CN118089743A - Unmanned aerial vehicle intelligent navigation and camera system special for converter station - Google Patents
Unmanned aerial vehicle intelligent navigation and camera system special for converter station Download PDFInfo
- Publication number
- CN118089743A CN118089743A CN202410496268.2A CN202410496268A CN118089743A CN 118089743 A CN118089743 A CN 118089743A CN 202410496268 A CN202410496268 A CN 202410496268A CN 118089743 A CN118089743 A CN 118089743A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- point
- real
- path
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 claims abstract description 48
- 238000007689 inspection Methods 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 23
- 230000000007 visual effect Effects 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims 4
- 230000004807 localization Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000009827 uniform distribution Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The invention discloses an unmanned aerial vehicle intelligent navigation and camera system special for a convertor station, which belongs to the technical field of navigation and comprises the following components: the electric quantity monitoring module monitors real-time electric quantity of the unmanned aerial vehicle; the detection point database stores detection point information of detection points of the converter station; the detection point information includes: position information and priority, wherein the priority is N level; the real-time positioning module acquires the comprehensive position of the unmanned aerial vehicle in real time; and when the real-time electric quantity is smaller than a first preset electric quantity threshold value, the path planning module re-plans the routing inspection path according to the detection point information and the comprehensive position of the unmanned aerial vehicle. According to the invention, through monitoring the electric quantity in real time, when the set threshold value is reached, the inspection path is automatically generated again according to the priority of the inspection point and the position of the unmanned aerial vehicle, the inspection point is maximized, and meanwhile, the situation that the electric quantity is too low to safely return to the navigation is avoided.
Description
Technical Field
The invention relates to the technical field of navigation, in particular to an intelligent navigation and shooting system of a special unmanned aerial vehicle for a converter station.
Background
The converter station is used as a key facility in a high-voltage direct-current transmission system and is responsible for converting alternating current into direct current or vice versa, so as to realize long-distance and large-capacity electric energy transmission. However, the converter station equipment is complex and environment-specific, and has higher difficulty and safety risk in daily inspection, fault detection, state monitoring and other works, so that with the development of technology, unmanned aerial vehicles are basically adopted for inspection.
In the conventional art, after the inspection path is set, the unmanned aerial vehicle of the converter station inspects according to the inspection path through the GPS navigation system, however, the inspection is carried out according to the inspection path in such a way as to consider the electric quantity problem of the unmanned aerial vehicle, under the condition that the electric quantity is not enough due to the charging of the unmanned aerial vehicle, the inspection cannot be completed according to the original set path, the problem that the safety return cannot be carried out due to the insufficient electric quantity exists, and at this time, the unmanned aerial vehicle is usually controlled manually by a worker, so that the optimal inspection path cannot be screened out to enable the unmanned aerial vehicle to detect important detection points in time, and the detection efficiency is seriously reduced.
In summary, in order to solve the above-mentioned problems, the present invention provides an intelligent navigation and camera system of an unmanned aerial vehicle dedicated for a converter station, wherein the unmanned aerial vehicle can automatically generate a patrol path according to its own position and in-station detection point information when the electric quantity is lower than a set threshold.
Disclosure of Invention
The invention provides an unmanned aerial vehicle intelligent navigation and camera system special for a converter station, which solves the technical problems in the prior art and comprises the following components:
The electric quantity monitoring module is used for monitoring the real-time electric quantity of the unmanned aerial vehicle;
the detection point database is used for storing detection point information of each detection point of the converter station; the detection point information includes: position information and priority, wherein the priority is N level;
The real-time positioning module is used for acquiring the comprehensive position of the unmanned aerial vehicle in real time;
and the path planning module is used for re-planning the routing inspection path according to the detection point information and the comprehensive position of the unmanned aerial vehicle when the real-time electric quantity is smaller than a first preset electric quantity threshold value.
