CN117373024B - Method, device, electronic equipment and computer readable medium for generating annotation image - Google Patents
Method, device, electronic equipment and computer readable medium for generating annotation image Download PDFInfo
- Publication number
- CN117373024B CN117373024B CN202311666991.2A CN202311666991A CN117373024B CN 117373024 B CN117373024 B CN 117373024B CN 202311666991 A CN202311666991 A CN 202311666991A CN 117373024 B CN117373024 B CN 117373024B
- Authority
- CN
- China
- Prior art keywords
- water color
- marine
- remote sensing
- image
- sensing image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 284
- 238000002372 labelling Methods 0.000 claims abstract description 144
- 238000012549 training Methods 0.000 claims abstract description 98
- 238000005259 measurement Methods 0.000 claims abstract description 64
- 230000004044 response Effects 0.000 claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 239000013598 vector Substances 0.000 claims description 20
- 239000013643 reference control Substances 0.000 claims description 18
- 238000010586 diagram Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 239000013535 sea water Substances 0.000 abstract description 10
- 230000000295 complement effect Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 239000003086 colorant Substances 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000000153 supplemental effect Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 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
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- 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
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the disclosure discloses a method, a device, an electronic device and a computer readable medium for generating an annotation image. One embodiment of the method comprises the following steps: acquiring a historical marine remote sensing image sequence and a historical marine water color labeling image sequence; training the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model; in response to determining that the training marine water color determination model meets the preset training conditions, determining the training marine water color determination model as a target marine water color determination model; acquiring a marine remote sensing image of a target sea area to obtain the marine remote sensing image; generating a sea water color labeling image by utilizing the sea remote sensing image and a target sea water color measuring model; and sending the ocean water color labeling image to a target monitoring terminal. According to the embodiment, automatic labeling of the ocean water color image can be achieved, and efficiency is improved.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a method, an apparatus, an electronic device, and a computer readable medium for generating an annotation image.
Background
Image annotation is a technology for adding annotations to pictures to identify and annotate different areas in the images. At present, when water color labeling is carried out on an ocean remote sensing image, the following modes are generally adopted: and (3) manually labeling, or classifying and labeling the pixels in the marine remote sensing image according to the pixel values of the pixels in the marine remote sensing image.
However, when the marine remote sensing image is adopted for water color labeling, the following technical problems often exist:
firstly, adopt the mode of manual mark to carry out the water color mark to ocean remote sensing image, mark efficiency is lower.
Secondly, the factors causing the change of the ocean water color are complex, and the pixels in the ocean remote sensing image are classified and marked manually or according to the pixel values of the pixels in the ocean remote sensing image, so that the marking result is inaccurate.
Disclosure of Invention
The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a method, apparatus, electronic device, and computer-readable medium for generating an annotation image to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a method of generating an annotation image, the method comprising: acquiring a historical marine remote sensing image and a historical marine water color labeling image of a target sea area to obtain a historical marine remote sensing image sequence and a historical marine water color labeling image sequence, wherein the historical marine remote sensing image in the historical marine remote sensing image sequence consists of ten wave band remote sensing images, and the historical marine remote sensing image in the historical marine remote sensing image sequence and the historical marine water color labeling image in the historical marine water color labeling image sequence correspond one by one; training the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model; in response to determining that the training marine water color determination model meets a preset training condition, determining the training marine water color determination model as a target marine water color determination model; in response to reaching a target time point, acquiring a marine remote sensing image of the target sea area to obtain the marine remote sensing image; generating a marine water color labeling image by using the marine remote sensing image and the target marine water color measuring model; and sending the ocean water color labeling image to a target monitoring terminal.
In a second aspect, some embodiments of the present disclosure provide an annotated image generating apparatus, the apparatus comprising: the first acquisition unit is configured to acquire a historical marine remote sensing image and a historical marine water color labeling image of a target sea area to obtain a historical marine remote sensing image sequence and a historical marine water color labeling image sequence, wherein the historical marine remote sensing image in the historical marine remote sensing image sequence consists of ten wave band remote sensing images, and the historical marine remote sensing image in the historical marine remote sensing image sequence and the historical marine water color labeling image in the historical marine water color labeling image sequence correspond one by one; the training unit is configured to train the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model; a determining unit configured to determine the training marine water color measurement model as a target marine water color measurement model in response to determining that the training marine water color measurement model satisfies a preset training condition; the second acquisition unit is configured to acquire the ocean remote sensing image of the target sea area to obtain the ocean remote sensing image in response to reaching a target time point; a generation unit configured to generate a sea water color labeling image using the sea remote sensing image and the target sea water color measurement model; and the transmitting unit is configured to transmit the ocean water color labeling image to the target monitoring terminal.
In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.
