CN112085036A - Region identification method, device, equipment and medium - Google Patents
Region identification method, device, equipment and medium Download PDFInfo
- Publication number
- CN112085036A CN112085036A CN202010981808.8A CN202010981808A CN112085036A CN 112085036 A CN112085036 A CN 112085036A CN 202010981808 A CN202010981808 A CN 202010981808A CN 112085036 A CN112085036 A CN 112085036A
- Authority
- CN
- China
- Prior art keywords
- image
- tree
- felling
- identified
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000004888 barrier function Effects 0.000 claims abstract description 167
- 238000004590 computer program Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 5
- 238000005259 measurement Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013138 pruning Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000009966 trimming Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
- G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a region identification method, a device, equipment and a medium. The method comprises the following steps: respectively acquiring an RGB image and a multispectral image of a complete line channel to be identified before and after the tree obstacle is felled; obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling; obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut; and inputting the tree obstacle area image before felling and the tree obstacle area image after felling into a trained area recognition model to obtain a tree obstacle felling area image. According to the technical scheme of the embodiment of the invention, the problem that the tree barrier cutting area is low in efficiency when being manually measured is solved, the automatic extraction of the tree barrier cutting area is realized, and the effect of improving the tree cutting area obtaining efficiency is improved.
Description
Technical Field
Embodiments of the present invention relate to image processing technologies, and in particular, to a method, an apparatus, a device, and a medium for region identification.
Background
The measurement of the safe distance of the conductor by trees in the corridor of the power transmission line and the control of felling and pruning are important operation and maintenance work of the power transmission line. Trees in the power transmission line corridor can periodically grow to be close to the conducting wire in the daily growth process, and if the distance is less than the safe distance required by operation and maintenance, the electricity is discharged from the electric wire to the trees to cause line failure shutdown and forest fire.
If the distance between the trees and the conducting wires of the power transmission line does not meet the safety requirement, periodic trimming and cutting are arranged, so that the operation and maintenance of the power transmission line each year involve a large amount of tree trimming and cutting engineering quantity calculation, the former supervision and the former Party A represent that the measurement of the tree trimming and cutting area is carried out on the cutting and cutting site in a manual measuring mode, and the efficiency is low.
Disclosure of Invention
The embodiment of the invention provides a region identification method, a device, equipment and a medium, which are used for realizing automatic extraction of a tree felling region, saving manpower and improving the tree felling region acquisition efficiency.
In a first aspect, an embodiment of the present invention provides a method for identifying an area, where the method includes:
respectively acquiring an RGB image and a multispectral image of a complete line channel to be identified before and after the tree obstacle is felled;
obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling;
obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut;
and inputting the tree obstacle area image before felling and the tree obstacle area image after felling into a trained area recognition model to obtain a tree obstacle felling area image.
In a second aspect, an embodiment of the present invention further provides an area identification apparatus, where the apparatus includes:
the image acquisition module is used for respectively acquiring an RGB image and a multispectral image of a complete line channel to be identified before and after the tree barrier is felled;
the pre-felling tree barrier area image acquisition module is used for acquiring a pre-felling tree barrier area image according to an RGB image of a complete to-be-identified line channel before tree barrier felling and a multispectral image of the complete to-be-identified line channel before tree barrier felling;
the device comprises a felled tree barrier area image acquisition module, a tree barrier identification module and a tree barrier identification module, wherein the felled tree barrier area image acquisition module is used for acquiring a felled tree barrier area image according to an RGB image of a complete to-be-identified line channel after the tree barrier is felled and a multispectral image of the complete to-be-identified line channel after the tree barrier is felled;
and the tree barrier felling area image acquisition module is used for inputting the tree barrier area image before felling and the tree barrier area image after felling into a trained area recognition model to obtain a tree barrier felling area image.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a region identification method as provided by any of the embodiments of the invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the area identification method as provided in any embodiment of the present invention.
The method comprises the steps of respectively obtaining an RGB image and a multispectral image of a complete line channel to be identified before and after the tree obstacle is felled; obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling; obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut; redundant areas in the RGB image and the multispectral image are removed, and the influence of other areas on the identification of the tree obstacle felling area is avoided. The obstacle tree region image before felling and the obstacle tree region image after felling are input into a trained region recognition model to obtain the obstacle tree felling region image, the problem that the obstacle tree felling region efficiency is low in manual measurement is solved, automatic extraction of the obstacle tree felling region is achieved, and the effect of obtaining efficiency of the tree felling region is improved.
