CN117911891A - Equipment identification method and device, electronic equipment and storage medium - Google Patents
Equipment identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117911891A CN117911891A CN202410078041.6A CN202410078041A CN117911891A CN 117911891 A CN117911891 A CN 117911891A CN 202410078041 A CN202410078041 A CN 202410078041A CN 117911891 A CN117911891 A CN 117911891A
- Authority
- CN
- China
- Prior art keywords
- identified
- equipment
- image
- power equipment
- remote sensing
- 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 67
- 238000012545 processing Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 5
- 239000000758 substrate Substances 0.000 claims 2
- 238000001514 detection method Methods 0.000 abstract description 11
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a device identification method, a device, an electronic device and a storage medium. The method comprises the following steps: acquiring a remote sensing image to be identified, wherein the remote sensing image to be identified contains target power equipment to be identified; slicing the remote sensing image to be identified to obtain a plurality of sub-images, wherein the size of an overlapping area between adjacent slices is related to the size of power equipment in equipment set, and the equipment set at least comprises target power equipment to be identified; and carrying out image recognition on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by recognition, and obtaining target recognition information corresponding to all target power equipment in the remote sensing image to be recognized. According to the method, the size of the overlapping area between adjacent slices is related to the size of the power equipment in the equipment set during slicing, so that the missing detection phenomenon can be avoided, meanwhile, the repetition of the detected target power equipment can be avoided through the heavy operation, and the accuracy of identifying the power equipment is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a device identification method, a device, electronic equipment and a storage medium.
Background
In the field of computer vision, object recognition is one of important branches, and object recognition is a means for automatically recognizing a specific object from an image or video and acquiring information such as the position and the category of the specific object. Target recognition can be applied to various fields, such as recognition of power equipment in satellite remote sensing images by means of target recognition.
On the basis that the satellite remote sensing image is a large-size image, the target to be identified in the satellite remote sensing image is relatively small, and the existing means for directly inputting the satellite remote sensing image into the model for target identification can possibly generate the problem of missed detection, so that the accuracy of target identification is low.
Disclosure of Invention
The invention provides a device identification method, a device, an electronic device and a storage medium, which can avoid the missing detection phenomenon and improve the accuracy of identifying the power device.
In a first aspect, an embodiment of the present invention provides a device identification method, including:
Acquiring a remote sensing image to be identified, wherein the remote sensing image to be identified contains target power equipment to be identified;
Slicing the remote sensing image to be identified to obtain a plurality of sub-images, wherein the size of an overlapping area between adjacent slices is related to the size of power equipment in equipment set, and the equipment set at least comprises target power equipment to be identified;
and carrying out image recognition on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by recognition, and obtaining target recognition information corresponding to all target power equipment in the remote sensing image to be recognized.
Further, the size of the overlapping area between adjacent slices during the slicing process comprises a first width and a first height;
The first width is the width of the power equipment with the largest equipment concentration size;
the first height is the height of the power equipment with the largest equipment concentration size.
Further, the size of each slice in the slice processing comprises a slice width and a slice height;
the slice width is the sum of a preset width and half of the first width;
the slice height is the sum of a preset height and half of the first height.
Further, performing image recognition on each sub-image includes:
and respectively inputting each sub-image into a target recognition model to obtain information of each candidate power device, wherein the number of the candidate power devices is multiple.
Further, the deduplication operation includes:
And if the longitude difference and the latitude difference of the two candidate power devices obtained through the different two sub-image recognition are respectively smaller than the corresponding threshold values, determining any one of the two candidate power devices as the target power device.
Further, the target identification information at least includes:
Longitude and latitude coordinates, equipment category and confidence coefficient corresponding to each target power equipment.
Further, the target power equipment is a transmission tower, and correspondingly, the equipment category corresponding to the target power equipment is a category determined according to the shape or the material of the target power equipment.