Further, the path planning module re-plans the inspection path, and the specific steps include:
s11, screening a to-be-detected point from the detection points, and acquiring to-be-detected points passing through a linear path from the current comprehensive position of the unmanned aerial vehicle to each target to-be-detected point, wherein the to-be-detected point is a detection point which is not yet detected;
S12, acquiring an actual path from the current comprehensive position of the unmanned aerial vehicle to each target to-be-measured point;
S13, predicting the total power consumption corresponding to the drop point of the unmanned aerial vehicle through each actual path by means of a trained prediction model, and taking the corresponding actual path as a feasible actual path if the difference value between the real-time power consumption and the total power consumption is greater than or equal to a second preset power consumption threshold value;
S14, calculating the priority value of each feasible actual path ，/>Screening out the feasible actual paths with the largest priority value, counting the number, taking the feasible actual paths as the re-planned routing inspection paths if the number is 1, and selecting the feasible actual paths with the smallest corresponding total power consumption from the feasible actual paths as the re-planned routing inspection paths if the number is more than 1; the number of the to-be-measured points with the nth priority included in the feasible actual path,/> Is the weight coefficient of the nth priority.
Further, the obtaining the point to be measured passed by the linear path from the current comprehensive position of the unmanned aerial vehicle to each target point to be measured specifically includes:
If the vertical distance from the point to be measured to the linear path is smaller than or equal to a preset threshold value, judging that the corresponding linear path passes through the point to be measured.
Further, the obtaining the actual path from the current comprehensive position of the unmanned aerial vehicle to each target to-be-measured point specifically includes:
And taking the path formed by sequentially connecting the current comprehensive position of the unmanned aerial vehicle, the to-be-measured point passing through in the corresponding straight path and the corresponding target to-be-measured point as the actual path from the current comprehensive position of the unmanned aerial vehicle to the corresponding target to-be-measured point.
Further, the real-time positioning module includes:
the visual positioning module is used for acquiring a first estimated position of the unmanned aerial vehicle in real time ；
The wireless signal positioning module is used for acquiring a second estimated position of the unmanned aerial vehicle in real time；
And the comprehensive positioning module is used for fusing the first estimated position and the second estimated position through an extended Kalman filtering algorithm to obtain a comprehensive position.
Further, the visual positioning module comprises:
The image acquisition module is used for continuously acquiring images of the surrounding environment of the unmanned aerial vehicle;
The feature point extraction module is used for extracting feature points of each frame of image;
The characteristic point matching module is used for matching the characteristic points of every two adjacent frame images to obtain reliable characteristic point pairs;
a first calculation module for obtaining a first estimated position by using SVD algorithm through reliable feature points 。
Further, the feature point extracting module extracts feature points of each frame of image, and the method comprises the following steps:
detecting characteristic points to obtain characteristic points of each frame of image;
feature point descriptions, a descriptor is generated for each detected feature point.
Further, the feature point detection adopts a SIFT algorithm, and the feature point description adopts an ORB algorithm.
Further, the wireless signal positioning module includes:
The receiving module is used for receiving Bluetooth signals of a plurality of Bluetooth beacons which are pre-deployed in the converter station, recording RSSI values of the Bluetooth signals and forming an RSSI value vector as a real-time fingerprint;
The fingerprint database is used for storing fingerprint samples of each Bluetooth beacon, and each fingerprint sample comprises a plurality of pre-measured RSSI values and corresponding position information;
A second calculation module for calculating a second estimated position of the unmanned aerial vehicle by matching the real-time fingerprint with the fingerprint database 。
Further, the second calculation module calculates a second estimated position of the unmanned aerial vehicleThe method specifically comprises the following steps:
Calculating the horse-type distance between the real-time fingerprint and each fingerprint sample in the fingerprint database by using a KNN algorithm, calculating the second estimated position of the unmanned aerial vehicle by adopting a weighted average method according to the position information of the fingerprint sample which is smaller than or equal to a second preset distance threshold value 。
Compared with the prior art, the invention has the beneficial effects that:
According to the invention, through monitoring the electric quantity in real time, when the set threshold value is reached, the inspection path is automatically generated again according to the priority of the inspection point and the position of the unmanned aerial vehicle, so that the inspection point is maximized, and meanwhile, the situation that the electric quantity is too low to safely return to the navigation is avoided;
According to the invention, the SIFT algorithm is adopted to detect the characteristic points, so that the SIFT algorithm can adapt to the size change of the image when the same characteristic is detected under different scales, the scale invariance is ensured, and meanwhile, a main direction can be allocated to each characteristic point, so that the SIFT algorithm has robustness to the image rotation, and the rotation invariance is ensured;
According to the invention, the ORB algorithm is selected to describe the feature points, the calculation efficiency is high, the memory occupation is small, and simultaneously 256 pairs of pixel points are selected in a random and uniform distribution manner, so that the independence between generated binary bits is improved, the robustness of the descriptor is improved, the influence of noise and mismatching is reduced, and the accuracy of a visual positioning result is improved.
