transmission image.
S404: and calculating the imaging distance between the center height of the power transmission image and the bottom line segment of the detection frame of the candidate target as a second imaging distance according to the height of the power transmission image and the position of the bottom line segment of the detection frame of the candidate target in the power transmission image.
S405: and calculating the scaling corresponding to the bottom line segment of the detection frame of the candidate target according to the first scaling, the first imaging distance and the second imaging distance, and taking the scaling as the second scaling.
For example, assuming that the height of the power transmission image is 1743pix, the center height of the power transmission image is 871pix. Assume that an imaging distance between a bottom line segment (line segment ab in fig. 3) of a detection frame of the transmission tower and a center height of the transmission image (i.e., a first imaging distance, i.e., a in fig. 4 0 ’O 0 ') 341pix, the imaging distance between the bottom line segment of the detection frame of the candidate object and the center height of the transmission image (i.e., the second imaging distance, i.e., A' O in FIG. 4) 0 ') 491pix, the scaling at line ce in fig. 3, i.e. the second scaling k=k 0 *A 0 ’O 0 ’/A’O 0 ’＝0.134*341/491＝0.093m/pix。
S406: and calculating the imaging distance between the bottom line segment of the detection frame of the candidate target and the wire region in the horizontal direction according to the position of the bottom line segment of the detection frame of the candidate target in the power transmission image and the position of the wire region in the power transmission image, and taking the imaging distance as a third imaging distance.
S407: and calculating the physical distance between the candidate target and the wire area according to the third imaging distance and the second scaling.
For example, assuming that the third imaging distance (i.e., the length of the line segment ce in fig. 3) is 274pix, the physical distance s=0.093×274=25.5 m between the candidate object and the wire region.
S5: and judging whether the physical distance is smaller than or equal to a distance threshold corresponding to the candidate target, and if so, executing the step S6.
S6: and judging the candidate target as a hidden danger target.
When the candidate target appears near the wire area and does not touch the wire area, the threat is caused to the power transmission line, and therefore, when the physical distance between the candidate target and the wire area is smaller than the corresponding distance threshold value, the candidate target is considered as a hidden danger target.
For example, the candidate object detected in fig. 3 is smoke, the smoke is a high risk object, the distance threshold corresponding to the smoke is 60 meters, and the physical distance between the detection frame of smoke and the wire area is 25.5 meters and less than the distance threshold of 60 meters, so that the smoke in fig. 3 is considered as a hidden danger object.
Further, different alarm strategies can be formulated according to the risk level of the hidden danger target and the physical distance between the hidden danger target and the wire area.
For example, when the hidden danger target is a low risk target, if the hidden danger target is more than 60 meters away from the wire area, prompting and alarming are carried out; if the distance from the lead area is 40-60 m, three-level alarming is carried out; if the distance from the lead area is 20-40 meters, performing secondary alarm; if the distance from the lead area is within 20 meters, performing primary alarm; and if the hidden danger target is positioned in the wire area, carrying out emergency warning.
When the hidden danger target is a high-risk target, if the hidden danger target is more than 80 meters away from the wire area, prompting and alarming are carried out; if the distance from the lead area is 60-80 m, three-level alarming is carried out; if the distance from the lead area is 40-60 m, carrying out secondary alarm; if the distance from the lead area is within 40 meters, performing primary alarm; and if the hidden danger target is positioned in the wire area, carrying out emergency warning.
In the embodiment, the target detection algorithm based on deep learning is used, so that the accuracy of target detection can be effectively improved, detection of various construction instruments can be supported, detection of mountain fire and smoke can be supported, the variety of targets can be expanded, and the comprehensiveness of target identification can be improved; whether the candidate target forms threat to the transmission conductor can be effectively and accurately distinguished by determining the conductor area; the target is classified according to the risk level, and the distance threshold is set according to the risk level, so that the identification sensitivity of the high-risk target can be improved; whether the candidate target is a hidden danger target or not is judged according to the actual physical distance between the candidate target detection frame and the wire area, missing report and false report can be effectively reduced, and the hidden danger identification accuracy is effectively improved.
Example two
The present embodiment is a computer readable storage medium corresponding to the above embodiment, and has a computer program stored thereon, where the program when executed by a processor implements the steps of a method for identifying a hidden danger target of a power transmission line in the above embodiment, and the same technical effects can be achieved, which will not be described here.