Further, after the remote sensing image to be identified is obtained, the method further includes:
Preprocessing the remote sensing image to be identified, wherein the preprocessing comprises one or more of the following steps:
radiometric calibration, atmospheric correction, data registration, image fusion, linear stretching, or super resolution.
In a second aspect, an embodiment of the present invention provides a device identification apparatus, including:
the remote sensing image identification device comprises an acquisition module and a recognition module, wherein the acquisition module is used for acquiring a remote sensing image to be identified, and the remote sensing image to be identified contains target power equipment to be identified;
The slicing module is used for slicing the remote sensing image to be identified to obtain a plurality of sub-images, and the size of an overlapping area between adjacent slices is related to the size of the power equipment in the equipment set during slicing, wherein the equipment set at least comprises target power equipment to be identified;
And the identification module is used for carrying out image identification on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by identification, and obtaining target identification information corresponding to all target power equipment in the remote sensing image to be identified.
Further, the size of the overlapping area between adjacent slices during the slicing process comprises a first width and a first height;
The first width is the width of the power equipment with the largest equipment concentration size;
the first height is the height of the power equipment with the largest equipment concentration size.
Further, the size of each slice in the slice processing comprises a slice width and a slice height;
the slice width is the sum of a preset width and half of the first width;
the slice height is the sum of a preset height and half of the first height.
Further, the identification module is specifically configured to:
and respectively inputting each sub-image into a target recognition model to obtain information of each candidate power device, wherein the number of the candidate power devices is multiple.
Further, the identification module is specifically configured to:
And if the longitude difference and the latitude difference of the two candidate power devices obtained through the different two sub-image recognition are respectively smaller than the corresponding threshold values, determining any one of the two candidate power devices as the target power device.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements a method as described in the first aspect.
The embodiment of the invention provides a device identification method, a device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring a remote sensing image to be identified, wherein the remote sensing image to be identified contains target power equipment to be identified; slicing the remote sensing image to be identified to obtain a plurality of sub-images, wherein the size of an overlapping area between adjacent slices is related to the size of power equipment in equipment set, and the equipment set at least comprises target power equipment to be identified; and carrying out image recognition on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by recognition, and obtaining target recognition information corresponding to all target power equipment in the remote sensing image to be recognized. According to the technical scheme, when the remote sensing image to be identified is subjected to slicing processing, the size of the overlapping area between adjacent slices is related to the size of the power equipment in the equipment set, so that each target power equipment can at least completely exist in one slice, the missing detection phenomenon can be avoided, meanwhile, the repetition of the detected target power equipment can be avoided through the repeated operation, and the accuracy of identifying the power equipment is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a device identification method according to a first embodiment of the present invention;
Fig. 2 is a flowchart of a device identification method according to a second embodiment of the present invention;
FIG. 3 is a schematic view of overlapping adjacent slices according to a second embodiment of the present invention;
Fig. 4 is a schematic structural view of a device identification apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing a device identification method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like herein are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a device identification method according to a first embodiment of the present invention, where the method may be applied to identifying a power device in a remote sensing image to be identified, and the method may be performed by a device identification apparatus, which may be implemented in the form of software and/or hardware and integrated in an electronic device. Further, the electronic device includes, but is not limited to: computers, notebook computers, smart phones, servers, etc.
As shown in fig. 1, the method includes:
s110, acquiring a remote sensing image to be identified, wherein the remote sensing image to be identified comprises target power equipment to be identified.
The remote sensing image to be identified may be an image for performing power equipment identification. The remote sensing image to be identified contains target power equipment to be identified. The target power device may be a power device to be identified in the remote sensing image to be identified, for example, may be various types of transmission towers, and is not limited herein. The number of the target power devices to be identified, which are included in the remote sensing image to be identified, is not limited, and may be one or more, and may be specifically determined according to actual needs.