According to the invention, by taking the electric quantity into consideration and simultaneously taking the priority of each detection point into consideration through the path planning module and matching with the weight coefficient to calculate the priority value of each feasible actual path, the unmanned aerial vehicle can safely return to the navigation with enough electric quantity, the quantity of detection points to be detected can be maximized while the important detection points are detected, and the detection efficiency is improved while the safety is ensured.
Drawings
Fig. 1 is a block diagram of a system for intelligent navigation and camera shooting of a special-purpose unmanned aerial vehicle for a converter station;
FIG. 2 is a block diagram of the real-time positioning module of the intelligent navigation and camera system of the special-purpose unmanned aerial vehicle for the converter station of the present invention;
Fig. 3 is a block diagram of the visual positioning module of the intelligent navigation and camera system of the special-purpose unmanned aerial vehicle for the converter station of the present invention;
fig. 4 is a block diagram of the wireless signal positioning module of the intelligent navigation and camera system of the special-purpose unmanned aerial vehicle for the converter station.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, the present invention provides a special unmanned aerial vehicle intelligent navigation and camera system for a converter station, comprising: the system comprises an electric quantity monitoring module, a detection point database, a real-time positioning module, a path planning module and a central processing unit;
and the electric quantity monitoring module, the detection point database, the real-time positioning module and the path planning module are all in communication connection with the central processing unit.
And the electric quantity monitoring module is used for monitoring the real-time electric quantity of the unmanned aerial vehicle.
The electric quantity monitoring module comprises: the device comprises a battery sensor, a data acquisition processing module and an electric quantity calculating module.
The battery sensor is used for collecting battery data of the unmanned aerial vehicle battery in real time, and the battery data comprise key parameters such as voltage, current, temperature and the like.
The data acquisition processing module is used for receiving the battery data from the battery sensor and preprocessing, wherein the preprocessing comprises filtering, denoising and the like.
And the electric quantity calculation module is used for calculating the real-time electric quantity of the unmanned aerial vehicle according to the preprocessed battery data.
And the detection point database is used for storing the detection point information of each detection point of the converter station.
The detection point information includes: location information and priority, the priority being N-level.
And the real-time positioning module is used for acquiring the comprehensive position of the unmanned aerial vehicle in real time.
Referring to fig. 2, the real-time positioning module includes: the system comprises a visual positioning module, a wireless signal positioning module and a comprehensive positioning module.
The visual positioning module is used for acquiring a first estimated position of the unmanned aerial vehicle in real time。
Referring to fig. 3, the visual positioning module includes: the device comprises an image acquisition module, a characteristic point extraction module, a characteristic point matching module and a first calculation module.
The image acquisition module is used for continuously acquiring images of the surrounding environment of the unmanned aerial vehicle.
The characteristic point extraction module is used for extracting characteristic points of each frame of image;
the feature point extraction module extracts feature points, wherein the feature point extraction module comprises a feature point detection step and a feature point description step;
the feature point detection step can adopt a SIFT algorithm (Scale-INVARIANT FEATURE TRANSFORM) to detect the feature points, and comprises the following specific steps:
Detecting scale space extremum, constructing a Gaussian differential pyramid to simulate the representation of an image under different scales, and finding out candidate feature points by comparing pixel intensities of adjacent scale layers;
positioning the feature points, and accurately positioning the candidate feature points by using an accurate sub-pixel level interpolation method;
and eliminating the feature points, namely eliminating non-important candidate feature points through main direction distribution and contrast threshold values.