The above embodiments of the present disclosure have the following advantageous effects: the method for transmitting the annotation image can improve the ocean water color annotation efficiency. Specifically, the reason for the low labeling efficiency is that: and (5) performing water color marking on the marine remote sensing image by adopting a manual marking mode. Based on this, in the annotation image generation method of some embodiments of the present disclosure, first, a historical marine remote sensing image and a historical marine water color annotation image of a target sea area are obtained, and a historical marine remote sensing image sequence and a historical marine water color annotation image sequence are obtained, wherein the historical marine remote sensing image in the historical marine remote sensing image sequence is composed of ten-band remote sensing images, and the historical marine remote sensing image in the historical marine remote sensing image sequence and the historical marine water color annotation image in the historical marine water color annotation image sequence correspond one by one. And then training the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model. And then, in response to determining that the training marine water color measurement model meets a preset training condition, determining the training marine water color measurement model as a target marine water color measurement model. Therefore, the target ocean water color measuring model can be obtained through historical image training, and automatic water color labeling of the ocean remote sensing image can be conveniently realized through the target ocean water color measuring model. And then, in response to reaching the target time point, acquiring the ocean remote sensing image of the target sea area to obtain the ocean remote sensing image. And then, generating a sea water color labeling image by using the sea remote sensing image and the target sea water color measuring model. And finally, the ocean water color labeling image is sent to a target monitoring terminal. Therefore, automatic labeling of ocean water color images can be achieved, and efficiency is improved.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a flow chart of some embodiments of a method of generating an annotation image according to the present disclosure;
FIG. 2 is a schematic structural diagram of some embodiments of an annotated image generation apparatus of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
FIG. 1 illustrates a flow of some embodiments of a annotated image generation method according to the present disclosure. The method for generating the annotation image comprises the following steps:
And step 101, acquiring a historical marine remote sensing image and a historical marine water color labeling image of a target sea area, and obtaining a historical marine remote sensing image sequence and a historical marine water color labeling image sequence.
In some embodiments, the execution body of the annotation image generating method may acquire the historical marine remote sensing image and the historical marine water color annotation image of the target sea area through a wired connection mode or a wireless connection mode, so as to obtain a historical marine remote sensing image sequence and a historical marine water color annotation image sequence. The historical marine remote sensing images in the historical marine remote sensing image sequence can be composed of ten wave band remote sensing images. The historical marine remote sensing images in the historical marine remote sensing image sequence and the historical marine water color labeling images in the historical marine water color labeling image sequence correspond one by one. And the pixels of the areas with different water colors in the historical marine water color labeling images in the historical marine water color labeling image sequence are labeled by different colors.
And 102, training the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color annotation image sequence to obtain a training ocean water color measurement model.
In some embodiments, pixels of different water color areas in the historical marine water color labeling images in the historical marine water color labeling image sequence are labeled by different colors.
The executing body trains the initial ocean water color measuring model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measuring model, and the executing body can comprise the following steps:
firstly, selecting an unselected historical marine remote sensing image from the historical marine remote sensing image sequence as a sample marine remote sensing image.
Secondly, executing the following model training substeps by using the sample marine remote sensing image:
and a first model training sub-step, namely inputting the sample marine remote sensing image into an initial marine water color measurement model to obtain an output marine water color labeling image. And the pixels of different water color areas in the output ocean water color labeling image are labeled by different colors. The initial marine water color determination model described above may include 5 convolutions and 3 fully connected layers.
And a second model training sub-step of determining a historical marine water color labeling image corresponding to the sample marine remote sensing image in the historical marine water color labeling image sequence as a sample marine water color labeling image.
And a third model training sub-step, determining the similarity of the output ocean water color labeling image and the sample ocean water color labeling image, and obtaining a similarity value. Wherein a difference between the average of pixel values of the output marine water color annotation image and the sample marine water color annotation image may be determined as a similarity value.
And a fourth model training sub-step of determining that the initial marine water color measurement model is trained in response to determining that the similarity value is less than or equal to the preset similarity value, and determining the initial marine water color measurement model as the target marine water color measurement model. The smaller the similarity value is, the higher the similarity between the output ocean water color labeling image and the sample ocean water color labeling image is.
In practice, the magnitude of the preset similarity value may be set according to actual application needs, which is not limited herein.
And thirdly, in response to determining that the similarity value is greater than the preset similarity value, selecting an unselected historical marine remote sensing image from the historical marine remote sensing image sequence as a sample marine remote sensing image, and continuing to execute the model training substep.
In some optional implementations of some embodiments, the determining, by the executing body, the similarity between the output ocean water color labeling image and the sample ocean water color labeling image to obtain the similarity value may include the following steps:
According to a preset sequence, generating an output image vector and a sample image vector according to pixel values of pixels in the output ocean water color labeling image and the sample ocean water color labeling image. The preset sequence may be a sequence from left to right and from top to bottom.
And a second step of determining a distance value between the output image vector and the sample image vector to obtain a vector distance value.
And thirdly, converting the output ocean water color labeling image and the sample ocean water color labeling image into gray images to obtain an output ocean water color labeling gray image and a sample ocean water color labeling gray image.