The method of acquiring the remote sensing image to be identified is not limited, and the remote sensing image to be identified can be acquired. If the remote sensing image to be identified is stored in the database in advance, the electronic equipment can acquire the remote sensing image to be identified from the database when the target power equipment is required to be identified; the electronic equipment can also obtain the remote sensing image to be identified through webpage downloading.
S120, slicing the remote sensing image to be identified to obtain a plurality of sub-images, wherein the size of an overlapping area between adjacent slices is related to the size of power equipment in equipment set, and the equipment set at least comprises target power equipment to be identified.
The sub-images can be images obtained by slicing the remote sensing image to be identified, and the number of the sub-images can be multiple. After the sub-images are obtained by slicing, for any sub-image, there may or may not be a target power device to be identified.
The device set can be a set of a plurality of electric devices, and each electric device stored in the device set can be different electric devices determined according to actual application needs, such as electric devices needing to be identified through satellite remote sensing images. The equipment set at least comprises target power equipment to be identified, which is contained in the remote sensing image to be identified.
The method of slicing the remote sensing image to be identified to obtain a plurality of sub-images is not limited, and may be implemented by an overlapping (Overlap) slicing method. The size of the overlapping area between adjacent slices in the slice processing is related to the size of the power device in the device concentration, wherein the adjacent slices may be four slices that are adjacent and overlap each other, and the size of the overlapping area between the four slices is related to the size of the power device in the device concentration.
Specifically, in practical application, the size of the overlapping area between the adjacent slices can be adjusted according to the size of each electric device in the device set, for example, the size of the overlapping area between the adjacent slices is consistent with the size of the electric device with the largest device set size, so that each target electric device to be identified can be ensured to be at least completely existing in one slice, all the target electric devices to be identified in the remote sensing image to be identified can be ensured to be identified, and the missing detection phenomenon of the electric devices can not be generated.
And S130, carrying out image recognition on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by recognition, and obtaining target recognition information corresponding to all target power equipment in the remote sensing image to be recognized.
The method of image recognition for each sub-image is not limited, and for example, each sub-image may be input into a target recognition model, and the result of recognition for each sub-image may be output through the target recognition model. The object recognition model may be a model for recognizing the power device in the image, and the model structure of the object recognition model is not limited, and the object recognition model may be a model for recognizing the power device in the image based on deep learning.
And if the sub-image contains the candidate power equipment, the identified result comprises the position corresponding to the candidate power equipment, the equipment type corresponding to the candidate power equipment and the confidence degree of the model output result. The candidate power device may be a power device obtained by performing image recognition on the sub-image. The position of the candidate power equipment can be a pixel coordinate of a center point of a base of the candidate power equipment, and affine transformation can be carried out on the pixel coordinate in the follow-up process to obtain longitude and latitude coordinates in an actual scene corresponding to the pixel coordinate.
After the image recognition is completed on all the sub-images, the information of each candidate power device recognized by each sub-image can be obtained, namely the position, the device type and the model corresponding to each candidate power device output the confidence of the position and the device type. The information of each candidate power device is integrated, and in the integrated information of each candidate power device, the same candidate power device may exist in 2 to 4 different slices at the same time, so that the integrated result needs to be deduplicated, so that the same candidate power device can exist in only one slice.
The deduplication of the integrated result may include the following operations: if the longitude difference and the latitude difference of the two candidate power devices obtained through the recognition of the two different sub-images are respectively smaller than the corresponding threshold values, the two candidate power devices are possibly identical power devices, but exist in the two sub-images at the same time, so that any one of the two candidate power devices can be determined as the target power device, the deduplication operation on the candidate power devices is completed, and the finally obtained target power devices cannot have repeated power devices.
And after the de-duplication operation is finished, obtaining target identification information corresponding to all target power equipment in the remote sensing image to be identified. The target identification information may be information of a target power device in the remote sensing image to be identified. The target identification information may include, but is not limited to: the number of target power devices in the remote sensing image to be identified, the position corresponding to each target power device, the device class corresponding to each target power device, the position corresponding to each target power device and the confidence of the device class.