The invention adopts SIFT algorithm to detect the characteristic points, and has the following technical effects:
1. The same features are detected under different scales, so that the method is suitable for the size change of images and ensures the scale invariance;
2. Each feature point is distributed with a main direction, so that the feature points have robustness to image rotation, and rotation invariance is ensured;
3. The method has better robustness to illumination variation, visual angle variation and partial shielding.
A feature point description step, namely generating a descriptor for each detected feature point, wherein the descriptor can uniquely and stably characterize local surrounding features of the feature point, is not influenced by factors such as illumination, rotation, scale transformation and the like, and specifically, an ORB algorithm (Oriented FAST and Rotated BRIEF) can be selected for feature point description, and the specific steps comprise:
Sampling a neighborhood of the feature points, and selecting an image area with a fixed size around the feature points;
And generating BRIEF descriptors, randomly selecting 256 pairs of pixel points, and comparing gray values of the pixel points to form a binary character string, wherein the process rotates the main direction of the feature points, so that the rotation invariance of the descriptors is ensured.
The invention selects ORB algorithm to describe the characteristic points, and has the following technical effects:
1. The calculation efficiency is high, the generation speed of the 256-bit BRIEF descriptor is high, the calculation complexity is low, only the gray value comparison of 256 pixel point pairs is needed, complex mathematical operation or histogram statistics is not needed, and the method is suitable for processing the visual positioning of the unmanned aerial vehicle in real time;
2. The memory occupation is small, the binary descriptor is very compact, the BRIEF descriptor with 256 bits is low in storage requirement space;
3. 256 pairs of pixel points are selected in a random and uniform distribution mode, independence among generated binary bits is improved, robustness of descriptors is improved, and noise and influence of subsequent mismatching are reduced.
The characteristic point matching module is used for matching the characteristic points of every two adjacent frame images to obtain reliable characteristic point pairs;
The method comprises the following specific steps:
preliminary matching, namely calculating the Hamming distance between descriptors corresponding to the feature points of every two adjacent frame images, and forming a preliminary matching feature point pair if the Hamming distance is smaller than a first preset distance threshold;
and (3) performing geometric consistency check, removing the mismatching characteristic point pairs, and outputting final matching characteristic point pairs.
In the scheme of the invention, the geometric consistency check is specifically as follows:
Selecting at least 8 pairs of preliminary matching characteristic point pairs from every two adjacent frame images, and calculating a basic matrix F by an eight-point method or a RANSAC algorithm;
Calculating the polar line L of q1 in the next adjacent frame image in each preliminary matching feature point pair (q 1, q 2), l=q2×fq1;
the dot product s of q2 and L is calculated, If the |s| is smaller than or equal to a preset threshold value, judging that q2 is located on the polar line of q1, wherein the corresponding primary matching characteristic point pair is a reliable characteristic point pair, and if the |s| is larger than the preset threshold value, classifying the corresponding primary matching characteristic point pair as mismatching and rejecting;
wherein q1 is a feature point, q2 is a feature point of an image of a next adjacent frame of the image where q1 is located, and T represents a vector transposition operation.
The first calculation module is used for obtaining a first estimated position through reliable feature points by utilizing SVD algorithm；
The method comprises the following specific steps:
Calculating a corresponding second basic matrix through reliable characteristic point pairs between every two adjacent frame images;
Decomposing each second basic matrix through an SVD algorithm to obtain corresponding translation vectors;
accumulating each translation vector at the initial position of the unmanned aerial vehicle to obtain a first estimated position 。
The wireless signal positioning module is used for acquiring a second estimated position of the unmanned aerial vehicle in real time。
Referring to fig. 4, the wireless signal positioning module includes: the fingerprint database comprises a receiving module, a fingerprint database and a second calculating module.
The receiving module is used for receiving Bluetooth signals of a plurality of Bluetooth beacons which are arranged in the converter station in advance, recording RSSI values of the Bluetooth signals and forming an RSSI value vector as a real-time fingerprint.
The Bluetooth beacons are deployed at the centers of detection points and open areas.
The fingerprint database is used for storing fingerprint samples of each Bluetooth beacon, and each fingerprint sample comprises a plurality of pre-measured RSSI values and corresponding position information.