And step four, respectively determining average values of pixel values of all pixels in the output ocean water color marking gray level diagram and the sample ocean water color marking gray level diagram to obtain an output average value and a sample average value.
Fifth, according to the preset sequence, for each pixel in the output ocean water color labeling gray map, the following output determination sub-steps are executed:
and a first output determining sub-step of determining a magnitude relation between the pixel value of the pixel and the output average value.
And a second output determining sub-step of adding the first preset value to the output value sequence in response to determining that the pixel value of the pixel is greater than the output average value. Wherein the output value sequence may be initially empty.
As an example, the first preset value may be 1.
And a third output determining sub-step of adding a second preset value to the output value sequence in response to determining that the pixel value of the pixel is equal to or less than the output average value.
As an example, the first preset value may be 2.
Sixth, according to the preset sequence, for each pixel in the sample ocean water color marking gray map, executing the following sample determination sub-steps:
a first sample determination sub-step of determining a magnitude relation between pixel values of the picture elements and the sample average value.
And a second sample determining sub-step of adding the first preset value to the sequence of sample values in response to determining that the pixel value of the pixel is greater than the sample average value. Wherein the sample value sequence may be initially empty.
And a third sample determining sub-step of adding the second preset value to the sample value sequence in response to determining that the pixel value of the pixel is equal to or less than the sample average value.
And seventh, determining the similarity between the output numerical value sequence and the sample numerical value sequence to obtain a similarity distance value. The similarity value between the output value sequence and the sample value sequence may be a distance value between the two vectors after the output value sequence and the sample value sequence are used as vectors.
And eighth, determining a product value of the vector distance value and the similarity distance value as a similarity value.
The step of training the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain the training ocean water color measurement model and the expansion step are taken as an invention point of the embodiment of the disclosure, so that the technical problem mentioned in the background art, namely the water color labeling of the ocean remote sensing image by adopting a manual labeling mode, is further solved, and the labeling efficiency is lower. Factors that cause the above technical problems are often as follows: and (5) performing water color marking on the marine remote sensing image by adopting a manual marking mode. If the above factors are solved, the effect of improving the marking efficiency can be achieved. To achieve this effect, the present disclosure trains an initial marine water color determination model using the above-described historical marine remote sensing image sequence and the above-described historical marine water color labeling image sequence, and determines whether the initial marine water color determination model has been trained by outputting the similarity between the marine water color labeling image and the sample marine water color labeling image. And determining the similarity of the output ocean water color labeling image and the sample ocean water color labeling image by utilizing the difference between the pixel values of each pixel in the output ocean water color labeling image and the sample ocean water color labeling image. Therefore, training of the initial ocean water color measurement model can be achieved by using the verified historical ocean water color annotation images in the historical ocean water color annotation image sequence. Furthermore, the training-completed target ocean water color measurement model can be utilized to realize efficient and rapid ocean water color labeling.
And step 103, determining the training marine water color measuring model as a target marine water color measuring model in response to determining that the training marine water color measuring model meets the preset training condition.
In some embodiments, the executing body may determine the training marine water color determination model as the target marine water color determination model in response to determining that the training marine water color determination model satisfies a preset training condition. The preset training condition may be that a similarity value between the output ocean water color labeling image and the sample ocean water color labeling image is smaller than a preset similarity value.
In some optional implementations of some embodiments, the executing entity further performs the supplemental training by using the training marine water color measurement model as a supplemental training marine water color measurement model in response to determining that the training marine water color measurement model does not meet the preset training condition, and may include the steps of:
and firstly, responding to the arrival of a target time point, and acquiring the ocean remote sensing image of the target sea area to obtain the ocean remote sensing image to be marked. The target time point may be set according to a preset time interval.
In practice, the preset time interval may be set according to actual application requirements, which is not limited herein.
And secondly, sending the ocean remote sensing image to be marked and a marking request to the target monitoring terminal.
And thirdly, acquiring the ocean water color artificial annotation image returned by the target monitoring terminal. The ocean water color manual annotation image is an ocean water color annotation image which is manually annotated and subjected to field verification.
And fourthly, inputting the ocean remote sensing image to be marked into the complementary training ocean water color measuring model to obtain a complementary output marked ocean remote sensing image.
And fifthly, determining the complementary training ocean water color measurement model as a target ocean water color measurement model in response to determining that the similarity value between the complementary output marked ocean remote sensing image and the ocean water color artificial marked image is smaller than or equal to the preset similarity value.
And sixthly, in response to determining that the similarity value between the supplementary output marked marine remote sensing image and the marine water color artificial marked image is larger than the preset similarity value, continuing to carry out supplementary training on the supplementary training marine water color measuring model.