The embodiment of the invention provides a device identification method, a device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring a remote sensing image to be identified, wherein the remote sensing image to be identified contains target power equipment to be identified; slicing the remote sensing image to be identified to obtain a plurality of sub-images, wherein the size of an overlapping area between adjacent slices is related to the size of power equipment in equipment set, and the equipment set at least comprises target power equipment to be identified; and carrying out image recognition on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by recognition, and obtaining target recognition information corresponding to all target power equipment in the remote sensing image to be recognized. According to the technical scheme, when the remote sensing image to be identified is subjected to slicing processing, the size of the overlapping area between adjacent slices is related to the size of the power equipment in the equipment set, so that each target power equipment can at least completely exist in one slice, the missing detection phenomenon can be avoided, meanwhile, the repetition of the detected target power equipment can be avoided through the repeated operation, and the accuracy of identifying the power equipment is improved.
Example two
Fig. 2 is a flowchart of a device identification method according to a second embodiment of the present invention, which is further refined based on the first embodiment.
In an embodiment of the present invention, after the obtaining of the remote sensing image to be identified, the method further includes:
Preprocessing the remote sensing image to be identified, wherein the preprocessing comprises one or more of the following steps:
radiometric calibration, atmospheric correction, data registration, image fusion, linear stretching, or super resolution.
In the embodiment of the invention, the size of the overlapping area between adjacent slices during slice processing comprises a first width and a first height;
The first width is the width of the power equipment with the largest equipment concentration size;
the first height is the height of the power equipment with the largest equipment concentration size.
In the embodiment of the invention, the image recognition of each sub-image comprises the following steps:
and respectively inputting each sub-image into a target recognition model to obtain information of each candidate power device, wherein the number of the candidate power devices is multiple.
In an embodiment of the present invention, the deduplication operation includes:
And if the longitude difference and the latitude difference of the two candidate power devices obtained through the different two sub-image recognition are respectively smaller than the corresponding threshold values, determining any one of the two candidate power devices as the target power device.
As shown in fig. 2, the method includes:
S201, acquiring a remote sensing image to be identified.
S202, preprocessing the remote sensing image to be identified, wherein the preprocessing comprises one or more of the following steps: radiometric calibration, atmospheric correction, data registration, image fusion, linear stretching, or super resolution.
Aiming at multispectral data corresponding to the remote sensing image to be identified, performing radiometric calibration, atmospheric correction and data registration processing on the multispectral data to obtain a first result; aiming at the full-color data corresponding to the remote sensing image to be identified, performing radiometric calibration, atmospheric correction and data registration processing on the full-color data to obtain a second result; and performing image fusion processing on the first result and the second result, and then sequentially performing linear stretching and super-resolution processing. The above steps can be understood as a preprocessing process of the remote sensing image to be recognized, and after preprocessing is finished, the image obtained by preprocessing can be regarded as a new remote sensing image to be recognized, and the subsequent steps are executed through the new remote sensing image to be recognized.
By preprocessing the remote sensing image to be identified through the steps, the definition and the accuracy of the remote sensing image to be identified can be improved, so that the subsequent segmentation of the remote sensing image to be identified and the identification processing of target power equipment can be facilitated.
S203, slicing the remote sensing image to be identified to obtain a plurality of sub-images, wherein the size of an overlapping area between adjacent slices during slicing comprises a first width and a first height; the first width is the width of the power equipment with the largest equipment concentration size; the first height is the height of the power equipment with the largest equipment concentration size.
In one embodiment, the dimensions of each slice at the time of the slice processing include slice width and slice height; the slice width is the sum of a preset width and half of the first width; the slice height is the sum of a preset height and half of the first height.
Fig. 3 is a schematic diagram of overlapping adjacent slices according to a second embodiment of the present invention, in which, as shown in fig. 3, a slice 31 (corresponding to a sub-image) and three other slices adjacent to the slice 31, the three other slices adjacent to the slice 31 are rectangular frames of the same size as the slice 31, and are shown in fig. 3 by different lines.