In summary, the method for identifying the hidden danger targets of the power transmission line and the computer readable storage medium provided by the invention can effectively improve the accuracy of target detection by using a target detection algorithm based on deep learning, can support the detection of various construction instruments, support the detection of forest fires and smoke, support the expansion of target types and improve the comprehensiveness of target identification; whether the candidate target forms threat to the transmission conductor can be effectively and accurately distinguished by determining the conductor area; the target is classified according to the risk level, and the distance threshold is set according to the risk level, so that the identification sensitivity of the high-risk target can be improved; whether the candidate target is a hidden danger target or not is judged according to the actual physical distance between the candidate target detection frame and the wire area, missing report and false report can be effectively reduced, and the hidden danger identification accuracy is effectively improved.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent changes made by the specification and drawings of the present invention, or direct or indirect application in the relevant art, are included in the scope of the present invention.
Claims (10)
1. The utility model provides a hidden danger target identification method for a power transmission line, which is characterized by comprising the following steps:
detecting a detection frame of a transmission tower and a detection frame of a candidate target in a transmission image through a target detection technology based on deep learning;
detecting in the power transmission image to obtain a power transmission wire through an edge detection technology, and determining a wire area;
determining a distance threshold corresponding to the candidate target according to the type of the candidate target;
calculating a physical distance between the candidate target and the wire area according to the actual height of the transmission tower, the height of the detection frame of the transmission tower, the positions of the detection frames of the transmission tower and the candidate target in the transmission image and the imaging distance between the detection frame of the candidate target and the wire area;
and if the physical distance is smaller than or equal to the distance threshold value corresponding to the candidate target, judging that the candidate target is a hidden danger target.
2. The method for identifying potential hazards of a power transmission line according to claim 1, wherein the detecting the power transmission line in the power transmission image by the edge detection technology and determining the line area specifically comprises:
detecting a marginal wire in the power transmission wire in a power transmission image through a rapid straight line detection algorithm, wherein the marginal wire comprises a left marginal wire and a right marginal wire;
mapping the left side marginal wire and the right side marginal wire to the horizontal ground to obtain a left side mapping ray and a right side mapping ray;
and determining a wire area according to the left mapping line, the right mapping line, the bottom line segment of the detection frame of the transmission tower and the bottom line segment of the transmission image.
3. The method for identifying potential transmission line targets according to claim 1, wherein the determining a distance threshold corresponding to the candidate target according to the type of the candidate target specifically includes:
determining the risk level of the candidate target according to the type of the candidate target;
and determining a distance threshold corresponding to the candidate target according to the risk level of the candidate target.
4. The method for identifying potential transmission line targets according to claim 1, wherein the calculating the physical distance between the candidate target and the wire area according to the actual height of the transmission tower, the height of the detection frame of the transmission tower, the positions of the detection frames of the transmission tower and the candidate target in the transmission image, and the imaging distance between the detection frame of the candidate target and the wire area is specifically:
determining the imaging height of the transmission tower according to the height of the detection frame of the transmission tower;
acquiring the actual height of the transmission tower, and calculating a scaling ratio corresponding to a bottom line segment of a detection frame of the transmission tower according to the imaging height and the actual height of the transmission tower to serve as a first scaling ratio;
calculating an imaging distance between the center height of the power transmission image and the bottom line segment of the detection frame of the power transmission tower as a first imaging distance according to the height of the power transmission image and the position of the bottom line segment of the detection frame of the power transmission tower in the power transmission image;
calculating an imaging distance between the center height of the power transmission image and the bottom line segment of the detection frame of the candidate target as a second imaging distance according to the height of the power transmission image and the position of the bottom line segment of the detection frame of the candidate target in the power transmission image;
calculating a scaling corresponding to a bottom line segment of a detection frame of the candidate target according to the first scaling, the first imaging distance and the second imaging distance, and taking the scaling as a second scaling;
calculating the imaging distance between the bottom line segment of the detection frame of the candidate target and the wire region in the horizontal direction according to the position of the bottom line segment of the detection frame of the candidate target in the power transmission image and the position of the wire region in the power transmission image, and taking the imaging distance as a third imaging distance;
and calculating the physical distance between the candidate target and the wire area according to the third imaging distance and the second scaling.
5. The method for identifying a hidden danger target of a power transmission line according to claim 4, wherein the steps of obtaining an actual height of the power transmission tower, and calculating a scaling corresponding to a bottom line segment of a detection frame of the power transmission tower as the first scaling according to the imaging height and the actual height of the power transmission tower are specifically as follows:
dividing the actual height of the transmission tower by the imaging height of the transmission tower to obtain a scaling corresponding to the bottom line segment of the detection frame of the transmission tower, and taking the scaling as a first scaling.
6. The method for identifying a hidden danger target of a power transmission line according to claim 4, wherein the calculating the scaling corresponding to the bottom line segment of the detection frame of the candidate target according to the first scaling, the first imaging distance and the second imaging distance is specific to:
and multiplying the first scaling by the first imaging distance and dividing the first scaling by the second imaging distance to obtain scaling corresponding to the bottom line segment of the detection frame of the candidate target, wherein the scaling is used as the second scaling.
