CN110618424B - Remote high-voltage line discovery method based on multi-sensor fusion - Google Patents
Remote high-voltage line discovery method based on multi-sensor fusion Download PDFInfo
- Publication number
- CN110618424B CN110618424B CN201910924503.0A CN201910924503A CN110618424B CN 110618424 B CN110618424 B CN 110618424B CN 201910924503 A CN201910924503 A CN 201910924503A CN 110618424 B CN110618424 B CN 110618424B
- Authority
- CN
- China
- Prior art keywords
- sensor
- radar sensor
- voltage line
- tower
- voltage
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/865—Combination of radar systems with lidar systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/885—Radar or analogous systems specially adapted for specific applications for ground probing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/87—Combinations of systems using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Abstract
The invention discloses a remote high-voltage wire discovery method based on multi-sensor fusion, which comprises the following specific steps: 1) input frame and noise reduction processing: performing framing processing on an input video stream, and performing primary noise reduction to obtain a high-quality image; 2) detecting the high-voltage line tower: carrying out end-to-end training by using a YOLO (YOLO) network; 3) pre-connecting lines among towers; 4) carrying out directional detection on a millimeter wave radar sensor and a laser radar sensor; 5) and constructing a precise high-voltage wire area. The method identifies the high-voltage line tower and key parts thereof, depicts possible areas of the high-voltage line, and avoids the situation that an image algorithm cannot work. Meanwhile, signals of the multi-source sensor are fused, the detection directions of the sensors such as millimeter waves and laser radars are guided through the pre-wiring technology, and high-voltage wire existing regions with high reliability are gradually generated along with the approach of the distance, so that the detection accuracy is greatly improved, and the method has important significance in the aspect of aviation or safety protection.
Description
Technical Field
The invention relates to a method, in particular to a remote high-voltage wire discovery method based on multi-sensor fusion.
Background
With the continuous development of science and technology, helicopters and unmanned aerial vehicles have been widely used in various fields. The ever-increasing demand for fast tasks, particularly at low altitudes, makes the need for remote target detection more and more urgent. Because helicopter and unmanned aerial vehicle often will carry out the task in the low latitude complex environment, the accident of colliding with the barrier takes place occasionally, causes very big personnel and economic loss. In helicopter accident statistical analysis, the high-voltage line has the biggest threat because of its small diameter, and the remote identification degree of difficulty is great. Therefore, it is necessary to develop a fast and effective method for automatically discovering high voltage lines from a long distance.
Although the methods currently found for high voltage lines are numerous, the following drawbacks remain in general:
(1) the image processing algorithm discovered by the existing high-voltage line cannot carry out remote detection
The traditional image segmentation method is to extract high-voltage line features based on a CNN structure, perform depth information retrieval on pictures by training a neural network, and discover possible positions of high-voltage lines. However, because the diameter of the high-voltage wire is small, the image shot at a long distance is not easy to find, so that the problem that the existing image segmentation method cannot find and provide the area of the high-voltage wire at a long distance at present is solved. The aircraft can be damaged due to the fact that the aircraft runs on a high-voltage line when the speed is high due to emergency tasks and low-altitude flight.
(2) The detection capability is limited with a single type of sensor:
aiming at the problems, the existing methods are solved by sensors such as millimeter wave radars, optical radars and the like, but the existing methods are all single-sensor solutions, and the single sensor has obvious defects and cannot undertake the task of independent detection. For example, a radar has a small detection distance, so that the airplane cannot perform timely evasion and other actions, and the accuracy is poor.
Disclosure of Invention
In order to solve the defects of the technology, the invention provides a method for finding a long-distance high-voltage wire based on multi-sensor fusion.