As can be seen from fig. 3, the adjacent slices can be four slices that are adjacent and overlap each other when the slices are processed, and the size of the overlapping area 32 between the four slices includes a first width Wmax and a first height Hmax, where the first width Wmax is the width of the power device with the largest device concentration size, and the first height Hmax is the height of the power device with the largest device concentration size. The size of each slice in the slice processing comprises a slice width which is the sum of half of a preset width W and a first width Wmax, and the size of each slice comprises a slice height which is the sum of half of a preset height H and a first height Hmax. The preset width and the preset height can be determined according to practical application requirements, and are not limited herein.
S204, inputting each sub-image into a target recognition model to obtain information of each candidate power device, wherein the number of the candidate power devices is multiple.
And respectively inputting each sub-image into a target recognition model, and outputting a result of recognizing each sub-image through the target recognition model, wherein the result of recognizing each sub-image is the information of each candidate power equipment. The object recognition model may be a model for recognizing the power device in the image, and the model structure of the object recognition model is not limited, and the object recognition model may be a model for recognizing the power device in the image based on deep learning.
And if the sub-image contains the candidate power equipment, the identified result comprises the position corresponding to the candidate power equipment, the equipment type corresponding to the candidate power equipment and the confidence degree of the model output result. The position of the candidate power equipment can be a pixel coordinate of a center point of a base of the candidate power equipment, and affine transformation can be carried out on the pixel coordinate in the follow-up process to obtain longitude and latitude coordinates in an actual scene corresponding to the pixel coordinate.
In one embodiment, for any sub-image, before the sub-image is input into the target recognition model, the sub-image may be input into the target frame marking model, the candidate power device is recognized in the sub-image by the target frame marking model, the target frame of the candidate power device is marked, and finally the sub-image marked with the target frame of the candidate power device is output. After the sub-image of the target frame marked with the candidate power equipment is obtained, the sub-image is input into a target recognition model to recognize the candidate power equipment, and then the pixel coordinates of the center point of the base of the candidate power equipment are determined. Wherein the target frame may be a rectangular frame containing candidate power devices.
The target frame marking model may be a model for marking a target frame corresponding to the power device in the image, for example, may be a convolutional neural network (Convolutional Neural Networks, CNN) model, or may be a YOLO model, i.e. "You Only Look Once", which is an algorithm for performing target detection using a convolutional neural network. The present invention is not limited to a specific target frame marking model as long as the power equipment can be detected in the image through the target frame marking model and the target frame of the power equipment can be marked.
The mode of combining the target frame marking model and the target identification model to realize the identification of the power equipment can provide more accurate longitude and latitude coordinates of the power equipment, and improves the accuracy of identifying the power equipment.
S205, integrating and de-duplicating the information of the candidate power equipment obtained by identification to obtain target identification information corresponding to all target power equipment in the remote sensing image to be identified; the de-duplication operation includes: and if the longitude difference and the latitude difference of the two candidate power devices obtained through the different two sub-image recognition are respectively smaller than the corresponding threshold values, determining any one of the two candidate power devices as the target power device.
If the longitude difference and the latitude difference of the two candidate power devices obtained through the recognition of the two different sub-images are respectively smaller than the corresponding threshold values, the two candidate power devices are possibly identical power devices, but exist in the two sub-images at the same time, so that any one of the two candidate power devices can be determined as the target power device, the deduplication operation on the candidate power devices is completed, and the finally obtained target power devices cannot have repeated power devices. After the de-duplication operation is finished, all the target power equipment in the remote sensing image to be identified can be obtained, and then the information corresponding to each target power equipment is determined as target identification information. The threshold value compared with the longitude difference and the latitude difference respectively can be determined according to the actual application requirement, and is not limited herein.
In one embodiment, the object identification information includes at least:
Longitude and latitude coordinates, equipment category and confidence coefficient corresponding to each target power equipment.