In response to determining that the training ocean water color measurement model does not meet the preset training condition, the step of taking the training ocean water color measurement model as a complementary training ocean water color measurement model to perform complementary training is taken as an invention point of the embodiment of the disclosure, so that the technical problem two mentioned in the background art, namely, factors causing ocean water color change are complex, and labeling results are not accurate enough due to manual work, is solved. Factors that cause the above technical problems are often as follows: the factors that cause the color change of ocean water are complex. If the above factors are solved, the effect of improving the accuracy of the labeling result can be achieved. In order to achieve the effect, the training ocean water color measuring model which is not trained is used as the complementary training ocean water color measuring model to carry out complementary training, after a new ocean remote sensing image to be marked is obtained at a target time point, the ocean remote sensing image to be marked and the marking request are sent to the target monitoring terminal, and therefore the ocean water color manual marking image which is returned by the target monitoring terminal and is marked manually and verified in the field is obtained. And further, training the complementary training ocean water color measurement model by utilizing the ocean remote sensing image to be marked and the ocean water color artificial marking image. Therefore, the final target ocean water color measuring model is sufficiently trained, and the accuracy of the ocean water color labeling image output by the target ocean water color measuring model is ensured to a certain extent.
And 104, responding to the arrival of the target time point, acquiring a marine remote sensing image of the target sea area, and obtaining the marine remote sensing image.
In some embodiments, the executing entity may obtain the marine remote sensing image of the target sea area in response to reaching the target time point, so as to obtain the marine remote sensing image.
And 105, generating a marine water color labeling image by using the marine remote sensing image and the target marine water color measurement model.
In some embodiments, the executing body generates the ocean water color labeling image by using the ocean remote sensing image and the target ocean water color measurement model, and the method may include the following steps:
the first step is to preprocess the ocean remote sensing image to obtain a preprocessed ocean remote sensing image. The preprocessing may be denoising.
And secondly, storing the preprocessed marine remote sensing image as a historical marine remote sensing image.
And thirdly, inputting the preprocessed marine remote sensing image into the target marine water color measuring model to obtain a marine water color labeling image output by the target marine water color measuring model.
In some optional implementations of some embodiments, the performing body may perform preprocessing on the marine remote sensing image to obtain a preprocessed marine remote sensing image, and may include the following steps:
The first step, obtaining the reference control point information of the target sea area, and obtaining a reference control point information set. Wherein, the reference control point information in the reference control point information set may include pixel coordinates.
And secondly, the ocean remote sensing image is sent to the target monitoring terminal to carry out control point labeling.
And thirdly, receiving the control point labeling ocean remote sensing image returned by the target monitoring terminal. The control point labeling marine remote sensing image can comprise at least one labeling control point.
And step four, matching the control point information in the control point information set with the marked control points in the control point marked marine remote sensing graph to obtain control point matching information. The control point matching information comprises at least one group of labeling control point information and reference control point information, and the labeling control point information in the control point matching information comprises pixel coordinates.
And fifthly, correcting the marine remote sensing image by using the control point matching information to obtain a first corrected marine remote sensing image.
Optionally, the executing body matches the control point information in the control point information set with the marked control points in the control point marked marine remote sensing map to obtain control point matching information, which may include the following steps:
A first step of, for each control point information in the set of control point information, performing the following matching sub-steps:
and a first matching sub-step of determining distance values between pixel coordinates in the control point information and pixel coordinates of each marked control point in the control point marked marine remote sensing map to obtain a distance value set.
And a second matching sub-step of determining the marked control point corresponding to the distance value meeting the preset condition in the distance value set as the marked control point matched with the control point information. The preset condition may be that the distance value is the smallest distance value in the distance value set.
Optionally, the performing body corrects the marine remote sensing image by using the control point matching information to obtain a first corrected marine remote sensing image, and may include the following steps:
and a first step of establishing a geometric model according to the control point matching information to obtain a target geometric model. The target geometric model may be a polynomial model and a perspective model.
And secondly, correcting each pixel in the marine remote sensing image by using the target geometric model to obtain a first corrected marine remote sensing image. The first corrected marine remote sensing image consists of ten wave band remote sensing images.
Third, the following correction sub-steps are executed for the remote sensing image of each wave band in the first corrected marine remote sensing image:
and a first correction sub-step, determining the brightness value of the pixel with the minimum brightness in the remote sensing image as a target brightness value.
And a second correction sub-step, updating the brightness value of each pixel in the remote sensing image by using the difference value between the brightness value of each pixel in the remote sensing image and the target brightness value to obtain a preprocessed remote sensing image.
And fourthly, combining the obtained preprocessed remote sensing images of each wave band to obtain the preprocessed marine remote sensing image.
And step 106, transmitting the ocean water color labeling image to a target monitoring terminal.
In some embodiments, the executing body may send the ocean water color labeling image to a target monitoring terminal.