7. The method for identifying potential transmission line targets according to claim 4, wherein the calculating the physical distance between the candidate target and the wire area according to the third imaging distance and the second scaling ratio is specifically:
multiplying the third imaging distance by the second scaling to obtain a physical distance between the candidate object and the wire region.
8. The method for identifying potential targets of a power transmission line according to claim 1, wherein after the candidate target is determined to be a potential target, further comprising:
and alarming according to the alarming strategy corresponding to the candidate target.
9. The method of any one of claims 1-8, wherein the candidate target includes, but is not limited to, construction equipment including, but not limited to, a tower crane, forklift, bulldozer, excavator, dump truck, crane, cement pump truck, ship crane, pile engine, and long arm excavator, forest fire, and smoke.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310152840.9A CN115995043A (en) | 2023-02-16 | 2023-02-16 | Transmission line hidden danger target identification method and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310152840.9A CN115995043A (en) | 2023-02-16 | 2023-02-16 | Transmission line hidden danger target identification method and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115995043A true CN115995043A (en) | 2023-04-21 |
Family
ID=85992094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310152840.9A Pending CN115995043A (en) | 2023-02-16 | 2023-02-16 | Transmission line hidden danger target identification method and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115995043A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314022A (en) * | 2023-11-29 | 2023-12-29 | 深圳金三立视频科技股份有限公司 | Method and device for analyzing hidden danger of power transmission line |
-
2023
- 2023-02-16 CN CN202310152840.9A patent/CN115995043A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314022A (en) * | 2023-11-29 | 2023-12-29 | 深圳金三立视频科技股份有限公司 | Method and device for analyzing hidden danger of power transmission line |
| CN117314022B (en) * | 2023-11-29 | 2024-05-28 | 深圳金三立视频科技股份有限公司 | Method and device for analyzing hidden danger of power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103697855B (en) | A kind of hull horizontal attitude measuring method detected based on sea horizon | |
| KR102269750B1 (en) | Method for Real-time Object Detection Based on Lidar Sensor and Camera Using CNN | |
| KR102660837B1 (en) | Method for landslide crack detection based deep learning and Method for landslide monitoring therewith and Apparatus thereof | |
| CN112001226A (en) | Unmanned 3D target detection method and device and storage medium | |
| CN115995043A (en) | Transmission line hidden danger target identification method and computer readable storage medium | |
| CN108229342A (en) | A kind of surface vessel target automatic testing method | |
| CN110147748B (en) | Mobile robot obstacle identification method based on road edge detection | |
| CN111626169A (en) | Image-based railway dangerous falling rock size judgment method | |
| CN114494075A (en) | Obstacle identification method based on three-dimensional point cloud, electronic device and storage medium | |
| CN116989679A (en) | Highway high slope displacement integrated monitoring method based on image processing | |
| JP3883124B2 (en) | Template matching processing method and processing apparatus in image processing | |
| JP7348575B2 (en) | Deterioration detection device, deterioration detection system, deterioration detection method, and program | |
| CN107765257A (en) | A kind of laser acquisition and measuring method based on the calibration of reflected intensity accessory external | |
| US11733174B2 (en) | Information processing apparatus, information processing method, and storage medium | |
| JP4941420B2 (en) | Target detection system | |
| CN113160191B (en) | Environmental composition integrity judging method and device based on laser radar | |
| JP3399104B2 (en) | Leading vehicle detection device and approach warning device | |
| EP3930306A2 (en) | Method and apparatus for stabilizing image, roadside device and cloud control platform | |
| KR102377393B1 (en) | Image analysis method and system for recognition of Heavy Equipment and Gas Pipe | |
| KR102357210B1 (en) | System and method for measuring waves for preventing beach accidents and computer program for the same | |
| CN114202631A (en) | Method for determining rock working face and working point in secondary rock crushing operation | |
| CN112857252A (en) | Tunnel image boundary line detection method based on reflectivity intensity | |
| CN114078140B (en) | Landslide track extraction method based on landslide boundary polygons and slope map | |
| CN117789198B (en) | Method for realizing point cloud degradation detection based on 4D millimeter wave imaging radar | |
| CN115440057B (en) | Method, device, equipment and medium for detecting curve vehicle based on radar map |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Sun Bo Inventor after: Zhang Yu Inventor after: Liu Dongjian Inventor after: Liang Hao Inventor before: Sun Bo Inventor before: Zhang Yu Inventor before: Liu Dongjian Inventor before: Liang Hao |