The confidence coefficient corresponding to each target power device can be understood as the confidence coefficient of longitude and latitude coordinates and device types corresponding to the target power device. And the longitude and latitude coordinates corresponding to each target power equipment are longitude and latitude coordinates in an actual scene obtained by affine transformation of pixel coordinates of a central point of a base of the target power equipment.
The target identification information may include, but is not limited to: the number of target power devices in the remote sensing image to be identified, the position (namely longitude and latitude coordinates) corresponding to each target power device, the device class corresponding to each target power device, the position corresponding to each target power device and the confidence of the device class.
In one embodiment, the target power device is a transmission tower, and correspondingly, the device class corresponding to the target power device is a class determined according to the shape or the material of the target power device.
When the target power equipment is a transmission tower, the equipment type corresponding to the target power equipment can be a type determined according to the shape or material of the target power equipment, such as a cup-shaped tower, a drum-shaped tower, a cat-head tower, a door-shaped tower, a T-shaped tower, a V-shaped tower, other angle steel towers, a steel pipe tower or a wooden pole tower.
According to the technical scheme provided by the embodiment of the invention, the definition and accuracy of the remote sensing image to be identified can be improved by preprocessing the remote sensing image to be identified; the size of the overlapping area between the adjacent sections is consistent with the size of the power equipment with the largest equipment concentration size, so that each target power equipment to be identified can be at least completely existing in one section, all the target power equipment to be identified in the remote sensing image to be identified can be ensured to be identified, and the missing detection phenomenon of the power equipment can not be generated; the repeated detection of the target power equipment can be avoided through the repeated removal operation, and the accuracy of identifying the power equipment is improved.
According to the technical scheme provided by the embodiment of the invention, the identification speed of the single power equipment can be in the millisecond level, the time cost and the labor cost of the detection of the power wireless private network equipment can be greatly reduced, namely, the identification of the power equipment can be realized with high efficiency and low cost, and the method has higher practical value and market application prospect.
Example III
Fig. 4 is a schematic structural diagram of a device identification apparatus according to a third embodiment of the present invention, where the embodiment is applicable to a case of identifying a power device in a remote sensing image to be identified, as shown in fig. 4, the specific structure of the apparatus includes:
The acquiring module 41 is configured to acquire a remote sensing image to be identified, where the remote sensing image to be identified includes a target power device to be identified;
The slicing module 42 is configured to perform slicing processing on the remote sensing image to be identified to obtain a plurality of sub-images, where a size of an overlapping area between adjacent slices during slicing processing is related to a size of a power device in a device set, and the device set at least includes a target power device to be identified;
the identifying module 43 is configured to perform image identification on each sub-image, integrate and deduplicate information of candidate power devices obtained by identification, and obtain target identification information corresponding to all target power devices in the remote sensing image to be identified.
According to the equipment identification device provided by the embodiment, the remote sensing image to be identified is obtained through the obtaining module, and the remote sensing image to be identified contains target power equipment to be identified; the method comprises the steps that a slicing module is used for slicing a remote sensing image to be identified to obtain a plurality of sub-images, and the size of an overlapping area between adjacent slices is related to the size of power equipment in equipment set, wherein the equipment set at least comprises target power equipment to be identified; and carrying out image recognition on each sub-image through a recognition module, integrating and de-duplicating the information of the candidate power equipment obtained by recognition, and obtaining target recognition information corresponding to all target power equipment in the remote sensing image to be recognized. According to the technical scheme, when the remote sensing image to be identified is subjected to slicing processing, the size of the overlapping area between adjacent slices is related to the size of the power equipment in the equipment set, so that each target power equipment can at least completely exist in one slice, the missing detection phenomenon can be avoided, meanwhile, the repetition of the detected target power equipment can be avoided through the repeated operation, and the accuracy of identifying the power equipment is improved.