Drawings
Fig. 1 is a flowchart of a region identification method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a region identification method according to a second embodiment of the present invention;
fig. 3 is a structural diagram of an area recognition apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device in a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a region identification method according to an embodiment of the present invention, where the embodiment is applicable to a case of identifying a cut-down region of a barrier tree, and the method may be executed by a region identification device, and specifically includes the following steps:
and S110, respectively obtaining an RGB image and a multispectral image of the complete line channel to be identified before and after the tree barrier is felled.
The method comprises the steps of shooting RGB images and multispectral images of the circuit channel to be identified before and after the tree barrier is cut and pruned through an unmanned aerial vehicle carrying camera. Multispectral refers to the fact that the wavelength distribution of sunlight is from short to long as the sunlight is a continuous spectrum with different wavelengths. The visible light with different colors shows color change due to the wavelength difference. Due to the difference of different object properties, when the sunlight is irradiated, the ratio of the sunlight absorbed by the surface of the object to the sunlight reflected by the surface of the object is different. The multispectral image is more advantageous for segmenting the region of interest.
Optionally, the obtaining of the RGB image and the multispectral image of the complete line channel to be identified before and after the felling of the tree obstacle includes: respectively acquiring RGB (red, green and blue) images and multispectral images of a line channel to be identified before and after the tree barrier is felled; and respectively cutting and splicing the RGB image and the multispectral image to obtain a complete RGB image of the line channel to be identified and a complete multispectral image of the line channel to be identified. Carry on RGB image and multispectral image before the pruning of line passageway obstacles to be discerned that camera was shot through unmanned aerial vehicle and prune not one can reflect the complete image of line passageway to be discerned, but treat that discerned line passageway has carried out the shooting of many images, need tailor and splice the image of shooing to obtain the complete image of line passageway to be discerned before the pruning of obstacles and after pruning, so that follow-up discerns the area of obstacles to be cut.
Optionally, the cutting and splicing are performed on the RGB image and the multispectral image respectively to obtain a complete RGB image of the line channel to be identified and a complete multispectral image of the line channel to be identified, which includes: generating an orthoimage of the RGB image according to the RGB image obtained by shooting; generating an orthoimage of the multispectral image according to the multispectral image obtained by shooting; cutting and splicing the orthographic images of the RGB images to obtain a complete RGB image of the line channel to be identified; and cutting and splicing the orthographic images of the multispectral images to obtain a complete multispectral image of the line channel to be identified. The ortho image is a remote sensing image with ortho projection properties. The original remote sensing image has distortion and distortion of different degrees because of the influence of the internal state change, the external state and the earth surface condition of the sensor during imaging. The geometric processing of the remote sensing image not only extracts spatial information, such as drawing contour lines, but also resamples the gray level of the image according to a correct geometric relationship to form a new orthoimage. And generating corresponding orthoimages from the RGB images and the multispectral images obtained by shooting, and cutting and splicing the orthoimages to obtain complete RGB images and multispectral images of the line channel to be identified. The orthoimage can improve the precision of the image and is more beneficial to identifying the felling area.
And S120, obtaining an image of the area of the tree barrier before felling according to the RGB image of the complete to-be-identified line channel before felling of the tree barrier and the multispectral image of the complete to-be-identified line channel before felling of the tree barrier.
And extracting the tree obstacle region according to the multispectral image of the complete to-be-identified line channel before the tree obstacle is cut to obtain the multispectral image of the tree obstacle region before the tree obstacle is cut, and then combining the RGB image of the complete to-be-identified line channel before the tree obstacle is cut to obtain the tree obstacle region image before the tree obstacle is cut.
Optionally, the obtaining of the image of the area of the tree barrier before felling according to the RGB image of the complete line channel to be identified before felling of the tree barrier and the multispectral image of the complete line channel to be identified before felling of the tree barrier includes: obtaining a multispectral image of a tree barrier region before felling according to the multispectral image of the to-be-identified line channel before tree barrier felling; and obtaining the RGB image of the tree barrier area before felling according to the multispectral image of the tree barrier area before felling and the RGB image of the line channel to be identified before the tree barrier is felled. And extracting the region of interest of the multispectral image of the line channel to be identified before the tree barrier is cut to obtain the multispectral image of the tree barrier region before cutting. And performing image segmentation on the RGB image of the line channel to be identified before the tree barrier is cut according to the multispectral image of the tree barrier area before the tree barrier is cut to obtain the RGB image of the tree barrier area before the tree barrier is cut. The multispectral image is extracted in the region of interest to obtain the multispectral image of the tree barrier region before felling, and then the RGB image is segmented to enable the obtained RGB image of the tree barrier region before felling to be more accurate.
S130, obtaining a cut tree barrier area image according to the RGB image of the complete to-be-identified line channel after the tree barrier is cut and the multispectral image of the complete to-be-identified line channel after the tree barrier is cut.
And extracting the tree barrier region according to the complete multispectral image of the line channel to be identified after the tree barrier is cut down to obtain the multispectral image of the cut tree barrier region, and then combining the complete RGB image of the line channel to be identified after the tree barrier is cut down to obtain the cut tree barrier region image.
Optionally, the obtaining of the cut tree barrier region image according to the RGB image of the complete line channel to be identified after the tree barrier is cut and the multispectral image of the complete line channel to be identified after the tree barrier is cut includes: obtaining a multi-spectral image of a cut tree barrier area according to the multi-spectral image of the to-be-identified line channel after the tree barrier is cut; and obtaining an RGB image of the cut tree barrier area according to the cut multispectral image of the tree barrier area and the cut RGB image of the line channel to be identified. And extracting the region of interest of the multi-spectral image of the to-be-identified line channel after the tree barrier is cut down, and filtering useless interference regions to obtain the multi-spectral image of the cut tree barrier region. And performing image segmentation on the RGB image of the cut to-be-identified line channel according to the multispectral image of the cut to-be-identified tree barrier area, and extracting the same area as the multispectral image of the cut to-be-identified line channel from the RGB image of the cut to-be-identified line channel to obtain the multispectral image of the cut to-be-identified tree barrier area.
S140, inputting the tree obstacle area image before felling and the tree obstacle area image after felling into a trained area recognition model to obtain the tree obstacle felling area image.
And inputting the segmented tree barrier region image before cutting and the segmented tree barrier region image after cutting into a trained region recognition model, and recognizing the tree barrier of the line channel before cutting and after cutting to obtain the tree barrier cut region image.
Optionally, the region identification model is a deep lavv 3+ model. And the picture format used in the training of the DeepLabv3+ model is consistent with the picture format of the channel to be identified. The DeepLabv3+ model can be trained through transfer learning, and can also be trained based on deep learning. Illustratively, a DeepLabv3+ model is trained on the basis of ground object classification remote sensing images, training parameters of a feature extraction layer are taken, and the training parameters are transferred to felling and lodging data set training to obtain a region recognition model. And inputting the tree obstacle area image before felling and the tree obstacle area image after felling into a trained DeepLabv3+ model to identify the tree obstacle felling area, so as to obtain an accurate tree obstacle felling area.
According to the technical scheme of the embodiment, the RGB image and the multispectral image of the complete line channel to be identified before and after the tree barrier is cut are respectively obtained; obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling; obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut; redundant areas in the RGB image and the multispectral image are removed, and the influence of other areas on the identification of the tree obstacle felling area is avoided. The obstacle area image before felling and the obstacle area image after felling are input into a trained area recognition model to obtain the obstacle felling area image, the problem that the obstacle felling area efficiency is low in manual measurement is solved, automatic extraction of the high-precision obstacle felling area is achieved, and the effect of obtaining efficiency of the tree felling area is improved.
Example two
Fig. 2 is a flowchart of a region identification method according to a second embodiment of the present invention, where this embodiment is further optimized based on the first embodiment, and after the pre-felled obstacle region image and the post-felled obstacle region image are input into a trained region identification model to obtain an obstacle felled region image, the method further includes: and calculating the area of the tree obstacle felling region according to the image of the tree obstacle felling region. And powerful data support is provided for settlement of engineering quantity.
As shown in fig. 2, the method specifically includes the following steps:
s210, respectively obtaining an RGB image and a multispectral image of the complete line channel to be identified before and after the tree obstacle is felled.
S220, obtaining an image of the area of the tree barrier before felling according to the RGB image of the complete to-be-identified line channel before felling of the tree barrier and the multispectral image of the complete to-be-identified line channel before felling of the tree barrier.
And S230, obtaining a cut tree barrier area image according to the RGB image of the complete to-be-identified line channel after the tree barrier is cut and the multispectral image of the complete to-be-identified line channel after the tree barrier is cut.
S240, inputting the tree obstacle area image before felling and the tree obstacle area image after felling into a trained area recognition model to obtain the tree obstacle felling area image.
And S250, calculating the area of the tree obstacle felling region according to the image of the tree obstacle felling region.
Before the image is cut and spliced to obtain a complete RGB image of the line channel to be identified and a complete multispectral image of the line channel to be identified, the shot RGB image and multispectral image of the line channel to be identified are converted into an ortho image, so that the image of the area of the tree barrier cut area obtained through the area identification model is also the ortho image, the ortho image of the area of the tree barrier cut area is measured to obtain the area of the tree barrier cut area, the area of the tree barrier cut area does not need to be measured and calculated manually, the labor cost is greatly saved, and powerful data support is provided for settlement of engineering quantities.
According to the technical scheme of the embodiment, the RGB image and the multispectral image of the complete line channel to be identified before and after the tree barrier is cut are respectively obtained; obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling; obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut; redundant areas in the RGB image and the multispectral image are removed, and the influence of other areas on the identification of the tree obstacle felling area is avoided. The regional image of the tree obstacle before will cutting and the regional image of the tree obstacle after cutting input obtains the regional image of the tree obstacle cutting to the regional recognition model of training, calculates the regional area of the tree obstacle cutting according to the regional image of the tree obstacle cutting, has solved the regional inefficiency of artifical measurement tree obstacle cutting, and the not high problem of degree of accuracy, has realized the regional automatic extraction of the tree obstacle cutting of high accuracy, has improved the regional effect of obtaining efficiency of tree cutting. And the measurement calculation of the area of the tree obstacle cut area is not needed manually, so that the labor cost is greatly saved, and powerful data support is provided for settlement of engineering quantity.
EXAMPLE III
Fig. 3 is a structural diagram of an area recognition apparatus according to a third embodiment of the present invention, where the area recognition apparatus includes: the tree obstacle pre-felling area image acquisition module 310, the tree obstacle area pre-felling image acquisition module 320, the tree obstacle area post-felling image acquisition module 330, and the tree obstacle felling area image acquisition module 340.
The image acquisition module 310 is configured to acquire an RGB image and a multispectral image of a complete line channel to be identified before and after felling of a tree barrier, respectively; the pre-felling tree barrier area image acquisition module 320 is used for acquiring a pre-felling tree barrier area image according to an RGB image of a complete to-be-identified line channel before tree barrier felling and a multispectral image of the complete to-be-identified line channel before tree barrier felling; the felled tree barrier area image acquisition module 330 is configured to obtain a felled tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is felled and a multispectral image of the complete line channel to be identified after the tree barrier is felled; and the tree barrier felling area image acquisition module 340 is configured to input the pre-felled tree barrier area image and the felled tree barrier area image into a trained area recognition model to obtain a tree barrier felling area image.
In the technical solution of the above embodiment, the image obtaining module 310 includes:
the device comprises a to-be-identified line channel image acquisition unit, a to-be-identified line channel identification unit and a to-be-identified line channel identification unit, wherein the to-be-identified line channel image acquisition unit is used for respectively acquiring RGB images and multispectral images of a to-be-identified line channel before and after the tree barrier is fell;
and the image cutting and splicing unit is used for respectively cutting and splicing the RGB image and the multispectral image to obtain a complete RGB image of the line channel to be identified and a complete multispectral image of the line channel to be identified.
In the technical solution of the above embodiment, the image cropping and stitching unit includes:
the orthoimage generation subunit of the RGB image is used for generating an orthoimage of the RGB image according to the shot RGB image;
the ortho-image generation subunit of the multispectral image is used for generating the ortho-image of the multispectral image according to the multispectral image obtained by shooting;
the orthoimage cutting and splicing subunit is used for cutting and splicing the orthoimages of the RGB images to obtain complete RGB images of the line channel to be identified; and cutting and splicing the orthographic images of the multispectral images to obtain a complete multispectral image of the line channel to be identified.
In the technical solution of the above embodiment, the pre-felling tree barrier area image obtaining module 320 includes:
the pre-felling tree barrier region multispectral image generating unit is used for obtaining a pre-felling tree barrier region multispectral image according to a multispectral image of a to-be-identified line channel before the tree barrier is felled;
and the RGB image generation unit of the tree barrier area before felling is used for obtaining the RGB image of the tree barrier area before felling according to the multispectral image of the tree barrier area before felling and the RGB image of the line channel to be identified before tree barrier felling.
In the technical solution of the above embodiment, the module 330 for obtaining an image of an area of a cut tree barrier includes:
the felled tree barrier region multispectral image generating unit is used for obtaining a felled tree barrier region multispectral image according to the shrunken tree barrier multispectral image of the to-be-identified line channel;
and the RGB image generation unit of the cut tree barrier area is used for obtaining the RGB image of the cut tree barrier area according to the multispectral image of the cut tree barrier area and the RGB image of the cut line channel to be identified.
Optionally, the region identification model is a deep lavv 3+ model.
In the technical solution of the above embodiment, the area identification apparatus further includes:
and the area calculation module is used for calculating the area of the tree obstacle felling region according to the tree obstacle felling region image.
According to the technical scheme of the embodiment, the RGB image and the multispectral image of the complete line channel to be identified before and after the tree barrier is cut are respectively obtained; obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling; obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut; redundant areas in the RGB image and the multispectral image are removed, and the influence of other areas on the identification of the tree obstacle felling area is avoided. The obstacle area image before felling and the obstacle area image after felling are input into a trained area recognition model to obtain the obstacle felling area image, the problem that the obstacle felling area efficiency is low in manual measurement is solved, automatic extraction of the high-precision obstacle felling area is achieved, and the effect of obtaining efficiency of the tree felling area is improved.
The area identification device provided by the embodiment of the invention can execute the area identification method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention, as shown in fig. 4, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processors 410 in the electronic device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the memory 420, the input device 430 and the output device 440 in the electronic apparatus may be connected by a bus or other means, and the bus connection is exemplified in fig. 4.
The memory 420 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the area identification method in the embodiment of the present invention (for example, the image acquisition module 310, the pre-felling obstacle area image acquisition module 320, the post-felling obstacle area image acquisition module 330, and the obstacle-felling area image acquisition module 340 in the area identification apparatus). The processor 410 executes various functional applications and data processing of the electronic device by executing software programs, instructions and modules stored in the memory 420, that is, implements the region identification method described above.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to an electronic device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus. The output device 440 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a region identification method, the method including:
respectively acquiring an RGB image and a multispectral image of a complete line channel to be identified before and after the tree obstacle is felled;
obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling;
obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut;
and inputting the tree obstacle area image before felling and the tree obstacle area image after felling into a trained area recognition model to obtain a tree obstacle felling area image.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the area identification method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. With this understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the area identification apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for identifying a region, comprising:
respectively acquiring an RGB image and a multispectral image of a complete line channel to be identified before and after the tree obstacle is felled;
obtaining a tree obstacle area image before felling according to an RGB image of a complete line channel to be identified before tree obstacle felling and a multispectral image of the complete line channel to be identified before tree obstacle felling;
obtaining a cut tree barrier area image according to an RGB image of a complete line channel to be identified after the tree barrier is cut and a multispectral image of the complete line channel to be identified after the tree barrier is cut;
and inputting the tree obstacle area image before felling and the tree obstacle area image after felling into a trained area recognition model to obtain a tree obstacle felling area image.
2. The method as claimed in claim 1, wherein the obtaining of the RGB image and the multispectral image of the complete line channel to be identified before and after the felling of the tree barrier comprises:
respectively acquiring RGB (red, green and blue) images and multispectral images of a line channel to be identified before and after the tree barrier is felled;
and respectively cutting and splicing the RGB image and the multispectral image to obtain a complete RGB image of the line channel to be identified and a complete multispectral image of the line channel to be identified.
3. The method according to claim 2, wherein the cropping and stitching the RGB image and the multispectral image to obtain a complete RGB image of the channel to be identified and a complete multispectral image of the channel to be identified respectively comprises:
generating an orthoimage of the RGB image according to the RGB image obtained by shooting;
generating an orthoimage of the multispectral image according to the multispectral image obtained by shooting;
cutting and splicing the orthographic images of the RGB images to obtain a complete RGB image of the line channel to be identified;
and cutting and splicing the orthographic images of the multispectral images to obtain a complete multispectral image of the line channel to be identified.
4. The method of claim 1, wherein obtaining the image of the area of the tree barrier before felling from the RGB image of the complete line channel to be identified before tree barrier felling and the multispectral image of the complete line channel to be identified before tree barrier felling comprises:
obtaining a multispectral image of a tree barrier region before felling according to the multispectral image of the to-be-identified line channel before tree barrier felling;
and obtaining the RGB image of the tree barrier area before felling according to the multispectral image of the tree barrier area before felling and the RGB image of the line channel to be identified before the tree barrier is felled.
5. The method as claimed in claim 1, wherein the obtaining of the image of the area of the cut tree barrier from the RGB image of the complete line channel to be identified after the tree barrier is cut and the multispectral image of the complete line channel to be identified after the tree barrier is cut comprises:
obtaining a multi-spectral image of a cut tree barrier area according to the multi-spectral image of the to-be-identified line channel after the tree barrier is cut;
and obtaining an RGB image of the cut tree barrier area according to the cut multispectral image of the tree barrier area and the cut RGB image of the line channel to be identified.
6. The method of claim 1, wherein the region identification model is a deep lab v3+ model.
7. The method of claim 1, wherein after inputting the pre-felled tree barrier region image and the post-felled tree barrier region image into a trained region recognition model to obtain a tree barrier felled region image, the method further comprises:
and calculating the area of the tree obstacle felling region according to the image of the tree obstacle felling region.
8. An area recognition apparatus, comprising:
the image acquisition module is used for respectively acquiring an RGB image and a multispectral image of a complete line channel to be identified before and after the tree barrier is felled;
the pre-felling tree barrier area image acquisition module is used for acquiring a pre-felling tree barrier area image according to an RGB image of a complete to-be-identified line channel before tree barrier felling and a multispectral image of the complete to-be-identified line channel before tree barrier felling;
the device comprises a felled tree barrier area image acquisition module, a tree barrier identification module and a tree barrier identification module, wherein the felled tree barrier area image acquisition module is used for acquiring a felled tree barrier area image according to an RGB image of a complete to-be-identified line channel after the tree barrier is felled and a multispectral image of the complete to-be-identified line channel after the tree barrier is felled;
and the tree barrier felling area image acquisition module is used for inputting the tree barrier area image before felling and the tree barrier area image after felling into a trained area recognition model to obtain a tree barrier felling area image.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the region identification method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the region identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010981808.8A CN112085036A (en) | 2020-09-17 | 2020-09-17 | Region identification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010981808.8A CN112085036A (en) | 2020-09-17 | 2020-09-17 | Region identification method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112085036A true CN112085036A (en) | 2020-12-15 |
Family
ID=73736559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010981808.8A Pending CN112085036A (en) | 2020-09-17 | 2020-09-17 | Region identification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085036A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119606A (en) * | 2022-01-20 | 2022-03-01 | 国网江西省电力有限公司电力科学研究院 | Intelligent tree obstacle hidden danger analysis method based on visible light photo power line coloring |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255317A (en) * | 2018-08-31 | 2019-01-22 | 西北工业大学 | A kind of Aerial Images difference detecting method based on dual network |
| CN109540814A (en) * | 2019-01-12 | 2019-03-29 | 合肥工业大学 | A kind of iris gray mold early detection method based on multi-optical spectrum imaging technology |
| CN110443195A (en) * | 2019-08-02 | 2019-11-12 | 四创科技有限公司 | A kind of remote sensing image brulee analysis method of combination super-pixel and deep learning |
| CN110595442A (en) * | 2019-08-13 | 2019-12-20 | 中国南方电网有限责任公司超高压输电公司昆明局 | Transmission line channel tree obstacle detection method, storage medium and computer equipment |
| CN111444833A (en) * | 2020-03-25 | 2020-07-24 | 中国农业科学院农业信息研究所 | Fruit measurement production method and device, computer equipment and storage medium |
| CN111461053A (en) * | 2020-04-13 | 2020-07-28 | 安徽大学 | System for identifying multiple growth period wheat lodging regions based on transfer learning |
-
2020
- 2020-09-17 CN CN202010981808.8A patent/CN112085036A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255317A (en) * | 2018-08-31 | 2019-01-22 | 西北工业大学 | A kind of Aerial Images difference detecting method based on dual network |
| CN109540814A (en) * | 2019-01-12 | 2019-03-29 | 合肥工业大学 | A kind of iris gray mold early detection method based on multi-optical spectrum imaging technology |
| CN110443195A (en) * | 2019-08-02 | 2019-11-12 | 四创科技有限公司 | A kind of remote sensing image brulee analysis method of combination super-pixel and deep learning |
| CN110595442A (en) * | 2019-08-13 | 2019-12-20 | 中国南方电网有限责任公司超高压输电公司昆明局 | Transmission line channel tree obstacle detection method, storage medium and computer equipment |
| CN111444833A (en) * | 2020-03-25 | 2020-07-24 | 中国农业科学院农业信息研究所 | Fruit measurement production method and device, computer equipment and storage medium |
| CN111461053A (en) * | 2020-04-13 | 2020-07-28 | 安徽大学 | System for identifying multiple growth period wheat lodging regions based on transfer learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119606A (en) * | 2022-01-20 | 2022-03-01 | 国网江西省电力有限公司电力科学研究院 | Intelligent tree obstacle hidden danger analysis method based on visible light photo power line coloring |
| CN114119606B (en) * | 2022-01-20 | 2022-05-10 | 国网江西省电力有限公司电力科学研究院 | Intelligent tree obstacle hidden danger analysis method based on visible light photo power line coloring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11869192B2 (en) | System and method for vegetation modeling using satellite imagery and/or aerial imagery | |
| CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
| CN106547814A (en) | A kind of power transmission line unmanned machine patrols and examines the structuring automatic archiving method of image | |
| CN110705847A (en) | Intelligent substation inspection method and system based on image recognition technology | |
| CN110969719A (en) | Automatic inspection method, system, terminal equipment and storage medium | |
| CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN115170792B (en) | Infrared image processing method, device and equipment and storage medium | |
| CN113515655A (en) | Fault identification method and device based on image classification | |
| CN115359239A (en) | Wind power blade defect detection and positioning method and device, storage medium and electronic equipment | |
| CN112085036A (en) | Region identification method, device, equipment and medium | |
| CN111552762A (en) | Orchard planting digital map management method and system based on fruit tree coding | |
| CN114880730A (en) | Method and device for determining target equipment and photovoltaic system | |
| CN112802027A (en) | Target object analysis method, storage medium and electronic device | |
| CN108537792B (en) | Power defect image identification method based on convolutional neural network | |
| CN113033386B (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
| CN112052811A (en) | Pasture grassland desertification detection method based on artificial intelligence and aerial image | |
| CN112329649A (en) | Urban vegetation type identification method, system, equipment and medium | |
| CN112016641A (en) | Method and device for alarming line short circuit fault caused by foreign matter | |
| CN116863452A (en) | Plant disease identification method, storage medium, and identification system | |
| CN114445326A (en) | Photovoltaic panel abnormity detection method, detection device and computer readable storage device | |
| CN113033355B (en) | Abnormal target identification method and device based on intensive power transmission channel | |
| CN113223155A (en) | Distance prediction method, device, equipment and medium | |
| CN114511943A (en) | Distribution line infrared inspection method and system based on mobile terminal | |
| CN114694048A (en) | Sparse shrub species identification method and system based on unmanned aerial vehicle remote sensing technology |
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 |