The second calculation module is used for calculating a second estimated position of the unmanned aerial vehicle through matching of the real-time fingerprint and the fingerprint databaseThe method specifically comprises the following steps:
Calculating the horse-type distance between the real-time fingerprint and each fingerprint sample in the fingerprint database by using a KNN algorithm, calculating the second estimated position of the unmanned aerial vehicle by adopting a weighted average method according to the position information of the fingerprint sample which is smaller than or equal to a second preset distance threshold value 。
The comprehensive positioning module is used for fusing the first estimated position and the second estimated position through an extended Kalman filtering algorithm to obtain a comprehensive position;
The method comprises the following specific steps:
establishing a visual positioning observation model And wireless signal positioning observation model/>，/>，; T represents the current time,/>And/>Nonlinear observation functions for visual localization and wireless signal localization, respectively,/>And/>Observing noise for visual positioning and wireless signal positioning respectively;
Predicting a comprehensive position at a current time ，/>；/>Is a state transfer function,/>To control input vector,/>Is system noise;
Predicting the integrated covariance of the current moment ，/>；/>Is a state transition matrix,/>A process noise covariance matrix;
Computing Kalman gain for visual localization at current time And Kalman gain for wireless signal localization/>，，/>；/>And/>Jacobian approximation of visual localization observation model and wireless signal localization observation model, respectively,/>And/>The observed noise covariance matrixes of the visual positioning observation model and the wireless signal positioning observation model are respectively;
Updating visual positioning locations And visual localization covariance/>，/>，；/>Is a unit matrix;
Updating integrated location And comprehensive covariance/>，/>，。
In the inspection of the unmanned aerial vehicle of the convertor station, a large number of large-scale power equipment and metal structures are usually arranged in the convertor station, so that GPS signals can be seriously attenuated;
Meanwhile, the visual positioning and the wireless signal positioning are respectively dependent on different physical principles and environmental conditions, the accuracy of the visual positioning and the wireless signal positioning can be influenced by factors such as illumination change, shielding, multipath effect and the like, the two factors are fused, when the performance of a single sensor is limited, the data of another sensor can be used for compensating, the robustness and the reliability of the whole positioning system are improved, the characteristic of the visual positioning and the characteristic of the wireless signal positioning can be combined by an extended Kalman filtering algorithm, and the real-time position with higher precision and global consistency is output;
The extended Kalman filtering algorithm can adaptively adjust the filtering weight according to covariance of the observed data and the observed model, adapt to precision changes of different sensors in different time and different environments, and ensure accuracy of fusion results.
And the path planning module is used for re-planning the routing inspection path according to the detection point information and the comprehensive position of the unmanned aerial vehicle when the real-time electric quantity is smaller than a first preset electric quantity threshold value.
The method comprises the following specific steps:
S11, screening a to-be-detected point from the detection points, and acquiring to-be-detected points which are passed by the linear paths from the current comprehensive position of the unmanned aerial vehicle to each target to-be-detected point, wherein the to-be-detected point is a detection point which is not yet detected;
S12, acquiring an actual path from the current comprehensive position of the unmanned aerial vehicle to each target to-be-measured point;
s13, predicting the total power consumption corresponding to the falling point of the unmanned aerial vehicle after passing through each actual path through a trained prediction model, and taking the corresponding actual path as a feasible actual path if the difference value between the real-time power consumption and the total power consumption is greater than or equal to a second preset power consumption threshold value;
S14, calculating the priority value of each feasible actual path ，/>Screening out the feasible actual paths with the largest priority value, counting the number, taking the feasible actual paths as the re-planned routing inspection paths if the number is 1, and selecting the feasible actual paths with the smallest corresponding total power consumption from the feasible actual paths as the re-planned routing inspection paths if the number is more than 1; /(I)The number of the to-be-measured points with the nth priority included in the feasible actual path,/>Is the weight coefficient of the nth priority.
In step S11, a point to be measured, through which a linear path from a current comprehensive position of the unmanned aerial vehicle to each target point to be measured passes, is obtained, specifically:
If the vertical distance from the point to be measured to the linear path is smaller than or equal to a preset threshold value, judging that the corresponding linear path passes through the point to be measured.