In order to solve the technical problems, the invention adopts the technical scheme that: a remote high-voltage line discovery method based on multi-sensor fusion comprises the following specific steps:
1) input frame and noise reduction processing: taking a video stream collected by an airborne sensor as input, performing framing processing on the input video stream through an algorithm, and performing primary noise reduction to obtain a high-quality image;
2) detecting the high-voltage line tower: carrying out key target detection on the frame subjected to framing processing in the step 1) by adopting a target detection neural network; the target detection neural network adopts a YOLO end-to-end training network, training data are labeled before training, the network is trained by using the labeled images, an original input frame image, calibration frame information of the position of a target, target category information and confidence coefficient are output, and finally, an optimal frame for framing the target is selected on a high-voltage line tower; the calibration frame information is a four-dimensional calibration frame and is expressed by (x, y, w, h), namely coordinates x and y of a target center point, and width w and height h of the frame;
3) pre-connecting lines between towers: establishing a pre-connection line between towers of the high-voltage line tower based on prior knowledge, namely pre-connecting a line between optimal frames;
when the distance is longer, the pre-connecting line between the towers is the connecting line between the tower tip parts, and is shown by the formula II:
{ a1, b1, c1. } - > { a2, b2, c2.. }
When the distance is close, the pre-connection line between towers is the connection line between the components on the towers and is shown by a formula III:
equation III, { a1} - > { a2}
In the formula II and the formula III, letter elements represent components on the tower, the numerical subscript is a label of the tower, and a symbol- > represents a corresponding relation;
4) and (3) carrying out directional detection on the millimeter wave radar sensor and the laser radar sensor: through the prediction of the step 3), the general direction of the high-voltage line is detected, the general direction is used for position guidance and is input into a central processing unit, the central processing unit calculates the position information into a control signal, and the rotation direction and the angle of the millimeter wave radar sensor and the laser radar sensor are controlled, so that the detection range is focused to a specified area; the information detected by the millimeter wave radar sensor and the laser radar sensor is received by the data fusion module, is converged and is input to the next link;
5) constructing an accurate high-voltage wire area: the method comprises the following steps that a millimeter wave radar sensor, a laser radar sensor and a photoelectric sensor jointly form a multi-source sensor, information obtained by the multi-source sensor is transmitted in a graph form, and transmitted graphs are aligned in space and time; the photoelectric sensor provides RGB images, the laser radar sensor is assisted to judge the object type, and the millimeter wave radar sensor feeds back depth, speed and direction information;
the aligned images are fused and correspond to a single object, so that the final object category, depth and position information is obtained, a high-voltage wire area with the confidence coefficient is constructed, and the remote high-voltage wire discovery is completed; the confidence measure method is shown in formula IV:
in the formula: n represents confidence probability, d represents distance, beta represents adjusting factor which is super parameter set by man; mAP represents the average precision of the image detection algorithm for detecting the components on the tower, and when the components cannot be detected at a long distance, the mAP is 1.
Further, in step 1), noise reduction is performed on the cloud and fog by using a dark channel prior method, and defogging operation is performed by operation between the input image, the atmospheric component and the projection ratio, as shown in formula I:
in the formula: j (x) represents a fog-free image, i (x) represents a fog image, t (x) represents a transmittance, and a represents an atmospheric light value; t is t0Representing a fixed parameter.
The invention discloses a remote high-voltage wire finding method based on multi-sensor fusion, which can quickly and effectively realize the identification of a high-voltage wire tower and key parts thereof, automatically draw the possible existing area of a high-voltage wire and avoid the condition that an image algorithm cannot work due to long distance, unobvious target and blurred image. Meanwhile, based on the knowledge level, signals of the multi-source sensors are fused, the detection directions of the sensors such as millimeter waves and laser radars are guided through the pre-connection technology, high-voltage wire existing regions with high reliability are gradually generated along with the approach of the distance, the accuracy of high-voltage wire detection is greatly improved, a safety foundation is laid for realizing low-altitude flight of the airplane, and the method has important significance in aviation or safety protection.
Drawings
FIG. 1 is a flow chart of a method for discovering a high voltage line according to the present invention.
FIG. 2 is a schematic diagram of a remote high-voltage line pre-wiring according to the present invention.