Further, the size of the overlapping area between adjacent slices during the slicing process comprises a first width and a first height;
The first width is the width of the power equipment with the largest equipment concentration size;
the first height is the height of the power equipment with the largest equipment concentration size.
Further, the size of each slice in the slice processing comprises a slice width and a slice height;
the slice width is the sum of a preset width and half of the first width;
the slice height is the sum of a preset height and half of the first height.
Further, the identification module 43 is specifically configured to:
and respectively inputting each sub-image into a target recognition model to obtain information of each candidate power device, wherein the number of the candidate power devices is multiple.
Further, the identification module 43 is specifically configured to:
And if the longitude difference and the latitude difference of the two candidate power devices obtained through the different two sub-image recognition are respectively smaller than the corresponding threshold values, determining any one of the two candidate power devices as the target power device.
Further, the target identification information at least includes:
Longitude and latitude coordinates, equipment category and confidence coefficient corresponding to each target power equipment.
Further, the target power equipment is a transmission tower, and correspondingly, the equipment category corresponding to the target power equipment is a category determined according to the shape or the material of the target power equipment.
Further, the device further comprises:
the preprocessing module is used for preprocessing the remote sensing image to be identified after the remote sensing image to be identified is acquired, and the preprocessing comprises one or more of the following steps: radiometric calibration, atmospheric correction, data registration, image fusion, linear stretching, or super resolution.
The device identification device provided by the embodiment of the invention can execute the device identification method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 is a schematic structural diagram of an electronic device implementing a device identification method according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the respective methods and processes described above, such as the device identification method.
In some embodiments, the device identification method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the device identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the device identification method in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (15)
1. A method of device identification, comprising:
Acquiring a remote sensing image to be identified, wherein the remote sensing image to be identified contains target power equipment to be identified;
Slicing the remote sensing image to be identified to obtain a plurality of sub-images, wherein the size of an overlapping area between adjacent slices is related to the size of power equipment in equipment set, and the equipment set at least comprises target power equipment to be identified;
and carrying out image recognition on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by recognition, and obtaining target recognition information corresponding to all target power equipment in the remote sensing image to be recognized.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
The size of the overlapping area between adjacent slices during the slicing process comprises a first width and a first height;
The first width is the width of the power equipment with the largest equipment concentration size;
the first height is the height of the power equipment with the largest equipment concentration size.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
The size of each slice in the slice processing comprises a slice width and a slice height;
the slice width is the sum of a preset width and half of the first width;
the slice height is the sum of a preset height and half of the first height.
4. The method of claim 1, wherein performing image recognition on each sub-image comprises:
and respectively inputting each sub-image into a target recognition model to obtain information of each candidate power device, wherein the number of the candidate power devices is multiple.
5. The method of claim 1, wherein the deduplication operation comprises:
And if the longitude difference and the latitude difference of the two candidate power devices obtained through the different two sub-image recognition are respectively smaller than the corresponding threshold values, determining any one of the two candidate power devices as the target power device.
6. The method according to claim 1, wherein the target identification information comprises at least:
Longitude and latitude coordinates, equipment category and confidence coefficient corresponding to each target power equipment.
7. The method of claim 6, wherein the target power device is a transmission tower, and the device class corresponding to the target power device is a class determined according to a shape or a material of the target power device.
8. The method of claim 1, further comprising, after the acquiring the remote sensing image to be identified:
Preprocessing the remote sensing image to be identified, wherein the preprocessing comprises one or more of the following steps:
radiometric calibration, atmospheric correction, data registration, image fusion, linear stretching, or super resolution.
9. A device identification apparatus, comprising:
the remote sensing image identification device comprises an acquisition module and a recognition module, wherein the acquisition module is used for acquiring a remote sensing image to be identified, and the remote sensing image to be identified contains target power equipment to be identified;
The slicing module is used for slicing the remote sensing image to be identified to obtain a plurality of sub-images, and the size of an overlapping area between adjacent slices is related to the size of the power equipment in the equipment set during slicing, wherein the equipment set at least comprises target power equipment to be identified;
And the identification module is used for carrying out image identification on each sub-image, integrating and de-duplicating the information of the candidate power equipment obtained by identification, and obtaining target identification information corresponding to all target power equipment in the remote sensing image to be identified.