The step S12 specifically includes:
And taking the path formed by sequentially connecting the current comprehensive position of the unmanned aerial vehicle, the to-be-measured point passing through in the corresponding straight path and the corresponding target to-be-measured point as the actual path from the current comprehensive position of the unmanned aerial vehicle to the corresponding target to-be-measured point.
According to the invention, by taking the electric quantity into consideration and simultaneously taking the priority of each detection point into consideration through the path planning module, and matching with the weight coefficient to calculate the priority value of each feasible actual path, under the condition of ensuring enough electric quantity return, the feasible actual path capable of maximally detecting the to-be-detected point is screened, so that the unmanned aerial vehicle can safely return enough electric quantity, the number of the to-be-detected points can be maximally increased while the important detection points are detected, and the detection efficiency is improved while the safety is ensured.
The invention has the beneficial effects that:
According to the invention, through monitoring the electric quantity in real time, when the set threshold value is reached, the inspection path is automatically generated again according to the priority of the inspection point and the position of the unmanned aerial vehicle, so that the inspection point is maximized, and meanwhile, the situation that the electric quantity is too low to safely return to the navigation is avoided;
According to the invention, the SIFT algorithm is adopted to detect the characteristic points, so that the SIFT algorithm can adapt to the size change of the image when the same characteristic is detected under different scales, the scale invariance is ensured, and meanwhile, a main direction can be allocated to each characteristic point, so that the SIFT algorithm has robustness to the image rotation, and the rotation invariance is ensured;
According to the invention, the ORB algorithm is selected to describe the feature points, the calculation efficiency is high, the memory occupation is small, and simultaneously 256 pairs of pixel points are selected in a random and uniform distribution manner, so that the independence between generated binary bits is improved, the robustness of the descriptor is improved, the influence of noise and mismatching is reduced, and the accuracy of a visual positioning result is improved.
According to the invention, by taking the electric quantity into consideration and simultaneously taking the priority of each detection point into consideration through the path planning module and matching with the weight coefficient to calculate the priority value of each feasible actual path, the unmanned aerial vehicle can safely return to the navigation with enough electric quantity, the quantity of detection points to be detected can be maximized while the important detection points are detected, and the detection efficiency is improved while the safety is ensured.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM, random access memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.
Claims (9)
1. An unmanned aerial vehicle intelligent navigation and camera system special for a converter station is characterized by comprising:
The electric quantity monitoring module is used for monitoring the real-time electric quantity of the unmanned aerial vehicle;
the detection point database is used for storing detection point information of each detection point of the converter station; the detection point information includes: position information and priority, wherein the priority is N level;
The real-time positioning module is used for acquiring the comprehensive position of the unmanned aerial vehicle in real time;
The path planning module is used for re-planning the routing inspection path according to the detection point information and the comprehensive position of the unmanned aerial vehicle when the real-time electric quantity is smaller than a first preset electric quantity threshold value, and specifically comprises the following steps:
s11, screening a to-be-detected point from the detection points, and acquiring to-be-detected points passing through a linear path from the current comprehensive position of the unmanned aerial vehicle to each target to-be-detected point, wherein the to-be-detected point is a detection point which is not yet detected;
S12, acquiring an actual path from the current comprehensive position of the unmanned aerial vehicle to each target to-be-measured point;
S13, predicting the total power consumption corresponding to the drop point of the unmanned aerial vehicle through each actual path by means of a trained prediction model, and taking the corresponding actual path as a feasible actual path if the difference value between the real-time power consumption and the total power consumption is greater than or equal to a second preset power consumption threshold value;
S14, calculating the priority value of each feasible actual path ，/>Screening out the feasible actual paths with the largest priority value, counting the number, taking the feasible actual paths as the re-planned routing inspection paths if the number is 1, and selecting the feasible actual paths with the smallest corresponding total power consumption from the feasible actual paths as the re-planned routing inspection paths if the number is more than 1; /(I)The number of the to-be-measured points with the nth priority included in the feasible actual path,/>Is the weight coefficient of the nth priority.