FIG. 3 is a schematic diagram of a high-voltage cable pre-wiring in a short distance according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
A remote high-voltage line discovery method based on multi-sensor fusion comprises the following specific steps:
1) input frame and noise reduction processing: taking a video stream collected by an airborne sensor as input, performing framing processing on the input video stream through an algorithm, and performing primary noise reduction to obtain a high-quality image; the noise reduction processing is mainly performed on the cloud and fog in a dark channel prior mode, and defogging operation is performed through operation among an input image, an atmospheric component and a projection ratio, so that the high-voltage line tower can be detected when the definition of the image needs to be ensured to be larger than 1 k; the defogging operation is shown in formula I:
in the formula: j (x) represents a fog-free image, i (x) represents a fog image, t (x) represents a transmittance, and a represents an atmospheric light value; t is t0Represents a fixed parameter;
2) detecting the high-voltage line tower: carrying out key target detection on the frame (namely the preprocessed frame) subjected to framing processing in the step 1) by adopting a target detection neural network; the target detection neural network adopts a YOLO end-to-end training network, training data are labeled before training, the network is trained by using the labeled images, an original input frame image, calibration frame information of the position of a target, target category information and confidence coefficient are output, and finally, an optimal frame for framing the target is selected on a high-voltage line tower; the calibration frame information is a four-dimensional calibration frame and is expressed by (x, y, w, h), namely coordinates x and y of a target center point, and width w and height h of the frame; the confidence may detect whether the box has a representation of the target;
3) pre-connecting lines between towers: establishing a pre-connection line between towers of the high-voltage line tower based on prior knowledge, namely pre-connecting a line between optimal frames; for the prior knowledge, relevant technical parameters are stored when the high-voltage wire is laid, so that the pre-connection line is established by means of the prior knowledge;
as shown in fig. 2, when the distance is far, because the helicopter or the unmanned aerial vehicle is far from the high-voltage wire and the fertility is limited, the target detection algorithm can only identify the top position of the high-voltage wire tower, and therefore, the pre-connection line between towers is the connection line between the tower tip parts, and is represented by the formula ii:
{ a1, b1, c1. } - > { a2, b2, c2.. }
As shown in fig. 3, when the distance is short, because the helicopter or the unmanned aerial vehicle is short from the high-voltage wire, the target detection algorithm can identify the position of the top component of the high-voltage wire tower, so that the connection line made by the components between towers is used as the predicted position of the high-voltage wire to obtain the position prediction with higher accuracy, that is, the pre-connection line between towers is the connection line between the components on the towers, and is shown in formula iii:
equation III, { a1} - > { a2}
In the formula II and the formula III, letter elements represent components on the tower, the numerical subscript is a label of the tower, and a symbol- > represents a corresponding relation; in fig. 2 and 3, the black boxes represent target position predictions made by deep learning (i.e., selected optimal boxes), and the connecting lines between the black boxes represent pre-connecting lines made according to prior knowledge;
when the distance is long, the target detection algorithm can only detect the position of the tower tip and cannot well identify the components on the tower, so that the position of the high-voltage wire can only be estimated by connecting the position of the tower tip, and the confidence coefficient is lower than that in the short distance; however, along with the approach of the distance between the airplane and the high-voltage line tower, more detailed component parts such as insulators, resistors and the like can be detected, and the connection directly takes the components as a starting point and an end point, so that the confidence of the constructed high-voltage line area is also continuously improved;
4) and (3) carrying out directional detection on the millimeter wave radar sensor and the laser radar sensor: through the prediction of the step 3), the general direction of the high-voltage line is detected, the general direction is used for position guidance and is input into a central processing unit, the central processing unit calculates the position information into a control signal, and the rotation direction and the angle of the millimeter wave radar sensor and the laser radar sensor are controlled, so that the detection range is focused to a specified area; the millimeter wave radar sensor can return the depth information, the speed and the steering angle of the target and output an image matrix in a point cloud picture mode; the laser radar can return a gray level image without being influenced by visible light; the central processing unit selects Xilinx Zynq-7000SoCZC702, the chip adopts an ARM + FPGA architecture, the ARM generates a scheduling signal, and the FPGA executes an operation acceleration function; finally, the information detected by the millimeter wave radar sensor and the laser radar sensor is received by the data fusion module, information is gathered, and the information is input to the next link;
5) constructing an accurate high-voltage wire area: the method comprises the following steps that a millimeter wave radar sensor, a laser radar sensor and a photoelectric sensor jointly form a multi-source sensor, information obtained by the multi-source sensor is transmitted in a graph form, and transmitted graphs are aligned in space and time; the photoelectric sensor provides RGB images, the laser radar sensor is assisted to judge the object type, and the millimeter wave radar sensor feeds back depth, speed and direction information;
the aligned images are fused and correspond to a single object to obtain final object category, depth and position information, and a high-voltage wire area with the confidence coefficient is constructed as the distance from the tower is closer, so that the remote high-voltage wire discovery is completed; the high-confidence interval can assist in adjusting the air route, and the route navigation algorithm selects a region with sparse high-voltage lines as a route planning node with higher priority. In the running process of the navigation system, the emergency can be responded at any time, the route is continuously adjusted according to the information obtained in real time, and the most reasonable route is planned;
the confidence measure is shown in formula iv:
in the formula: n represents confidence probability, d represents distance, beta represents adjusting factor which is super parameter set by man; mAP represents the average precision of the image detection algorithm for detecting the components on the tower, and when the components cannot be detected at a long distance, the mAP is 1.