The above embodiments of the present disclosure have the following advantageous effects: the method for transmitting the annotation image can improve the ocean water color annotation efficiency. Specifically, the reason for the low labeling efficiency is that: and (5) performing water color marking on the marine remote sensing image by adopting a manual marking mode. Based on this, in the annotation image generation method of some embodiments of the present disclosure, first, a historical marine remote sensing image and a historical marine water color annotation image of a target sea area are obtained, and a historical marine remote sensing image sequence and a historical marine water color annotation image sequence are obtained, wherein the historical marine remote sensing image in the historical marine remote sensing image sequence is composed of ten-band remote sensing images, and the historical marine remote sensing image in the historical marine remote sensing image sequence and the historical marine water color annotation image in the historical marine water color annotation image sequence correspond one by one. And then training the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model. And then, in response to determining that the training marine water color measurement model meets a preset training condition, determining the training marine water color measurement model as a target marine water color measurement model. Therefore, the target ocean water color measuring model can be obtained through historical image training, and automatic water color labeling of the ocean remote sensing image can be conveniently realized through the target ocean water color measuring model. And then, in response to reaching the target time point, acquiring the ocean remote sensing image of the target sea area to obtain the ocean remote sensing image. And then, generating a sea water color labeling image by using the sea remote sensing image and the target sea water color measuring model. And finally, the ocean water color labeling image is sent to a target monitoring terminal. Therefore, automatic labeling of ocean water color images can be achieved, and efficiency is improved.
With further reference to fig. 2, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a labeling image generation apparatus, which correspond to those method embodiments shown in fig. 1, and which are particularly applicable in various electronic devices.
As shown in fig. 2, the annotated image generating apparatus of some embodiments includes: a first acquisition unit 201, a training unit 202, a determination unit 203, a second acquisition unit 204, a generation unit 205, and a transmission unit 206. The first obtaining unit 201 is configured to obtain a historical marine remote sensing image and a historical marine water color labeling image of a target sea area, so as to obtain a historical marine remote sensing image sequence and a historical marine water color labeling image sequence, wherein the historical marine remote sensing image in the historical marine remote sensing image sequence consists of ten wave band remote sensing images, and the historical marine remote sensing image in the historical marine remote sensing image sequence and the historical marine water color labeling image in the historical marine water color labeling image sequence correspond one by one; a training unit 202 configured to train the initial marine water color measurement model by using the historical marine remote sensing image sequence and the historical marine water color labeling image sequence to obtain a trained marine water color measurement model; a determining unit 203 configured to determine the training marine water color measurement model as a target marine water color measurement model in response to determining that the training marine water color measurement model satisfies a preset training condition; a second obtaining unit 204 configured to obtain a marine remote sensing image of the target sea area in response to reaching a target time point, thereby obtaining a marine remote sensing image; a generation unit 205 configured to generate a sea water color labeling image using the sea remote sensing image and the target sea water color measurement model; and a transmitting unit 206 configured to transmit the ocean water color labeling image to a target monitoring terminal.
It will be appreciated that the elements described in the annotation image generation apparatus correspond to the individual steps in the method described with reference to fig. 1. Thus, the operations, features and advantages described above with respect to the method are equally applicable to the annotation image generating device and the units contained therein, and are not described here again.
Referring now to fig. 3, a schematic diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.
As shown in fig. 3, the electronic device may include a processing means (e.g., a central processor, a graphics processor, etc.) 301 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; and communication means 309. The communication means 309 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.
It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a historical marine remote sensing image and a historical marine water color labeling image of a target sea area to obtain a historical marine remote sensing image sequence and a historical marine water color labeling image sequence, wherein the historical marine remote sensing image in the historical marine remote sensing image sequence consists of ten wave band remote sensing images, and the historical marine remote sensing image in the historical marine remote sensing image sequence and the historical marine water color labeling image in the historical marine water color labeling image sequence correspond one by one; training the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model; in response to determining that the training marine water color determination model meets a preset training condition, determining the training marine water color determination model as a target marine water color determination model; in response to reaching a target time point, acquiring a marine remote sensing image of the target sea area to obtain the marine remote sensing image; generating a marine water color labeling image by using the marine remote sensing image and the target marine water color measuring model; and sending the ocean water color labeling image to a target monitoring terminal.
Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes a first acquisition unit, a training unit, a determination unit, a second acquisition unit, a generation unit, and a transmission unit. The names of these units do not constitute a limitation on the unit itself in some cases, and for example, a transmission unit may also be described as "a unit that transmits an image".