2. The intelligent navigation and imaging system of a special unmanned aerial vehicle for a converter station according to claim 1, wherein the point to be measured, through which the linear path from the current comprehensive position of the unmanned aerial vehicle to each target point to be measured passes, is specifically:
If the vertical distance from the point to be measured to the linear path is smaller than or equal to a preset threshold value, judging that the corresponding linear path passes through the point to be measured.
3. The intelligent navigation and imaging system of the special unmanned aerial vehicle for the converter station according to claim 1, wherein the actual path from the current comprehensive position of the unmanned aerial vehicle to each target to-be-measured point is obtained specifically:
And taking the path formed by sequentially connecting the current comprehensive position of the unmanned aerial vehicle, the to-be-measured point passing through in the corresponding straight path and the corresponding target to-be-measured point as the actual path from the current comprehensive position of the unmanned aerial vehicle to the corresponding target to-be-measured point.
4. The system of claim 1, wherein the real-time positioning module comprises:
the visual positioning module is used for acquiring a first estimated position of the unmanned aerial vehicle in real time ；
The wireless signal positioning module is used for acquiring a second estimated position of the unmanned aerial vehicle in real time；
And the comprehensive positioning module is used for fusing the first estimated position and the second estimated position through an extended Kalman filtering algorithm to obtain a comprehensive position.
5. The system for intelligent navigation and camera shooting of a converter station specific unmanned aerial vehicle of claim 4, wherein the visual positioning module comprises:
The image acquisition module is used for continuously acquiring images of the surrounding environment of the unmanned aerial vehicle;
The feature point extraction module is used for extracting feature points of each frame of image;
The characteristic point matching module is used for matching the characteristic points of every two adjacent frame images to obtain reliable characteristic point pairs;
a first calculation module for obtaining a first estimated position by using SVD algorithm through reliable feature points 。
6. The intelligent navigation and imaging system of a converter station dedicated unmanned aerial vehicle according to claim 5, wherein the feature point extraction module extracts feature points of each frame of image, comprising the steps of:
detecting characteristic points to obtain characteristic points of each frame of image;
feature point descriptions, a descriptor is generated for each detected feature point.
7. The intelligent navigation and imaging system of a converter station specific unmanned aerial vehicle of claim 6, wherein the feature point detection uses SIFT algorithm and the feature point description uses ORB algorithm.
8. The system of claim 4, wherein the wireless signal positioning module comprises:
The receiving module is used for receiving Bluetooth signals of a plurality of Bluetooth beacons which are pre-deployed in the converter station, recording RSSI values of the Bluetooth signals and forming an RSSI value vector as a real-time fingerprint;
The fingerprint database is used for storing fingerprint samples of each Bluetooth beacon, and each fingerprint sample comprises a plurality of pre-measured RSSI values and corresponding position information;
A second calculation module for calculating a second estimated position of the unmanned aerial vehicle by matching the real-time fingerprint with the fingerprint database 。
9. The intelligent navigation and camera system of a converter station specific unmanned aerial vehicle of claim 8, wherein the second calculation module calculates a second estimated position of the unmanned aerial vehicleThe method specifically comprises the following steps:
Calculating the horse-type distance between the real-time fingerprint and each fingerprint sample in the fingerprint database by using a KNN algorithm, calculating the second estimated position of the unmanned aerial vehicle by adopting a weighted average method according to the position information of the fingerprint sample which is smaller than or equal to a second preset distance threshold value 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410496268.2A CN118089743B (en) | 2024-04-24 | 2024-04-24 | Unmanned aerial vehicle intelligent navigation and camera system special for converter station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410496268.2A CN118089743B (en) | 2024-04-24 | 2024-04-24 | Unmanned aerial vehicle intelligent navigation and camera system special for converter station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118089743A true CN118089743A (en) | 2024-05-28 |