The invention discloses a remote high-voltage line discovery method based on multi-sensor fusion, which is a method for constructing and discovering a high-voltage line region by combining an optical sensor, a millimeter wave radar sensor, a laser radar sensor and a laser radar sensor into a multi-source sensor (namely signal fusion of the multi-source sensor) on the basis of the optical sensor, the millimeter wave radar sensor and the laser radar sensor which are arranged on a helicopter and an unmanned aerial vehicle, is used for remotely discovering a high-voltage line to assist the central controller to make timely early warning and plan a feasible path, can increase the confidence coefficient of a threat region from far to near by the cooperation of the multi-source sensors under the condition of larger environmental interference (such as foggy days and rainy days), helps the airplane to sense threats in advance in a sight distance range, makes reasonable planning, achieves the purpose of accurately and efficiently discovering threats, and realizes the safety foundation of low-altitude flight of the airplane, the safety is ensured to a great extent, and the method has important significance in aviation or safety protection.
Compared with the prior art, the invention mainly makes the following progress:
(1) remote prediction and anti-collision early warning of high-voltage lines: different from other methods which directly adopt an identification method to find the high-voltage wire, the method firstly finds the wire tower, generates the potential existing position of the high-voltage wire by predicting the wire tower, and transmits the potential position information to sensors such as a millimeter wave radar, a laser radar and the like. The sensor carries out directional detection, can obtain the high-voltage line region that the confidence coefficient is higher and higher along with being closer to the high-voltage line, when the confidence coefficient is higher than certain threshold value, can plan the circuit and avoid, realized that the helicopter can begin the detection process to the high-voltage line from a distance to and a set of mechanism that helps it avoid striking the high-voltage line.
(2) A new mechanism for multi-sensor fusion: the sensor is guided by the high-voltage wire prediction position to perform directional detection; different from the existing method for directly fusing signals, the fusion adopted by the invention is based on knowledge type fusion on a higher level, namely, the independence of the operation among the sensors is kept, the knowledge fusion is processed, the scheduling information is generated to realize the cooperation among the sensors, and the data of the sensors are fused on the knowledge level to achieve the optimal effect.
The above embodiments are not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make variations, modifications, additions or substitutions within the technical scope of the present invention.
Claims (2)
1. A remote high-voltage line discovery method based on multi-sensor fusion is characterized by comprising the following steps: the method comprises the following specific steps:
1) input frame and noise reduction processing: taking a video stream collected by an airborne sensor as input, performing framing processing on the input video stream through an algorithm, and performing primary noise reduction to obtain a high-quality image;
2) detecting the high-voltage line tower: carrying out key target detection on the frame subjected to framing processing in the step 1) by adopting a target detection neural network; the target detection neural network adopts a YOLO end-to-end training network, training data are labeled before training, the network is trained by using the labeled images, an original input frame image, calibration frame information of the position of a target, target category information and confidence coefficient are output, and finally, an optimal frame for framing the target is selected on a high-voltage line tower; the calibration frame information is a four-dimensional calibration frame and is expressed by (x, y, w, h), namely coordinates x and y of a target center point, and width w and height h of the frame;
3) pre-connecting lines between towers: establishing a pre-connection line between towers of the high-voltage line tower based on prior knowledge, namely pre-connecting a line between optimal frames;
when the distance is longer, the pre-connecting line between the towers is the connecting line between the tower tip parts, and is shown by the formula II:
{ a1, b1, c1. } - > { a2, b2, c2.. }
When the distance is close, the pre-connection line between towers is the connection line between the components on the towers and is shown by a formula III:
equation III, { a1} - > { a2}
In the formula II and the formula III, letter elements represent components on the tower, the numerical subscript is a label of the tower, and a symbol- > represents a corresponding relation;
4) and (3) carrying out directional detection on the millimeter wave radar sensor and the laser radar sensor: through the prediction of the step 3), the general direction of the high-voltage line is detected, the general direction is used for position guidance and is input into a central processing unit, the central processing unit calculates the position information into a control signal, and the rotation direction and the angle of the millimeter wave radar sensor and the laser radar sensor are controlled, so that the detection range is focused to a specified area; the information detected by the millimeter wave radar sensor and the laser radar sensor is received by the data fusion module, is converged and is input to the next link;
5) constructing an accurate high-voltage wire area: the method comprises the following steps that a millimeter wave radar sensor, a laser radar sensor and a photoelectric sensor jointly form a multi-source sensor, information obtained by the multi-source sensor is transmitted in a graph form, and transmitted graphs are aligned in space and time; the photoelectric sensor provides RGB images, the laser radar sensor is assisted to judge the object type, and the millimeter wave radar sensor feeds back depth, speed and direction information;
the aligned images are fused and correspond to a single object, so that the final object category, depth and position information is obtained, a high-voltage wire area with the confidence coefficient is constructed, and the remote high-voltage wire discovery is completed; the confidence measure is shown in formula iv:
in the formula: n represents confidence probability, d represents distance, beta represents adjusting factor which is super parameter set by man; mAP represents the average precision of the image detection algorithm for detecting the components on the tower, and when the components cannot be detected at a long distance, the mAP is 1.