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
Claims (10)
1. A method of generating an annotation image, comprising:
acquiring a historical marine remote sensing image and a historical marine water color labeling image of a target sea area to obtain a historical marine remote sensing image sequence and a historical marine water color labeling image sequence, wherein the historical marine remote sensing image in the historical marine remote sensing image sequence consists of ten wave band remote sensing images, and the historical marine remote sensing image in the historical marine remote sensing image sequence and the historical marine water color labeling image in the historical marine water color labeling image sequence correspond one by one;
Training an initial ocean water color measurement model by utilizing the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model;
in response to determining that the training marine water color determination model meets a preset training condition, determining the training marine water color determination model as a target marine water color determination model;
in response to reaching a target time point, acquiring a marine remote sensing image of the target sea area to obtain a marine remote sensing image;
generating a marine water color labeling image by utilizing the marine remote sensing image and the target marine water color measuring model;
the ocean water color labeling image is sent to a target monitoring terminal;
the training of the initial ocean water color measurement model by using the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model comprises the following steps:
selecting an unselected historical marine remote sensing image from the historical marine remote sensing image sequence as a sample marine remote sensing image;
executing the following model training substeps by using the sample marine remote sensing image:
inputting the sample marine remote sensing image into an initial marine water color measurement model to obtain an output marine water color labeling image;
Determining a historical marine water color labeling image corresponding to the sample marine remote sensing image in the historical marine water color labeling image sequence as a sample marine water color labeling image;
determining the similarity of the output ocean water color labeling image and the sample ocean water color labeling image to obtain a similarity value;
determining that the initial marine water color measurement model is trained in response to determining that the similarity value is less than or equal to the preset similarity value, and determining the initial marine water color measurement model as a target marine water color measurement model;
in response to determining that the similarity value is greater than the preset similarity value, selecting an unselected historical marine remote sensing image from the sequence of historical marine remote sensing images as a sample marine remote sensing image, and continuing to perform the model training sub-step;
the method for determining the similarity between the output ocean water color labeling image and the sample ocean water color labeling image to obtain a similarity value comprises the following steps:
according to a preset sequence, generating an output image vector and a sample image vector according to pixel values of each pixel in the output ocean water color labeling image and the sample ocean water color labeling image;
determining a distance value between the output image vector and the sample image vector to obtain a vector distance value;
Converting the output ocean water color annotation image and the sample ocean water color annotation image into gray images to obtain an output ocean water color annotation gray image and a sample ocean water color annotation gray image;
respectively determining average values of pixel values of all pixels in the output ocean water color marking gray level diagram and the sample ocean water color marking gray level diagram to obtain an output average value and a sample average value;
according to the preset sequence, for each pixel in the output ocean water color annotation gray scale map, the following output determination sub-steps are executed:
determining a magnitude relation between a pixel value of the pixel and the output average value;
responsive to determining that the pixel value of the pixel is greater than the output average, adding a first preset value to the sequence of output values;
in response to determining that the pixel value of the pixel is less than or equal to the output average value, adding a second preset value to the sequence of output values;
according to the preset sequence, for each pixel in the sample ocean water color marking gray map, the following sample determination sub-steps are executed:
determining a magnitude relation between a pixel value of the pixel and the sample average value;
Responsive to determining that the pixel value of the pixel is greater than the sample average, adding the first preset value to a sequence of sample values;
in response to determining that the pixel value of the pixel is less than or equal to the sample average value, adding the second preset value to the sequence of sample values;
determining the similarity between the output numerical value sequence and the sample numerical value sequence to obtain a similarity distance value;
and determining a product value of the vector distance value and the similarity distance value as a similarity value.
2. The method of claim 1, wherein the generating a marine water color annotation image using the marine remote sensing image and the target marine water color determination model comprises:
preprocessing the ocean remote sensing image to obtain a preprocessed ocean remote sensing image;
storing the preprocessed marine remote sensing image as a historical marine remote sensing image;
and inputting the preprocessed marine remote sensing image into the target marine water color measuring model to obtain a marine water color labeling image output by the target marine water color measuring model.
3. The method of claim 2, wherein the preprocessing the marine remote sensing image to obtain a preprocessed marine remote sensing image comprises:
Acquiring reference control point information of the target sea area to obtain a reference control point information set, wherein the reference control point information in the reference control point information set comprises pixel coordinates;
the ocean remote sensing image is sent to the target monitoring terminal to carry out control point labeling;
receiving a control point marked marine remote sensing image returned by the target monitoring terminal, wherein the control point marked marine remote sensing image comprises at least one marked control point;
matching the reference control point information in the reference control point information set with the marked control points in the control point marked marine remote sensing image to obtain control point matching information, wherein the control point matching information comprises at least one group of marked control point information and reference control point information, and the marked control point information in the control point matching information comprises pixel coordinates;
and correcting the marine remote sensing image by using the control point matching information to obtain a first corrected marine remote sensing image.
4. The method of claim 3, wherein the matching the reference control point information in the reference control point information set with the labeled control points in the control point labeled marine remote sensing image to obtain control point matching information comprises:
For each reference control point information in the set of reference control point information, performing the following matching sub-steps:
determining a distance value between a pixel coordinate in the reference control point information and a pixel coordinate of each labeling control point in the control point labeling ocean remote sensing image to obtain a distance value set;
and determining a labeling control point corresponding to a distance value meeting a preset condition in the distance value set as a labeling control point matched with the reference control point information, wherein the preset condition is that the distance value is the smallest distance value in the distance value set.
5. The method of claim 4, wherein correcting the marine remote sensing image using the control point matching information results in a first corrected marine remote sensing image, comprising:
establishing a geometric model according to the control point matching information to obtain a target geometric model;
and correcting each pixel in the marine remote sensing image by using the target geometric model to obtain a first corrected marine remote sensing image.