| CN118089743B CN118089743B (en) | 2024-07-12 |
Family
ID=91150400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410496268.2A Active CN118089743B (en) | 2024-04-24 | 2024-04-24 | Unmanned aerial vehicle intelligent navigation and camera system special for converter station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118089743B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104859643A (en) * | 2014-02-24 | 2015-08-26 | 丰田自动车株式会社 | Travel support device, travel support method and drive support system |
| CN109709983A (en) * | 2019-01-09 | 2019-05-03 | 南京邮电大学 | A kind of logistics unmanned plane makes a return voyage safely control method |
| JP2020041910A (en) * | 2018-09-11 | 2020-03-19 | 株式会社東芝 | Route search system using drone, method for searching for route in the same, route search device, method for searching for route, and program |
| WO2022036980A1 (en) * | 2020-08-17 | 2022-02-24 | 浙江商汤科技开发有限公司 | Pose determination method and apparatus, electronic device, storage medium, and program |
| CN115145311A (en) * | 2022-07-27 | 2022-10-04 | 广东电网有限责任公司 | Routing inspection path planning method, device, equipment and storage medium |
-
2024
- 2024-04-24 CN CN202410496268.2A patent/CN118089743B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104859643A (en) * | 2014-02-24 | 2015-08-26 | 丰田自动车株式会社 | Travel support device, travel support method and drive support system |
| JP2020041910A (en) * | 2018-09-11 | 2020-03-19 | 株式会社東芝 | Route search system using drone, method for searching for route in the same, route search device, method for searching for route, and program |
| CN109709983A (en) * | 2019-01-09 | 2019-05-03 | 南京邮电大学 | A kind of logistics unmanned plane makes a return voyage safely control method |
| WO2022036980A1 (en) * | 2020-08-17 | 2022-02-24 | 浙江商汤科技开发有限公司 | Pose determination method and apparatus, electronic device, storage medium, and program |
| CN115145311A (en) * | 2022-07-27 | 2022-10-04 | 广东电网有限责任公司 | Routing inspection path planning method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118089743B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108388927B (en) | Small sample polarization SAR terrain classification method based on deep convolution twin network | |
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| CN106356757B (en) | A kind of power circuit unmanned plane method for inspecting based on human-eye visual characteristic | |
| CN108564085B (en) | Method for automatically reading of pointer type instrument | |
| Maniat et al. | Deep learning-based visual crack detection using Google Street View images | |
| CN114564982B (en) | Automatic identification method for radar signal modulation type | |
| CN109544501A (en) | A kind of transmission facility defect inspection method based on unmanned plane multi-source image characteristic matching | |
| CN110197185B (en) | Method and system for monitoring space under bridge based on scale invariant feature transform algorithm | |
| CN117076928A (en) | Bridge health state monitoring method, device and system and electronic equipment | |
| CN103679740A (en) | ROI (Region of Interest) extraction method of ground target of unmanned aerial vehicle | |
| CN116152678A (en) | Marine disaster-bearing body identification method based on twin neural network under small sample condition | |
| CN117156442A (en) | Cloud data security protection method and system based on 5G network | |
| CN117541534A (en) | Power transmission line inspection method based on unmanned plane and CNN-BiLSTM model | |
| CN116310852A (en) | Double-time-phase remote sensing image unsupervised classification and change detection method and system | |
| CN111462310A (en) | Bolt defect space positioning method based on multi-view geometry | |
| US11727665B2 (en) | Unmanned aircraft system (UAS) detection and assessment via temporal intensity aliasing | |
| Cromwell et al. | Lidar cloud detection with fully convolutional networks | |
| CN117475327A (en) | Multi-target detection positioning method and system based on remote sensing image in city | |
| CN118089743B (en) | Unmanned aerial vehicle intelligent navigation and camera system special for converter station | |
| CN109934147B (en) | Target detection method, system and device based on deep neural network | |
| CN109558771B (en) | Behavior state identification method, device and equipment of marine ship and storage medium | |
| Ebert-Uphoff et al. | Evaluation, tuning and interpretation of neural networks for meteorological applications | |
| CN114782822A (en) | Method and device for detecting state of power equipment, electronic equipment and storage medium | |
| CN111368823B (en) | Pointer type instrument reading identification method and device | |
| Wan et al. | Squeeze excitation densely connected residual convolutional networks for specific emitter identification based on measured signals |
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 |