2. The method for discovering long distance high voltage line based on multi-sensor fusion as claimed in claim 1, wherein: in the step 1), noise reduction is performed on cloud and mist by adopting a dark channel prior mode, and defogging operation is performed by operation among an input image, an atmospheric component and a projection ratio, as shown in a formula I:
in the formula: j (x) represents a fog-free image, i (x) represents a fog image, t (x) represents a transmittance, and a represents an atmospheric light value; t is t0Representing a fixed parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910924503.0A CN110618424B (en) | 2019-09-27 | 2019-09-27 | Remote high-voltage line discovery method based on multi-sensor fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910924503.0A CN110618424B (en) | 2019-09-27 | 2019-09-27 | Remote high-voltage line discovery method based on multi-sensor fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110618424A CN110618424A (en) | 2019-12-27 |
| CN110618424B true CN110618424B (en) | 2021-09-21 |
Family
ID=68924813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910924503.0A Active CN110618424B (en) | 2019-09-27 | 2019-09-27 | Remote high-voltage line discovery method based on multi-sensor fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110618424B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113470442B (en) * | 2021-07-02 | 2023-01-20 | 时代低空(山东)产业发展有限公司 | Method for detecting dangerous approaching of high-voltage line of low-altitude flight of aircraft |
| CN113570701B (en) * | 2021-07-13 | 2023-10-24 | 聚好看科技股份有限公司 | Hair reconstruction method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120126511A (en) * | 2011-05-12 | 2012-11-21 | 국방과학연구소 | Threat evaluation system and method against antiair target and computer-readerable storage medium having a program recorded thereon where the program is to carry out its method |
| CN105743017A (en) * | 2016-04-19 | 2016-07-06 | 平玉兰 | Unmanned aerial vehicle inspection ground measurement and control station and transportation safeguard system used for power transmission line |
| CN105892489A (en) * | 2016-05-24 | 2016-08-24 | 国网山东省电力公司电力科学研究院 | Multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and control method |
| DE102015104212A1 (en) * | 2015-03-20 | 2016-09-22 | Valeo Schalter Und Sensoren Gmbh | Lens device for an optoelectronic sensor of a motor vehicle with fastening device, optoelectronic sensor, motor vehicle and method |
| CN107561509A (en) * | 2017-08-28 | 2018-01-09 | 电子科技大学 | A kind of airborne millimetre-wave radar electric power line detecting method |
| CN107729808A (en) * | 2017-09-08 | 2018-02-23 | 国网山东省电力公司电力科学研究院 | A kind of image intelligent acquisition system and method for power transmission line unmanned machine inspection |
| CN107742093A (en) * | 2017-09-01 | 2018-02-27 | 国网山东省电力公司电力科学研究院 | A kind of infrared image power equipment component real-time detection method, server and system |
| CN108061901A (en) * | 2017-12-01 | 2018-05-22 | 国家电网公司 | The method that 3D electric power line models are rebuild based on airborne laser radar point cloud data |
| CN108319982A (en) * | 2018-02-06 | 2018-07-24 | 贵州电网有限责任公司 | A kind of power-line patrolling unmanned plane Fusion obstacle detection method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU77979U1 (en) * | 2008-07-22 | 2008-11-10 | Военная академия воздушно-космической обороны имени Маршала Советского Союза Г.К. Жукова | SYSTEM OF AUTOMATIC RECOGNITION OF CLASSES OF AIR GOALS |
| CN106874886A (en) * | 2017-03-10 | 2017-06-20 | 南京沃杨机械科技有限公司 | For the farm environment cognitive method of the unpiloted Multi-sensor Fusion of agricultural machinery |
| CN108229366B (en) * | 2017-12-28 | 2021-12-14 | 北京航空航天大学 | Deep learning vehicle-mounted obstacle detection method based on radar and image data fusion |
| RU2686878C1 (en) * | 2018-07-05 | 2019-05-06 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Саратовский государственный технический университет имени Гагарина Ю.А." (СГТУ имени Гагарина Ю.А.) | Single-electrode gas sensor based on oxidised titanium, procedure for its fabrication, sensor device and multi-sensor line based on its |
-
2019
- 2019-09-27 CN CN201910924503.0A patent/CN110618424B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120126511A (en) * | 2011-05-12 | 2012-11-21 | 국방과학연구소 | Threat evaluation system and method against antiair target and computer-readerable storage medium having a program recorded thereon where the program is to carry out its method |
| DE102015104212A1 (en) * | 2015-03-20 | 2016-09-22 | Valeo Schalter Und Sensoren Gmbh | Lens device for an optoelectronic sensor of a motor vehicle with fastening device, optoelectronic sensor, motor vehicle and method |
| CN105743017A (en) * | 2016-04-19 | 2016-07-06 | 平玉兰 | Unmanned aerial vehicle inspection ground measurement and control station and transportation safeguard system used for power transmission line |
| CN105892489A (en) * | 2016-05-24 | 2016-08-24 | 国网山东省电力公司电力科学研究院 | Multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and control method |
| CN107561509A (en) * | 2017-08-28 | 2018-01-09 | 电子科技大学 | A kind of airborne millimetre-wave radar electric power line detecting method |
| CN107742093A (en) * | 2017-09-01 | 2018-02-27 | 国网山东省电力公司电力科学研究院 | A kind of infrared image power equipment component real-time detection method, server and system |
| CN107729808A (en) * | 2017-09-08 | 2018-02-23 | 国网山东省电力公司电力科学研究院 | A kind of image intelligent acquisition system and method for power transmission line unmanned machine inspection |
| CN108061901A (en) * | 2017-12-01 | 2018-05-22 | 国家电网公司 | The method that 3D electric power line models are rebuild based on airborne laser radar point cloud data |
| CN108319982A (en) * | 2018-02-06 | 2018-07-24 | 贵州电网有限责任公司 | A kind of power-line patrolling unmanned plane Fusion obstacle detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110618424A (en) | 2019-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107161141B (en) | Unmanned automobile system and automobile | |
| CN206691107U (en) | Pilotless automobile system and automobile | |
| KR20220155559A (en) | Autonomous navigation method using image segmentation | |
| CN108469817B (en) | Unmanned ship obstacle avoidance control system based on FPGA and information fusion | |
| CN102707724A (en) | Visual localization and obstacle avoidance method and system for unmanned plane | |
| CN111551959B (en) | Airplane wake vortex identification method and device, readable medium and electronic equipment | |
| CN110618424B (en) | Remote high-voltage line discovery method based on multi-sensor fusion | |
| CN113820714B (en) | Dust fog weather road environment sensing system based on multi-sensor fusion | |
| CN104590573A (en) | Barrier avoiding system and method for helicopter | |
| CN113885062A (en) | Data acquisition and fusion equipment, method and system based on V2X | |
| KR102466804B1 (en) | Autonomous navigation method using image segmentation | |
| US20220215197A1 (en) | Data processing method and apparatus, chip system, and medium | |
| Zsedrovits et al. | Visual detection and implementation aspects of a UAV see and avoid system | |
| CN110825099B (en) | Inspection unmanned aerial vehicle control method and device for smart road | |
| CN113485450A (en) | Unmanned aerial vehicle keeps away barrier system based on computer vision | |
| CN113759947B (en) | Airborne flight obstacle avoidance assisting method, device and system based on laser radar | |
| CN110568437A (en) | Precise environment modeling method based on radar assistance | |
| CN109885091B (en) | Unmanned aerial vehicle autonomous flight control method and system | |
| Wang et al. | Building smart city drone for graffiti detection and clean-up | |
| CN112306078A (en) | Method and system for unmanned aerial vehicle to automatically avoid obstacle conducting wire | |
| CN204297108U (en) | Helicopter obstacle avoidance system | |
| EP3989034B1 (en) | Automatic safe-landing-site selection for unmanned aerial systems | |
| US20230073120A1 (en) | Method for Controlling an Unmanned Aerial Vehicle for an Inspection Flight to Inspect an Object and Inspection Unmanned Aerial Vehicle | |
| CN116243725A (en) | Substation unmanned aerial vehicle inspection method and system based on visual navigation | |
| CN117472081B (en) | Unmanned aerial vehicle obstacle avoidance method based on perception constraint |
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 |