10. The apparatus of claim 9, wherein the device comprises a plurality of sensors,
The size of the overlapping area between adjacent slices during the slicing process comprises a first width and a first height;
The first width is the width of the power equipment with the largest equipment concentration size;
the first height is the height of the power equipment with the largest equipment concentration size.
11. The apparatus of claim 10, wherein the device comprises a plurality of sensors,
The size of each slice in the slice processing comprises a slice width and a slice height;
the slice width is the sum of a preset width and half of the first width;
the slice height is the sum of a preset height and half of the first height.
12. The apparatus according to claim 9, wherein the identification module is specifically configured to:
and respectively inputting each sub-image into a target recognition model to obtain information of each candidate power device, wherein the number of the candidate power devices is multiple.
13. The apparatus according to claim 9, wherein the identification module is specifically configured to:
And if the longitude difference and the latitude difference of the two candidate power devices obtained through the different two sub-image recognition are respectively smaller than the corresponding threshold values, determining any one of the two candidate power devices as the target power device.
14. An electronic device, comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
15. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410078041.6A CN117911891A (en) | 2024-01-18 | 2024-01-18 | Equipment identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410078041.6A CN117911891A (en) | 2024-01-18 | 2024-01-18 | Equipment identification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117911891A true CN117911891A (en) | 2024-04-19 |
Family
ID=90694214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410078041.6A Pending CN117911891A (en) | 2024-01-18 | 2024-01-18 | Equipment identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117911891A (en) |
-
2024
- 2024-01-18 CN CN202410078041.6A patent/CN117911891A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112597837B (en) | Image detection method, apparatus, device, storage medium, and computer program product | |
| CN113971751A (en) | Training feature extraction model, and method and device for detecting similar images | |
| CN112560862B (en) | Text recognition method and device and electronic equipment | |
| CN113139543A (en) | Training method of target object detection model, target object detection method and device | |
| CN112989995B (en) | Text detection method and device and electronic equipment | |
| CN112784732B (en) | Method, device, equipment and medium for identifying and model training of feature type change | |
| CN112528858A (en) | Training method, device, equipment, medium and product of human body posture estimation model | |
| CN112802037A (en) | Portrait extraction method, device, electronic equipment and storage medium | |
| CN113205041A (en) | Structured information extraction method, device, equipment and storage medium | |
| CN112967315A (en) | Target tracking method and device and electronic equipment | |
| CN112507956B (en) | Signal lamp identification method and device, electronic equipment, road side equipment and cloud control platform | |
| CN114359932A (en) | Text detection method, text recognition method and text recognition device | |
| CN113569912A (en) | Vehicle identification method and device, electronic equipment and storage medium | |
| CN113569911A (en) | Vehicle identification method and device, electronic equipment and storage medium | |
| CN113537309B (en) | Object identification method and device and electronic equipment | |
| CN117911891A (en) | Equipment identification method and device, electronic equipment and storage medium | |
| CN115131315A (en) | Image change detection method, device, equipment and storage medium | |
| CN114612971A (en) | Face detection method, model training method, electronic device, and program product | |
| CN113361371A (en) | Road extraction method, device, equipment and storage medium | |
| CN112801078A (en) | Point of interest (POI) matching method and device, electronic equipment and storage medium | |
| CN111428729A (en) | Target detection method and device | |
| CN116229209B (en) | Training method of target model, target detection method and device | |
| CN117746069B (en) | Graph searching model training method and graph searching method | |
| CN113570607B (en) | Target segmentation method and device and electronic equipment | |
| CN117765083A (en) | Equipment positioning method and device, electronic equipment and storage medium |
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 |