6. The method of claim 5, wherein the first corrected marine telemetry image consists of ten bands of telemetry images; and
The preprocessing of the ocean remote sensing image to obtain a preprocessed ocean remote sensing image further comprises:
the following correction sub-steps are performed on the remote sensing image of each wave band in the first corrected marine remote sensing image:
determining the brightness value of the pixel with the minimum brightness in the remote sensing image as a target brightness value;
updating the brightness value of each pixel in the remote sensing image by utilizing the difference value between the brightness value of each pixel in the remote sensing image and the target brightness value to obtain a preprocessed remote sensing image;
and combining the obtained preprocessed remote sensing images of each wave band to obtain the preprocessed marine remote sensing image.
7. The method of claim 1, wherein the method further comprises:
and in response to determining that the training marine water color determination model does not meet the preset training conditions, taking the training marine water color determination model as a supplementary training marine water color determination model for supplementary training.
8. An annotated image generation apparatus, comprising:
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is configured to acquire a historical marine remote sensing image and a historical marine water color labeling image of a target sea area to obtain a historical marine remote sensing image sequence and a historical marine water color labeling image sequence, the historical marine remote sensing image in the historical marine remote sensing image sequence consists of ten wave band remote sensing images, and the historical marine remote sensing images in the historical marine remote sensing image sequence and the historical marine water color labeling images in the historical marine water color labeling image sequence correspond one by one;
The training unit is configured to train the initial ocean water color measurement model by utilizing the historical ocean remote sensing image sequence and the historical ocean water color labeling image sequence to obtain a training ocean water color measurement model;
a determining unit configured to determine the training marine water color determination model as a target marine water color determination model in response to determining that the training marine water color determination model satisfies a preset training condition;
the second acquisition unit is configured to acquire a marine remote sensing image of the target sea area in response to reaching a target time point, so as to obtain the marine remote sensing image;
a generation unit configured to generate a marine water color annotation image using the marine remote sensing image and the target marine water color measurement model;
a transmitting unit configured to transmit the marine water color annotation image to a target monitoring terminal;
wherein the training unit is further configured to:
selecting an unselected historical marine remote sensing image from the historical marine remote sensing image sequence as a sample marine remote sensing image;
executing the following model training substeps by using the sample marine remote sensing image:
inputting the sample marine remote sensing image into an initial marine water color measurement model to obtain an output marine water color labeling image;
Determining a historical marine water color labeling image corresponding to the sample marine remote sensing image in the historical marine water color labeling image sequence as a sample marine water color labeling image;
determining the similarity of the output ocean water color labeling image and the sample ocean water color labeling image to obtain a similarity value;
determining that the initial marine water color measurement model is trained in response to determining that the similarity value is less than or equal to the preset similarity value, and determining the initial marine water color measurement model as a target marine water color measurement model;
in response to determining that the similarity value is greater than the preset similarity value, selecting an unselected historical marine remote sensing image from the sequence of historical marine remote sensing images as a sample marine remote sensing image, and continuing to perform the model training sub-step;
the method for determining the similarity between the output ocean water color labeling image and the sample ocean water color labeling image to obtain a similarity value comprises the following steps:
according to a preset sequence, generating an output image vector and a sample image vector according to pixel values of each pixel in the output ocean water color labeling image and the sample ocean water color labeling image;
determining a distance value between the output image vector and the sample image vector to obtain a vector distance value;
Converting the output ocean water color annotation image and the sample ocean water color annotation image into gray images to obtain an output ocean water color annotation gray image and a sample ocean water color annotation gray image;
respectively determining average values of pixel values of all pixels in the output ocean water color marking gray level diagram and the sample ocean water color marking gray level diagram to obtain an output average value and a sample average value;
according to the preset sequence, for each pixel in the output ocean water color annotation gray scale map, the following output determination sub-steps are executed:
determining a magnitude relation between a pixel value of the pixel and the output average value;
responsive to determining that the pixel value of the pixel is greater than the output average, adding a first preset value to the sequence of output values;
in response to determining that the pixel value of the pixel is less than or equal to the output average value, adding a second preset value to the sequence of output values;
according to the preset sequence, for each pixel in the sample ocean water color marking gray map, the following sample determination sub-steps are executed:
determining a magnitude relation between a pixel value of the pixel and the sample average value;
Responsive to determining that the pixel value of the pixel is greater than the sample average, adding the first preset value to a sequence of sample values;
in response to determining that the pixel value of the pixel is less than or equal to the sample average value, adding the second preset value to the sequence of sample values;
determining the similarity between the output numerical value sequence and the sample numerical value sequence to obtain a similarity distance value;
and determining a product value of the vector distance value and the similarity distance value as a similarity value.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.
10. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311666991.2A CN117373024B (en) | 2023-12-07 | 2023-12-07 | Method, device, electronic equipment and computer readable medium for generating annotation image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311666991.2A CN117373024B (en) | 2023-12-07 | 2023-12-07 | Method, device, electronic equipment and computer readable medium for generating annotation image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117373024A CN117373024A (en) | 2024-01-09 |
| CN117373024B true CN117373024B (en) | 2024-03-08 |
Family
ID=89404412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311666991.2A Active CN117373024B (en) | 2023-12-07 | 2023-12-07 | Method, device, electronic equipment and computer readable medium for generating annotation image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117373024B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108428220A (en) * | 2018-03-05 | 2018-08-21 | 武汉大学 | Satellite sequence remote sensing image sea island reef region automatic geometric correction method |
| CN110866900A (en) * | 2019-11-05 | 2020-03-06 | 江河瑞通（北京）技术有限公司 | Water body color identification method and device |
| CN111307727A (en) * | 2020-03-13 | 2020-06-19 | 生态环境部卫星环境应用中心 | Water body water color abnormity identification method and device based on time sequence remote sensing image |
| CN113177183A (en) * | 2021-06-29 | 2021-07-27 | 广东海洋大学 | Seawater pollution monitoring and early warning method and system based on ocean remote sensing image |
| CN117111092A (en) * | 2023-07-19 | 2023-11-24 | 苏州梦伯乐信息科技有限公司 | High-spatial-resolution remote sensing water quality detection method based on machine learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5254893B2 (en) * | 2009-06-26 | 2013-08-07 | キヤノン株式会社 | Image conversion method and apparatus, and pattern identification method and apparatus |
-
2023
- 2023-12-07 CN CN202311666991.2A patent/CN117373024B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108428220A (en) * | 2018-03-05 | 2018-08-21 | 武汉大学 | Satellite sequence remote sensing image sea island reef region automatic geometric correction method |
| CN110866900A (en) * | 2019-11-05 | 2020-03-06 | 江河瑞通（北京）技术有限公司 | Water body color identification method and device |
| CN111307727A (en) * | 2020-03-13 | 2020-06-19 | 生态环境部卫星环境应用中心 | Water body water color abnormity identification method and device based on time sequence remote sensing image |
| CN113177183A (en) * | 2021-06-29 | 2021-07-27 | 广东海洋大学 | Seawater pollution monitoring and early warning method and system based on ocean remote sensing image |
| CN117111092A (en) * | 2023-07-19 | 2023-11-24 | 苏州梦伯乐信息科技有限公司 | High-spatial-resolution remote sensing water quality detection method based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 海洋水色卫星遥感算法综述;陈淼;《中国优秀博硕士学位论文全文数据库 (硕士) 基础科学辑》;20051215;第2005年卷(第08期);A010-2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117373024A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113487608B (en) | Endoscope image detection method, endoscope image detection device, storage medium, and electronic apparatus | |
| US11417014B2 (en) | Method and apparatus for constructing map | |
| CN113469295B (en) | Training method for generating model, polyp recognition method, device, medium, and apparatus | |
| CN116182878B (en) | Road curved surface information generation method, device, equipment and computer readable medium | |
| CN115578570A (en) | Image processing method, device, readable medium and electronic equipment | |
| CN114708150A (en) | Scanning data processing method and device, electronic equipment and medium | |
| EP4318398A1 (en) | Calibration and verification method and apparatus for intrinsic camera parameter, device, and medium | |
| CN113592033B (en) | Oil tank image recognition model training method, oil tank image recognition method and device | |
| CN115272667B (en) | Farmland image segmentation model training method and device, electronic equipment and medium | |
| CN115620264B (en) | Vehicle positioning method and device, electronic equipment and computer readable medium | |
| CN117373024B (en) | Method, device, electronic equipment and computer readable medium for generating annotation image | |
| CN113808134B (en) | Oil tank layout information generation method, oil tank layout information generation device, electronic apparatus, and medium | |
| CN112418233B (en) | Image processing method and device, readable medium and electronic equipment | |
| CN116248991A (en) | Camera position adjustment method, camera position adjustment device, electronic equipment and computer readable medium | |
| CN111680754B (en) | Image classification method, device, electronic equipment and computer readable storage medium | |
| CN112597788B (en) | Target measuring method, target measuring device, electronic apparatus, and computer-readable medium | |
| CN115187510A (en) | Loop detection method, device, electronic equipment and medium | |
| CN116630436B (en) | Camera external parameter correction method, camera external parameter correction device, electronic equipment and computer readable medium | |
| CN112862110B (en) | Model generation method and device and electronic equipment | |
| CN113542800B (en) | Video picture scaling method, device and terminal equipment | |
| CN115345931B (en) | Object attitude key point information generation method and device, electronic equipment and medium | |
| CN116010289B (en) | Automatic driving simulation scene test method and device, electronic equipment and readable medium | |
| CN115170674B (en) | Camera principal point calibration method, device, equipment and medium based on single image | |
| CN114554108B (en) | Image processing method and device and electronic equipment | |
| CN115292540B (en) | Multi-mode part information identification method, device, equipment and computer readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |